System

Abstract

A system is provided.SOLUTION: A system including a dialogue management means for allowing a user to have a dialogue with a generation AI via a terminal, a determination means for analyzing dialogue contents obtained via the dialogue management means and determining a suspicion of harassment, an evidence collection means for automatically starting recording and photographing on a terminal when the suspicion of harassment is determined by the determination means, a data management means for safely encrypting evidence data collected by the evidence collection means and uploading the evidence data to a server, and a reporting means for automatically reporting the evidence data uploaded to the server to a related department or public institution.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, harassment in the workplace, schools, and elsewhere has become a serious social problem, yet it remains difficult for victims to report harassment and take action toward a resolution. Specifically, victims often do not know how to report harassment appropriately, or are anxious about the time and risk involved in collecting evidence and how to respond after reporting. As a result, many cases of harassment go unnoticed, and victims continue to suffer. The present invention aims to solve these problems and provide a system that allows victims to report harassment more easily and safely and receive appropriate support. [Means for solving the problem]

[0005] The present invention enables victims to easily and safely report harassment and receive necessary support through a system that includes a dialogue management means that allows users to interact with generative AI via a terminal, a judgment means that analyzes the content of the dialogue obtained through the dialogue management means and determines whether harassment is suspected, an evidence collection means that automatically starts recording and filming on the terminal if the judgment means determines that harassment is suspected, a data management means that securely encrypts the evidence data collected by the evidence collection means and uploads it to a server, and a reporting means that analyzes the evidence data uploaded to the server and automatically reports it to the relevant departments and public institutions.

[0006] Specifically, the user uses a device to interact with the generative AI and sends the content to a server. The server analyzes the received content using a natural language processing engine, and if it determines that harassment is suspected, it instructs the device to begin collecting evidence. The device receives the instruction, automatically collects audio and video, encrypts the data, and securely uploads it to the server. The server analyzes the collected data, converts it into a standardized reporting format, and notifies the relevant departments and public institutions. It also automatically contacts mental health clinics to provide mental health support if necessary.

[0007] "User" means an individual or organization that uses this system to report harassment or collect evidence.

[0008] A "terminal" is an electronic device used by a user, such as a smartphone, tablet, or PC.

[0009] "Generative AI" is an artificial intelligence technology that understands users' text and voice input and generates natural dialogue.

[0010] A "dialogue management means" is a component that provides an interface and functionality for users to interact with generative AI.

[0011] The "determination means" is a function that analyzes the content of the dialogue obtained via the dialogue management means and determines the possibility of harassment.

[0012] The "evidence collection means" is a function that automatically records and photographs recordings when the assessment means determines that harassment is suspected.

[0013] "Data management means" is a function for encrypting collected evidence data and uploading it securely to a server.

[0014] The "server" is a central processing unit that stores, analyzes, and reports the contents of conversations and evidence data.

[0015] "Reporting means" is a function that automatically reports evidential data uploaded to the server to relevant departments and public institutions. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[0038] Hearing phase

[0039] 1. The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[0040] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0041] 2. The terminal transmits the user's input in real time to the server, which has a means of analyzing the content of the conversation and determining whether it constitutes harassment.

[0042] Judgment Phase

[0043] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine to determine whether it is suspected of harassment. At this time, the content is scored by a judgment means, and if it exceeds a certain threshold, the process proceeds to the next step.

[0044] Evidence Gathering Phase

[0045] 4. If the server judges that harassment is highly suspected, it sends a command to the device to start automatic recording or video recording. The device receives this command and automatically starts recording audio or video.

[0046] The device captures and encodes audio data to record what is happening around the user.

[0047] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[0048] 6. The device uploads the encrypted data to the server.

[0049] Reporting Phase

[0050] 7. The server receives the uploaded evidence data and analyzes it, using speech recognition technology to convert the audio data into text and extract the key parts.

[0051] 8. The server creates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0052] 9. The server automatically sends a report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The report is sent via email or a dedicated portal.

[0053] Feedback Phase

[0054] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[0055] For example: "Your report was successfully submitted. Please wait for our response."

[0056] Mental care support

[0057] 11. If the server determines that the user needs mental health care, it will automatically contact a mental health clinic and, with the user's consent, arrange an appointment with a specialist.

[0058] The above is a specific form for implementing the invention. This system allows victims to easily and safely report harassment and receive prompt support. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[0062] Step 2:

[0063] The device sends the user's input, including text and voice data, to the server in real time.

[0064] Step 3:

[0065] The server analyzes the conversation content received using a natural language processing (NLP) engine to determine whether it is suspected of harassment. Based on the analysis results, a certain score is generated.

[0066] Step 4:

[0067] If the server finds that the score exceeds a certain threshold, it determines that harassment is suspected and moves on to the evidence collection phase.

[0068] Step 5:

[0069] The server sends a command to the device to start automatic recording and shooting. The device receives this command and automatically starts recording and shooting audio and video.

[0070] Step 6:

[0071] The device encrypts the evidence data (audio, video) collected and uploads the data to a server.

[0072] Step 7:

[0073] The server receives and analyzes the uploaded evidence data, converting audio data into text using speech recognition technology and extracting key parts.

[0074] Step 8:

[0075] The server generates a standardized report format based on the analysis results, which includes a summary of the problem and links to supporting data.

[0076] Step 9:

[0077] The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., police, labor standards inspection office) via email or a dedicated portal.

[0078] Step 10:

[0079] The server then provides the user with a status update and feedback on next steps. The user receives a notification within the application.

[0080] Step 11:

[0081] The server provides mental health support to the user as needed, and with the user's consent, contacts and arranges appointments with mental health clinics.

[0082] Example 1

[0083] 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."

[0084] In the past, proper reporting and support for harassment required specialized knowledge and time, making it difficult for victims to receive prompt action. Furthermore, there was no comprehensive system in place to handle the entire process, including collecting and safely managing evidence, properly reporting to the relevant authorities, and providing mental health care. This created a mental burden for victims, making them hesitant to report harassment.

[0085] 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.

[0086] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, a feedback means for sending a notification to the user after reporting and providing feedback, and a support means for determining the need for mental health care and contacting a medical institution if necessary. This enables prompt reporting of harassment, safe management of evidence, reporting to appropriate relevant institutions, and mental health care support for users.

[0087] "User" refers to a person who uses this system to report harassment issues and receive support.

[0088] "Terminal" refers to a device used by a user that has a dedicated application installed for interacting with generative AI.

[0089] "Generative AI" refers to artificial intelligence technology that understands user input and responds appropriately.

[0090] "Dialogue management means" refers to the function of managing the dialogue between the user and generative AI and processing the data appropriately.

[0091] "Determination means" refers to a function that analyzes the content of conversations with generative AI and determines whether there is any suspicion of harassment.

[0092] "Evidence collection means" refers to a function that automatically records and photographs audio and video on the device if harassment is suspected.

[0093] "Data management means" refers to the function for securely encrypting collected evidence data and uploading it to a server.

[0094] A "server" refers to a central computer that manages the entire system and analyzes and communicates various data.

[0095] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0096] "Feedback mechanism" refers to the functionality to send notifications to users after a report is made and provide feedback on status updates and next steps.

[0097] "Support measures" refers to the function of determining the need for mental care and contacting a medical institution when necessary.

[0098] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[0099] The system begins when a user interacts with the generative AI using a device with a dedicated application installed. The interaction is conducted via text input or voice input, and the content is sent to the server.

[0100] Dialogue Management

[0101] The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text input or voice input. For example, the user might type, "Recently, my boss at work has been verbally abusing me almost every day." The device then sends the user's input to the server in real time. At this time, the device temporarily stores the input in a buffer and transmits it over the internet using a secure communication protocol (e.g., HTTPS).

[0102] Judgment means

[0103] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API) to determine whether there is any suspicion of harassment. This determination is based on a scoring system, and if the score exceeds a certain threshold, the system proceeds to the next phase.

[0104] Evidence collection

[0105] If harassment is suspected, the server sends a command to the device to start automatic recording and filming. The device automatically starts recording audio or video when instructed to do so using its built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in the device's storage. The device then uploads the encrypted data to the server. The device uses the HTTPS protocol to securely and quickly send the data to the server.

[0106] Data Management and Reporting

[0107] The server receives the uploaded evidence data and, if it is audio data, converts it into text using speech recognition technology (e.g., IBM Watson Speech to Text API). Video data is analyzed in the same way. The server creates a standardized report format based on the analysis results. The report includes a summary of the problem, a link to the collected evidence data, and the analysis results. The server sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The server sends the report using a pre-configured mail server or dedicated portal.

[0108] Feedback tools and mental health support

[0109] After reporting, the server sends a notification to the user, providing an update on the situation and feedback on next steps. For example, a notification stating "The report was sent successfully. Please wait for our response" may be displayed on the device. Furthermore, if the server determines that the user needs mental health care, it can use the Google Calendar API to arrange an appointment with a mental health clinic and send a notification to the user.

[0110] This system allows victims to easily and safely report harassment and receive prompt action. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[0111] Prompt Sentence Examples

[0112] "I feel like I am being verbally abused by my boss at work every day. Please tell me the steps to report this and how to gather evidence."

[0113] When the user inputs information based on this prompt, the generative AI can provide appropriate support to the user and respond quickly and safely.

[0114] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0115] Step 1:

[0116] A user begins a dialogue with the generative AI using a device with a dedicated application installed. The user describes the harassment situation they are facing using text input or voice input. For example, they might say, "Recently, my boss at work has been verbally abusing me almost every day." The input data is then imported into the device in text format.

[0117] Input: The user inputs information about the harassment into the device using text or voice.

[0118] Output: The terminal temporarily stores the user's input as text data and sends it to the next process.

[0119] Step 2:

[0120] The device sends the user's input to the server in real time. The device stores the input in a buffer and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0121] Input: User input (text data).

[0122] Output: The user's input sent to the server.

[0123] Step 3:

[0124] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API). Based on this analysis, the server scores the likelihood of harassment and proceeds to the next step if the score exceeds a certain threshold.

[0125] Input: User input sent to the server.

[0126] Output: Scoring data as the analysis result.

[0127] The server passes the input text data to a natural language processing engine, which analyzes it for keywords and context that suggest harassment, and scores it based on the results of this analysis.

[0128] Step 4:

[0129] If the server determines that there is a strong suspicion of harassment, it will send instructions to the device to automatically start recording and filming.

[0130] Input: Analysis results (scoring data).

[0131] Output: Automatic recording and shooting instructions to the device.

[0132] Step 5:

[0133] The device receives the command and automatically starts recording audio or video using the built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in storage.

[0134] Input: Automatic recording and shooting instructions from the server.

[0135] Output: Encrypted audio or video data.

[0136] Step 6:

[0137] The device uploads the encrypted evidence data to the server. The device uses the HTTPS protocol to send the data to the server safely and quickly.

[0138] Input: Encrypted audio or video data.

[0139] Output: The encrypted data uploaded to the server.

[0140] Step 7:

[0141] The server receives the uploaded evidence data and converts it into text using voice recognition technology (e.g., IBM Watson Speech to Text API) if it is audio data. Video data is also analyzed in the same way.

[0142] Input: Encrypted evidence data.

[0143] Output: Parsed data converted to text.

[0144] Step 8:

[0145] The server then generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0146] Input: Parsed data converted to text.

[0147] Output: Standardized report.

[0148] Step 9:

[0149] The server automatically sends reports to the relevant departments and public institutions using a pre-configured mail server or dedicated portal.

[0150] Input: Standardized report.

[0151] Output: Reports sent to responsible departments and public authorities.

[0152] Step 10:

[0153] After the server reports, it will send a notification to the user to provide a status update and feedback on next steps, such as a notification displayed on the device stating "Report submitted successfully. Please wait for our response."

[0154] Input: Report status data.

[0155] Output: Feedback notification to the user.

[0156] Step 11:

[0157] If the server determines that the user needs mental health care, it will automatically contact a mental health clinic. The server can use the Google Calendar API or similar to arrange an appointment with the mental health clinic and send a notification to the user.

[0158] Input: A determination of the user's mental health needs.

[0159] Output: Mental clinic appointment notification.

[0160] (Application example 1)

[0161] 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."

[0162] Conventional harassment reporting systems require users to manually collect evidence, create a report, and report to a public institution or department in charge, which is time-consuming and makes it difficult to respond quickly.The present invention aims to provide a system that allows users to quickly and easily report harassment and receive appropriate support promptly.

[0163] 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.

[0164] In this invention, the server includes a dialogue management means for a user to dialogue with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and a hearing means for the generative AI to transmit the dialogue content to the server in real time when the user inputs voice or text into a predetermined input means. This enables users to easily report harassment and quickly receive appropriate support and mental care.

[0165] The "dialogue management means" provides a function that allows users to interact with generative AI via a terminal.

[0166] The "determination means" has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[0167] The "evidence collection means" is a function that automatically starts recording or photographing on the terminal when the assessment means determines that harassment is suspected.

[0168] The "data management means" has a function for safely encrypting the evidence data collected by the evidence collection means and uploading it to a server.

[0169] The "reporting means" has the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0170] A "hearing means" is a function that allows the generative AI to send the content of the dialogue to a server in real time when the user inputs voice or text into a specified input means.

[0171] "Generative AI" refers to artificial intelligence technology that generates dialogue based on user input and analyzes the content of the dialogue.

[0172] "Device" refers to a terminal used by a user, such as a smartphone, smart glasses, a head-mounted display, or a robot.

[0173] "Encryption" refers to a technology for protecting data from being leaked to third parties while maintaining its security.

[0174] A "natural language processing engine" includes technology for analyzing and understanding the meaning of user input.

[0175] This invention provides a system that allows users to quickly and easily report harassment issues and receive appropriate support. Specifically, it has the following configuration.

[0176] System Overview

[0177] The system includes the following means for interacting with generative AI using a user's device to determine whether harassment is suspected.

[0178] Dialogue Management Tools

[0179] Judgment means

[0180] Evidence collection methods

[0181] Data Management Measures

[0182] Reporting means

[0183] Hearing methods

[0184] Hardware and software used

[0185] Hardware: Smartphones, smart glasses, head-mounted displays, robots, etc.

[0186] Software: Python, Requests library, SpeechRecognition library, Natural Language Processing engine (e.g. spaCy or NLTK)

[0187] Program processing

[0188] User Input and Hearing Phase

[0189] The user uses a designated device (e.g., a smartphone) to initiate a dialogue with the generative AI. The user registers details of the harassment through voice or text input. At this time, the generative AI sends the user's input to the server in real time. Examples of prompt sentences include the following:

[0190] "I'm having trouble with verbal abuse from my boss at work."

[0191] "I'm being harassed by my classmates at school."

[0192] Assessment and evidence gathering phase

[0193] The server analyzes the received user input using a natural language processing engine to determine whether there is any suspicion of harassment. If there is any suspicion, the server sends instructions to the device to automatically record and record audio and video. The device then receives the instructions, automatically collects audio and video from the surrounding area, and securely encrypts the data.

[0194] Data management and analysis phase

[0195] The encrypted evidence data is uploaded to a server, which analyzes the uploaded data and automatically notifies the relevant departments and public institutions. Specifically, the collected evidence data is converted into a standardized report format and sent via email or a dedicated portal.

[0196] Feedback Phase

[0197] If the report is successful, the user is notified and given feedback on progress and next steps, and the server is available to assist the user in providing additional information or asking questions.

[0198] Mental care support

[0199] Finally, if the server determines that the user needs mental health care, it will automatically schedule an appointment with a specialist with the user's consent, allowing the user to receive appropriate support promptly.

[0200] The above is a specific embodiment of the present invention. This system allows users to easily report harassment and receive prompt support and assistance. Furthermore, the system automatically notifies the appropriate authorities and provides mental health care, allowing users to use the system with peace of mind.

[0201] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0202] Step 1:

[0203] The user initiates a dialogue with the generative AI via a device. The user registers details of the harassment using voice or text input. Examples of input include:

[0204] "I'm having trouble with verbal abuse from my boss at work."

[0205] "I'm being harassed by my classmates at school."

[0206] Input data is sent from the terminal to the server in real time.

[0207] Step 2:

[0208] The server analyzes the received user input data using a natural language processing engine. Specifically, it tokenizes the input text and analyzes its meaning. The server determines whether the input is suspected of harassment and assigns a score. This analysis uses a generative AI model.

[0209] Input: User-entered text or voice data

[0210] Output: Suspected harassment score

[0211] Step 3:

[0212] If the server determines that harassment is suspected, it will send an instruction to the device to automatically record and record. When the device receives this instruction, it will automatically collect audio and video from the surrounding area. The collected data is immediately encrypted.

[0213] Input: Server recording start instruction

[0214] Output: Encrypted audio and video data

[0215] Step 4:

[0216] The evidence data encrypted on the device is uploaded to a server, where it is analyzed and reported to the relevant departments and public institutions. Specifically, the evidence data is converted into a standardized reporting format and sent via email or a dedicated portal.

[0217] Input: Encrypted evidence data

[0218] Output: Report and transmission log

[0219] Step 5:

[0220] If the report is successful, the server sends a notification to the user. The feedback includes information about the report result and next steps. The user can also provide additional information or ask questions, and an interface is provided for this.

[0221] Input: Report result, additional information

[0222] Output: Notification and feedback to the user

[0223] Step 6:

[0224] The server determines the user's mental health needs and automatically schedules appointments with specialists if necessary. This appointment requires the user's consent, and arrangements are made only after the consent is confirmed.

[0225] Input: User consent, mental health care need data

[0226] Output: Specialist appointment information and user notification

[0227] The above are the specific processing steps for carrying out the present invention, which enable users to quickly and easily report harassment and receive appropriate support.

[0228] 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.

[0229] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system improves analysis accuracy and provides appropriate mental health support.

[0230] Hearing phase

[0231] 1. A user initiates a conversation with a generative AI chatbot on their device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[0232] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0233] 2. The device sends the user's input, including text and voice data, to the server in real time.

[0234] Judgment Phase

[0235] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected. The emotion engine recognizes emotions from the user's input and voice data and reflects them in the analysis results.

[0236] Example: The emotion engine recognizes that a user is stressed or anxious based on their tone of voice and the way they use words.

[0237] Evidence Gathering Phase

[0238] 4. If the server determines that harassment is highly suspected based on the analysis results of the emotion engine, it sends a command to the device to start automatic recording and filming. The device receives this command and automatically starts recording and filming audio and video.

[0239] The device captures and encodes audio data to record what is happening around the user.

[0240] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[0241] 6. The device uploads the encrypted data to the server.

[0242] Reporting Phase

[0243] 7. The server receives the uploaded evidence data and analyzes it. Audio data is converted into text using speech recognition technology, and key parts are extracted.

[0244] 8. The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0245] 9. The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). It is sent via email or a dedicated portal.

[0246] Feedback Phase

[0247] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[0248] For example: "Your report was successfully submitted. Please wait for our response."

[0249] Mental care support

[0250] 11. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic. With the user's consent, it can arrange an appointment with a specialist.

[0251] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[0252] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[0253] The processing flow will be explained below.

[0254] Step 1:

[0255] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[0256] Step 2:

[0257] The device sends the user's input, including text and voice data, to the server in real time.

[0258] Step 3:

[0259] The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine, and determines whether the dialogue is suspected of harassment and the user's emotional state.

[0260] Step 4:

[0261] If the server detects suspicion of harassment and the emotion engine detects high stress or anger, it sends instructions to the terminal to proceed to the evidence collection phase.

[0262] Step 5:

[0263] The device receives instructions from the server and automatically starts recording and capturing images. When instructed to record or capture images, the device captures audio and video data around the user.

[0264] Step 6:

[0265] The device encrypts the evidence data (audio, video) collected, converts it into a secure format, and uploads it to the server.

[0266] Step 7:

[0267] The server receives the uploaded evidence data, converts the audio data into text using voice recognition technology, and extracts and analyzes the important parts.

[0268] Step 8:

[0269] The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0270] Step 9:

[0271] The server automatically sends the report to the relevant department or public institution via email or a dedicated portal.

[0272] Step 10:

[0273] The server then provides the user with a status update and feedback on next steps. The user receives a notification from the application.

[0274] Step 11:

[0275] If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic to provide appropriate mental health care support. With the user's consent, it will arrange an appointment with a specialist.

[0276] Step 12:

[0277] If the user wishes to provide feedback or additional information, they can continue to interact with the generative AI through their device. The server will analyze the new information and, if necessary, perform the evidence gathering and reporting phases again.

[0278] The above is a specific embodiment of the invention, and a detailed step-by-step explanation of the overall system flow. This system allows users to easily and safely report harassment, and also allows them to receive mental health support through the emotion engine.

[0279] Example 2

[0280] 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."

[0281] Conventional anti-harassment systems make it difficult for users to receive appropriate support promptly, and the need to manually collect evidence and report incidents places an excessive burden on victims. Furthermore, support provided often does not take into account the user's mental state, resulting in insufficient mental care.

[0282] 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.

[0283] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the content of the dialogue obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and an emotion engine that recognizes the user's emotions. This enables victims to quickly and efficiently report harassment and also enables them to receive appropriate mental care that takes into account the user's mental state.

[0284] "User" refers to an individual who uses the system to report a harassment issue.

[0285] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0286] "Generative AI" refers to an artificial intelligence model that generates natural language and engages in dialogue.

[0287] "Dialogue management means" refers to a software module with the function of managing and recording dialogue between a user and a generative AI.

[0288] The "determination means" refers to a software module that has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[0289] "Evidence collection means" refers to a software module that has the function of automatically starting recording and filming on a device when it is determined that harassment is suspected.

[0290] "Data management means" refers to a software module that has the function of securely encrypting collected evidence data and uploading it to a server.

[0291] "Reporting means" refers to a software module that has the function of analyzing evidence data uploaded to the server and automatically reporting to relevant departments and public institutions.

[0292] "Emotion engine" refers to a software module that has the function of analyzing and recognizing a user's emotions.

[0293] The system of the present invention provides a set of features that allow users to report harassment issues and receive appropriate assistance. The system is implemented using specific hardware and software.

[0294] Basic configuration

[0295] The system consists of the following main components:

[0296] Device: An electronic device used by a user, such as a smartphone or tablet.

[0297] Server: A remote computer system for analyzing, storing, and reporting data.

[0298] Generative AI: AI systems that generate natural language and engage in dialogue.

[0299] Natural Language Processing (NLP) engine: Software that analyzes text data (e.g., spaCy, NLTK).

[0300] Emotion engine: Software that analyzes user emotions (e.g., Microsoft Azure Cognitive Services' Text Analytics API).

[0301] Processing flow

[0302] 1. The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[0303] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0304] 2. The device sends the user's input (text data or voice data) to the server in real time. The device sends the data using the HTTP protocol.

[0305] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether it is suspected of harassment. The server uses a Python-based NLP library (e.g., spaCy or NLTK) to perform text analysis and an emotion engine to analyze emotions.

[0306] 4. If the server determines that harassment is highly suspected, it sends a command to the device to automatically start recording and filming. The server sends the command in real time using the WebSocket protocol.

[0307] 5. The device securely encrypts the collected evidence data (audio, video) and uploads it to the server. The device uses the AES encryption algorithm and transmits the data using the HTTPS protocol.

[0308] 6. The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), and extracts key parts.

[0309] 7. The server uses a template engine (e.g., Jinja2) to create a standardized report format based on the analysis results. This report includes a summary of the problem, links to collected evidence data, and the analysis results.

[0310] 8. The server automatically sends the report to the relevant departments or public institutions by email using the SMTP protocol or by sending the data via a dedicated portal API.

[0311] 9. After the server reports the incident, it sends a notification to the user to provide feedback on the status update and next steps. The server uses a push notification API (e.g., Firebase Cloud Messaging) to send the notification to the user's device.

[0312] 10. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental clinic. The server will send an email or a notification to the user, and if an appointment with a specialist is made online, it will use the reservation system's API.

[0313] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[0314] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[0315] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0316] Step 1:

[0317] The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[0318] Input: Text or voice input from the user.

[0319] Output: Beginning of dialogue with generative AI.

[0320] What happens: The user taps "Open app" and then types "Lately, my boss at work has been verbally abusing me almost every day," or types the same thing out loud.

[0321] Step 2:

[0322] The device sends the user's input (text data or voice data) to the server in real time.

[0323] Input: Text or voice data entered by the user.

[0324] Output: The data sent to the server.

[0325] Specific operation: The terminal sends text data and audio data to the server using the HTTP protocol.

[0326] Step 3:

[0327] The server analyzes the conversation content received using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected.

[0328] Input: Text or voice data sent from the device.

[0329] Output: The result of the judgment on suspected harassment.

[0330] How it works: The server performs text analysis using a Python-based NLP library (e.g., spaCy or NLTK) and analyzes emotions using the Microsoft Azure Cognitive Services Text Analytics API. The emotion engine recognizes that the user is feeling stressed or anxious based on their tone of voice and choice of words.

[0331] Step 4:

[0332] If the server determines that there is a strong suspicion of harassment, it sends instructions to the device to begin automatic recording and filming.

[0333] Input: Judgment result.

[0334] Output: Instructions to the terminal.

[0335] Specific operation: The server sends instructions to the terminal in real time using the WebSocket protocol.

[0336] Step 5:

[0337] The evidence data (audio, video) collected by the device is securely encrypted and uploaded to the server.

[0338] Input: Evidence data obtained as a result of automatic recording and photography.

[0339] Output: The encrypted data.

[0340] Specific operation: The terminal encrypts the evidence data using the AES encryption algorithm and sends it to the server using the HTTPS protocol.

[0341] Step 6:

[0342] The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology, and extracts the important parts.

[0343] Input: Encrypted evidence data.

[0344] Output: Text data with important parts extracted.

[0345] How it works: The server uses the speech recognition APIs of Google Cloud Speech-to-Text and Amazon Transcribe to analyze the audio data and extract the key parts.

[0346] Step 7:

[0347] The server creates a standardized report format based on the analysis results.

[0348] Input: Text data with important parts extracted.

[0349] Output: Report format.

[0350] Specific behavior: The server uses a template engine (e.g., Jinja2) to generate a report that includes a summary of the problem and links to supporting data.

[0351] Step 8:

[0352] The server automatically sends the report to the relevant department or public institution.

[0353] Input: Report format.

[0354] Output: The report sent.

[0355] Specific operation: The server sends an email using the SMTP protocol or sends data via a dedicated portal API.

[0356] Step 9:

[0357] Once the server has notified the user, it will send a notification to provide feedback on the status update and next steps.

[0358] Input: Reported report.

[0359] Output: Feedback to the user.

[0360] Specific operation: The server uses a push notification API (e.g., Firebase Cloud Messaging) to send a notification to the user's device.

[0361] Step 10:

[0362] If the server determines using the emotion engine that the user needs mental care, it will automatically contact a mental clinic.

[0363] Input: Analysis results of the emotion engine.

[0364] Output: Contact mental health clinic.

[0365] Specific operation: The server sends emails and notifications to the user, and uses the reservation system's API to make an appointment with a specialist online.

[0366] (Application example 2)

[0367] 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."

[0368] Conventional harassment reporting systems are only effective when the user is in a fixed environment, making it difficult to respond when the user is in a car or on the move. In addition, they often do not provide appropriate mental health support that takes the user's emotional state into consideration, which can increase the user's mental burden. Therefore, there is a need for a system that can instantly report and record harassment even while on the move, monitor the user's emotional state, and provide appropriate mental health support.

[0369] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0370] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content and the user's emotional data obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording within the autonomous vehicle if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, and a mental care means for continuously monitoring the user's emotional state and providing mental care support as needed. This enables harassment to be immediately reported and recorded even while on the move, and appropriate mental care support that takes the user's emotional state into consideration.

[0371] "User" refers to an individual who uses the system to report harassment issues.

[0372] "Terminal" refers to an electronic device operated by a user, including smartphones and in-car infotainment systems.

[0373] "Generative AI" refers to an artificial intelligence system that supports dialogue with users and has the ability to perform natural language processing and emotion analysis.

[0374] "Dialogue management means" refers to the management function that allows users to interact with generative AI via a terminal.

[0375] The "determination means" refers to a function that analyzes the content of the dialogue and the user's emotional data obtained via the dialogue management means and determines whether harassment is suspected.

[0376] "Evidence collection means" refers to a function that automatically starts recording and filming within an autonomous vehicle if it is determined that harassment is suspected.

[0377] "Data management means" refers to a function that safely encrypts evidence data collected by evidence collection means and uploads it to a server.

[0378] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0379] "Mental care means" refers to a function that continuously monitors the user's emotional state and provides mental care support as needed.

[0380] "Emotion data" refers to data that indicates the user's emotional state and that has been analyzed by the emotion engine.

[0381] An "emotion engine" refers to a system that recognizes emotions from user input and voice data and reflects them in the analysis results.

[0382] This invention provides a system that allows users to report harassment issues in autonomous vehicles and receive appropriate support. Specific embodiments of this invention are described below. This system includes both hardware and software, and its main components are a user terminal and a server.

[0383] Program Overview

[0384] 1. How users interact with generative AI via their devices:

[0385] The user initiates a dialogue with the generative AI using the infotainment system or smartphone installed in the autonomous vehicle. A dedicated application is installed on the device, and the user interacts with the AI ​​using voice or text input.

[0386] 2. Analysis of dialogue content and emotion data:

[0387] The user's input and voice data are sent to a server in real time, where a natural language processing engine (NLP engine) and an emotion engine analyze the data and determine whether it is suspected harassment. The emotion engine recognizes the user's emotional state and feeds that data back to the AI ​​model.

[0388] 3. Collecting evidence:

[0389] If the server determines that harassment is highly suspected, it automatically sends instructions to the device to start recording and filming. The device collects evidence data using the in-car camera and microphone, encrypts it, and then uploads the encrypted data to the server.

[0390] 4. Data Management and Analysis:

[0391] The server analyzes the uploaded evidence data and uses natural language processing technology to extract key information, which is then converted into a standardized reporting format and automatically sent to the relevant departments and public institutions.

[0392] 5. Mental health support:

[0393] The server determines whether the user needs mental care based on the results of the emotion engine. If necessary, it introduces the user to a specialized institution that provides mental care support and arranges for a reservation.

[0394] The specific hardware and software used

[0395] Hardware:

[0396] Smartphone

[0397] Autonomous vehicle infotainment systems

[0398] In-car camera and microphone

[0399] software:

[0400] SpeechRecognition library: Used to convert voice input to text.

[0401] EmotionRecognition library: Used to analyze the user's emotional state.

[0402] VideoCapture library: Provides audio and video recording functions.

[0403] CloudStorage module: Encrypts and uploads evidence data to the cloud.

[0404] ReportGenerator module: Provides automatic report generation functionality.

[0405] Notifications module: Notifies the user.

[0406] Mental Care module: Contact and schedule mental health support.

[0407] Specific examples

[0408] For example, if a user shouts "harassment" inside an autonomous vehicle, the system immediately performs sentiment analysis and automatically starts recording. The collected evidence data is encrypted and securely uploaded to the cloud. The server then analyzes the collected data, generates a standardized report, and automatically sends it to the designated department. For example, if a user says, "My boss is verbally abusing me at work," the system will detect harassment and begin responding.

[0409] Example prompt sentence:

[0410] "I would like to report harassment at my workplace. Please start recording and collecting evidence."

[0411] "Now, record any problematic conversations you hear while riding alone."

[0412] The above is a specific embodiment of the present invention. This system allows users to easily and safely report harassment even while on the move, enabling a prompt response. Furthermore, the introduction of an emotion engine provides analysis that takes into account the user's mental state and provides appropriate mental care support.

[0413] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0414] Step 1:

[0415] The user initiates a dialogue with the generative AI via a device. The user inputs voice or text, which the device sends to the server in real time. Input: Voice data or text data. Output: Data sent to the server.

[0416] Step 2:

[0417] The server analyzes the received voice or text data using a natural language processing engine (NLP engine) to understand what the user is saying. The server then analyzes the voice data using an emotion engine to recognize the user's emotions. Input: Data sent to the server. Output: Analysis results (text content and emotion data).

[0418] Step 3:

[0419] Based on the analysis results, the server determines whether there is any suspicion of harassment. The server analyzes the content of the user's remarks and emotional state, and if it determines that there is suspicion of harassment, it sends instructions to the device to automatically record and film. Input: Analysis results. Output: Instruction to start recording and filming.

[0420] Step 4:

[0421] The terminal receives instructions from the server and starts recording and capturing images using the camera and microphone inside the autonomous vehicle. Evidence data is collected and encrypted. Input: Instruction to start recording and capturing images. Output: Encrypted evidence data.

[0422] Step 5:

[0423] The terminal uploads the encrypted evidence data to the server. Input: Encrypted evidence data. Output: Data uploaded to the server.

[0424] Step 6:

[0425] The server analyzes the uploaded evidence data and extracts important information. It then converts the extracted information into a standardized report format and automatically notifies the relevant departments and public institutions. Input: Uploaded evidence data. Output: Report generation and notification.

[0426] Step 7:

[0427] The server determines whether the user needs mental care based on the results of the emotion engine. If it determines that mental care is necessary, it introduces the user to a specialized institution for mental care support and arranges an appointment. Input: Analysis results of the emotion engine. Output: Provision of mental care support.

[0428] The above are the specific processing steps in the system for realizing the present invention. The specific operations performed in each step, as well as the inputs and outputs, have also been explained.

[0429] 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.

[0430] 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.

[0431] 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.

[0432] [Second embodiment]

[0433] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0434] 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.

[0435] 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).

[0436] 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.

[0437] 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.

[0438] 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).

[0439] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0440] 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.

[0441] 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.

[0442] 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.

[0443] 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.

[0444] 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."

[0445] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[0446] Hearing phase

[0447] 1. The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[0448] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0449] 2. The terminal transmits the user's input in real time to the server, which has a means of analyzing the content of the conversation and determining whether it constitutes harassment.

[0450] Judgment Phase

[0451] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine to determine whether it is suspected of harassment. At this time, the content is scored by a judgment means, and if it exceeds a certain threshold, the process proceeds to the next step.

[0452] Evidence Gathering Phase

[0453] 4. If the server judges that harassment is highly suspected, it sends a command to the device to start automatic recording or video recording. The device receives this command and automatically starts recording audio or video.

[0454] The device captures and encodes audio data to record what is happening around the user.

[0455] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[0456] 6. The device uploads the encrypted data to the server.

[0457] Reporting Phase

[0458] 7. The server receives the uploaded evidence data and analyzes it, using speech recognition technology to convert the audio data into text and extract the key parts.

[0459] 8. The server creates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0460] 9. The server automatically sends a report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The report is sent via email or a dedicated portal.

[0461] Feedback Phase

[0462] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[0463] For example: "Your report was successfully submitted. Please wait for our response."

[0464] Mental care support

[0465] 11. If the server determines that the user needs mental health care, it will automatically contact a mental health clinic and, with the user's consent, arrange an appointment with a specialist.

[0466] The above is a specific form for implementing the invention. This system allows victims to easily and safely report harassment and receive prompt support. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[0467] The processing flow will be explained below.

[0468] Step 1:

[0469] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[0470] Step 2:

[0471] The device sends the user's input, including text and voice data, to the server in real time.

[0472] Step 3:

[0473] The server analyzes the conversation content received using a natural language processing (NLP) engine to determine whether it is suspected of harassment. Based on the analysis results, a certain score is generated.

[0474] Step 4:

[0475] If the server finds that the score exceeds a certain threshold, it determines that harassment is suspected and moves on to the evidence collection phase.

[0476] Step 5:

[0477] The server sends a command to the device to start automatic recording and shooting. The device receives this command and automatically starts recording and shooting audio and video.

[0478] Step 6:

[0479] The device encrypts the evidence data (audio, video) collected and uploads the data to a server.

[0480] Step 7:

[0481] The server receives and analyzes the uploaded evidence data, converting audio data into text using speech recognition technology and extracting key parts.

[0482] Step 8:

[0483] The server generates a standardized report format based on the analysis results, which includes a summary of the problem and links to supporting data.

[0484] Step 9:

[0485] The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., police, labor standards inspection office) via email or a dedicated portal.

[0486] Step 10:

[0487] The server then provides the user with a status update and feedback on next steps. The user receives a notification within the application.

[0488] Step 11:

[0489] The server provides mental health support to the user as needed, and with the user's consent, contacts and arranges appointments with mental health clinics.

[0490] Example 1

[0491] 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."

[0492] In the past, proper reporting and support for harassment required specialized knowledge and time, making it difficult for victims to receive prompt action. Furthermore, there was no comprehensive system in place to handle the entire process, including collecting and safely managing evidence, properly reporting to the relevant authorities, and providing mental health care. This created a mental burden for victims, making them hesitant to report harassment.

[0493] 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.

[0494] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, a feedback means for sending a notification to the user after reporting and providing feedback, and a support means for determining the need for mental health care and contacting a medical institution if necessary. This enables prompt reporting of harassment, safe management of evidence, reporting to appropriate relevant institutions, and mental health care support for users.

[0495] "User" refers to a person who uses this system to report harassment issues and receive support.

[0496] "Terminal" refers to a device used by a user that has a dedicated application installed for interacting with generative AI.

[0497] "Generative AI" refers to artificial intelligence technology that understands user input and responds appropriately.

[0498] "Dialogue management means" refers to the function of managing the dialogue between the user and generative AI and processing the data appropriately.

[0499] "Determination means" refers to a function that analyzes the content of conversations with generative AI and determines whether there is any suspicion of harassment.

[0500] "Evidence collection means" refers to a function that automatically records and photographs audio and video on the device if harassment is suspected.

[0501] "Data management means" refers to the function for securely encrypting collected evidence data and uploading it to a server.

[0502] A "server" refers to a central computer that manages the entire system and analyzes and communicates various data.

[0503] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0504] "Feedback mechanism" refers to the functionality to send notifications to users after a report is made and provide feedback on status updates and next steps.

[0505] "Support measures" refers to the function of determining the need for mental care and contacting a medical institution when necessary.

[0506] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[0507] The system begins when a user interacts with the generative AI using a device with a dedicated application installed. The interaction is conducted via text input or voice input, and the content is sent to the server.

[0508] Dialogue Management

[0509] The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text input or voice input. For example, the user might type, "Recently, my boss at work has been verbally abusing me almost every day." The device then sends the user's input to the server in real time. At this time, the device temporarily stores the input in a buffer and transmits it over the internet using a secure communication protocol (e.g., HTTPS).

[0510] Judgment means

[0511] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API) to determine whether there is any suspicion of harassment. This determination is based on a scoring system, and if the score exceeds a certain threshold, the system proceeds to the next phase.

[0512] Evidence collection

[0513] If harassment is suspected, the server sends a command to the device to start automatic recording and filming. The device automatically starts recording audio or video when instructed to do so using its built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in the device's storage. The device then uploads the encrypted data to the server. The device uses the HTTPS protocol to securely and quickly send the data to the server.

[0514] Data Management and Reporting

[0515] The server receives the uploaded evidence data and, if it is audio data, converts it into text using speech recognition technology (e.g., IBM Watson Speech to Text API). Video data is analyzed in the same way. The server creates a standardized report format based on the analysis results. The report includes a summary of the problem, a link to the collected evidence data, and the analysis results. The server sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The server sends the report using a pre-configured mail server or dedicated portal.

[0516] Feedback tools and mental health support

[0517] After reporting, the server sends a notification to the user, providing an update on the situation and feedback on next steps. For example, a notification stating "The report was sent successfully. Please wait for our response" may be displayed on the device. Furthermore, if the server determines that the user needs mental health care, it can use the Google Calendar API to arrange an appointment with a mental health clinic and send a notification to the user.

[0518] This system allows victims to easily and safely report harassment and receive prompt action. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[0519] Prompt Sentence Examples

[0520] "I feel like I am being verbally abused by my boss at work every day. Please tell me the steps to report this and how to gather evidence."

[0521] When the user inputs information based on this prompt, the generative AI can provide appropriate support to the user and respond quickly and safely.

[0522] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0523] Step 1:

[0524] A user begins a dialogue with the generative AI using a device with a dedicated application installed. The user describes the harassment situation they are facing using text input or voice input. For example, they might say, "Recently, my boss at work has been verbally abusing me almost every day." The input data is then imported into the device in text format.

[0525] Input: The user inputs information about the harassment into the device using text or voice.

[0526] Output: The terminal temporarily stores the user's input as text data and sends it to the next process.

[0527] Step 2:

[0528] The device sends the user's input to the server in real time. The device stores the input in a buffer and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0529] Input: User input (text data).

[0530] Output: The user's input sent to the server.

[0531] Step 3:

[0532] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API). Based on this analysis, the server scores the likelihood of harassment and proceeds to the next step if the score exceeds a certain threshold.

[0533] Input: User input sent to the server.

[0534] Output: Scoring data as the analysis result.

[0535] The server passes the input text data to a natural language processing engine, which analyzes it for keywords and context that suggest harassment, and scores it based on the results of this analysis.

[0536] Step 4:

[0537] If the server determines that there is a strong suspicion of harassment, it will send instructions to the device to automatically start recording and filming.

[0538] Input: Analysis results (scoring data).

[0539] Output: Automatic recording and shooting instructions to the device.

[0540] Step 5:

[0541] The device receives the command and automatically starts recording audio or video using the built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in storage.

[0542] Input: Automatic recording and shooting instructions from the server.

[0543] Output: Encrypted audio or video data.

[0544] Step 6:

[0545] The device uploads the encrypted evidence data to the server. The device uses the HTTPS protocol to send the data to the server safely and quickly.

[0546] Input: Encrypted audio or video data.

[0547] Output: The encrypted data uploaded to the server.

[0548] Step 7:

[0549] The server receives the uploaded evidence data and converts it into text using voice recognition technology (e.g., IBM Watson Speech to Text API) if it is audio data. Video data is also analyzed in the same way.

[0550] Input: Encrypted evidence data.

[0551] Output: Parsed data converted to text.

[0552] Step 8:

[0553] The server then generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0554] Input: Parsed data converted to text.

[0555] Output: Standardized report.

[0556] Step 9:

[0557] The server automatically sends reports to the relevant departments and public institutions using a pre-configured mail server or dedicated portal.

[0558] Input: Standardized report.

[0559] Output: Reports sent to responsible departments and public authorities.

[0560] Step 10:

[0561] After the server reports, it will send a notification to the user to provide a status update and feedback on next steps, such as a notification displayed on the device stating "Report submitted successfully. Please wait for our response."

[0562] Input: Report status data.

[0563] Output: Feedback notification to the user.

[0564] Step 11:

[0565] If the server determines that the user needs mental health care, it will automatically contact a mental health clinic. The server can use the Google Calendar API or similar to arrange an appointment with the mental health clinic and send a notification to the user.

[0566] Input: A determination of the user's mental health needs.

[0567] Output: Mental clinic appointment notification.

[0568] (Application example 1)

[0569] 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."

[0570] Conventional harassment reporting systems require users to manually collect evidence, create a report, and report to a public institution or department in charge, which is time-consuming and makes it difficult to respond quickly.The present invention aims to provide a system that allows users to quickly and easily report harassment and receive appropriate support promptly.

[0571] 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.

[0572] In this invention, the server includes a dialogue management means for a user to dialogue with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and a hearing means for the generative AI to transmit the dialogue content to the server in real time when the user inputs voice or text into a predetermined input means. This enables users to easily report harassment and quickly receive appropriate support and mental care.

[0573] The "dialogue management means" provides a function that allows users to interact with generative AI via a terminal.

[0574] The "determination means" has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[0575] The "evidence collection means" is a function that automatically starts recording or photographing on the terminal when the assessment means determines that harassment is suspected.

[0576] The "data management means" has a function for safely encrypting the evidence data collected by the evidence collection means and uploading it to a server.

[0577] The "reporting means" has the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0578] A "hearing means" is a function that allows the generative AI to send the content of the dialogue to a server in real time when the user inputs voice or text into a specified input means.

[0579] "Generative AI" refers to artificial intelligence technology that generates dialogue based on user input and analyzes the content of the dialogue.

[0580] "Device" refers to a terminal used by a user, such as a smartphone, smart glasses, a head-mounted display, or a robot.

[0581] "Encryption" refers to a technology for protecting data from being leaked to third parties while maintaining its security.

[0582] A "natural language processing engine" includes technology for analyzing and understanding the meaning of user input.

[0583] This invention provides a system that allows users to quickly and easily report harassment issues and receive appropriate support. Specifically, it has the following configuration.

[0584] System Overview

[0585] The system includes the following means for interacting with generative AI using a user's device to determine whether harassment is suspected.

[0586] Dialogue Management Tools

[0587] Judgment means

[0588] Evidence collection methods

[0589] Data Management Measures

[0590] Reporting means

[0591] Hearing methods

[0592] Hardware and software used

[0593] Hardware: Smartphones, smart glasses, head-mounted displays, robots, etc.

[0594] Software: Python, Requests library, SpeechRecognition library, Natural Language Processing engine (e.g. spaCy or NLTK)

[0595] Program processing

[0596] User Input and Hearing Phase

[0597] The user uses a designated device (e.g., a smartphone) to initiate a dialogue with the generative AI. The user registers details of the harassment through voice or text input. At this time, the generative AI sends the user's input to the server in real time. Examples of prompt sentences include the following:

[0598] "I'm having trouble with verbal abuse from my boss at work."

[0599] "I'm being harassed by my classmates at school."

[0600] Assessment and evidence gathering phase

[0601] The server analyzes the received user input using a natural language processing engine to determine whether there is any suspicion of harassment. If there is any suspicion, the server sends instructions to the device to automatically record and record audio and video. The device then receives the instructions, automatically collects audio and video from the surrounding area, and securely encrypts the data.

[0602] Data management and analysis phase

[0603] The encrypted evidence data is uploaded to a server, which analyzes the uploaded data and automatically notifies the relevant departments and public institutions. Specifically, the collected evidence data is converted into a standardized report format and sent via email or a dedicated portal.

[0604] Feedback Phase

[0605] If the report is successful, the user is notified and given feedback on progress and next steps, and the server is available to assist the user in providing additional information or asking questions.

[0606] Mental care support

[0607] Finally, if the server determines that the user needs mental health care, it will automatically schedule an appointment with a specialist with the user's consent, allowing the user to receive appropriate support promptly.

[0608] The above is a specific embodiment of the present invention. This system allows users to easily report harassment and receive prompt support and assistance. Furthermore, the system automatically notifies the appropriate authorities and provides mental health care, allowing users to use the system with peace of mind.

[0609] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0610] Step 1:

[0611] The user initiates a dialogue with the generative AI via a device. The user registers details of the harassment using voice or text input. Examples of input include:

[0612] "I'm having trouble with verbal abuse from my boss at work."

[0613] "I'm being harassed by my classmates at school."

[0614] Input data is sent from the terminal to the server in real time.

[0615] Step 2:

[0616] The server analyzes the received user input data using a natural language processing engine. Specifically, it tokenizes the input text and analyzes its meaning. The server determines whether the input is suspected of harassment and assigns a score. This analysis uses a generative AI model.

[0617] Input: User-entered text or voice data

[0618] Output: Suspected harassment score

[0619] Step 3:

[0620] If the server determines that harassment is suspected, it will send an instruction to the device to automatically record and record. When the device receives this instruction, it will automatically collect audio and video from the surrounding area. The collected data is immediately encrypted.

[0621] Input: Server recording start instruction

[0622] Output: Encrypted audio and video data

[0623] Step 4:

[0624] The evidence data encrypted on the device is uploaded to a server, where it is analyzed and reported to the relevant departments and public institutions. Specifically, the evidence data is converted into a standardized reporting format and sent via email or a dedicated portal.

[0625] Input: Encrypted evidence data

[0626] Output: Report and transmission log

[0627] Step 5:

[0628] If the report is successful, the server sends a notification to the user. The feedback includes information about the report result and next steps. The user can also provide additional information or ask questions, and an interface is provided for this.

[0629] Input: Report result, additional information

[0630] Output: Notification and feedback to the user

[0631] Step 6:

[0632] The server determines the user's mental health needs and automatically schedules appointments with specialists if necessary. This appointment requires the user's consent, and arrangements are made only after the consent is confirmed.

[0633] Input: User consent, mental health care need data

[0634] Output: Specialist appointment information and user notification

[0635] The above are the specific processing steps for carrying out the present invention, which enable users to quickly and easily report harassment and receive appropriate support.

[0636] 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.

[0637] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system improves analysis accuracy and provides appropriate mental health support.

[0638] Hearing phase

[0639] 1. A user initiates a conversation with a generative AI chatbot on their device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[0640] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0641] 2. The device sends the user's input, including text and voice data, to the server in real time.

[0642] Judgment Phase

[0643] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected. The emotion engine recognizes emotions from the user's input and voice data and reflects them in the analysis results.

[0644] Example: The emotion engine recognizes that a user is stressed or anxious based on their tone of voice and the way they use words.

[0645] Evidence Gathering Phase

[0646] 4. If the server determines that harassment is highly suspected based on the analysis results of the emotion engine, it sends a command to the device to start automatic recording and filming. The device receives this command and automatically starts recording and filming audio and video.

[0647] The device captures and encodes audio data to record what is happening around the user.

[0648] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[0649] 6. The device uploads the encrypted data to the server.

[0650] Reporting Phase

[0651] 7. The server receives the uploaded evidence data and analyzes it. Audio data is converted into text using speech recognition technology, and key parts are extracted.

[0652] 8. The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0653] 9. The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). It is sent via email or a dedicated portal.

[0654] Feedback Phase

[0655] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[0656] For example: "Your report was successfully submitted. Please wait for our response."

[0657] Mental care support

[0658] 11. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic. With the user's consent, it can arrange an appointment with a specialist.

[0659] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[0660] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[0661] The processing flow will be explained below.

[0662] Step 1:

[0663] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[0664] Step 2:

[0665] The device sends the user's input, including text and voice data, to the server in real time.

[0666] Step 3:

[0667] The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine, and determines whether the dialogue is suspected of harassment and the user's emotional state.

[0668] Step 4:

[0669] If the server detects suspicion of harassment and the emotion engine detects high stress or anger, it sends instructions to the terminal to proceed to the evidence collection phase.

[0670] Step 5:

[0671] The device receives instructions from the server and automatically starts recording and capturing images. When instructed to record or capture images, the device captures audio and video data around the user.

[0672] Step 6:

[0673] The device encrypts the evidence data (audio, video) collected, converts it into a secure format, and uploads it to the server.

[0674] Step 7:

[0675] The server receives the uploaded evidence data, converts the audio data into text using voice recognition technology, and extracts and analyzes the important parts.

[0676] Step 8:

[0677] The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0678] Step 9:

[0679] The server automatically sends the report to the relevant department or public institution via email or a dedicated portal.

[0680] Step 10:

[0681] The server then provides the user with a status update and feedback on next steps. The user receives a notification from the application.

[0682] Step 11:

[0683] If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic to provide appropriate mental health care support. With the user's consent, it will arrange an appointment with a specialist.

[0684] Step 12:

[0685] If the user wishes to provide feedback or additional information, they can continue to interact with the generative AI through their device. The server will analyze the new information and, if necessary, perform the evidence gathering and reporting phases again.

[0686] The above is a specific embodiment of the invention, and a detailed step-by-step explanation of the overall system flow. This system allows users to easily and safely report harassment, and also allows them to receive mental health support through the emotion engine.

[0687] Example 2

[0688] 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."

[0689] Conventional anti-harassment systems make it difficult for users to receive appropriate support promptly, and the need to manually collect evidence and report incidents places an excessive burden on victims. Furthermore, support provided often does not take into account the user's mental state, resulting in insufficient mental care.

[0690] 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.

[0691] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the content of the dialogue obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and an emotion engine that recognizes the user's emotions. This enables victims to quickly and efficiently report harassment and also enables them to receive appropriate mental care that takes into account the user's mental state.

[0692] "User" refers to an individual who uses the system to report a harassment issue.

[0693] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[0694] "Generative AI" refers to an artificial intelligence model that generates natural language and engages in dialogue.

[0695] "Dialogue management means" refers to a software module with the function of managing and recording dialogue between a user and a generative AI.

[0696] The "determination means" refers to a software module that has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[0697] "Evidence collection means" refers to a software module that has the function of automatically starting recording and filming on a device when it is determined that harassment is suspected.

[0698] "Data management means" refers to a software module that has the function of securely encrypting collected evidence data and uploading it to a server.

[0699] "Reporting means" refers to a software module that has the function of analyzing evidence data uploaded to the server and automatically reporting to relevant departments and public institutions.

[0700] "Emotion engine" refers to a software module that has the function of analyzing and recognizing a user's emotions.

[0701] The system of the present invention provides a set of features that allow users to report harassment issues and receive appropriate assistance. The system is implemented using specific hardware and software.

[0702] Basic configuration

[0703] The system consists of the following main components:

[0704] Device: An electronic device used by a user, such as a smartphone or tablet.

[0705] Server: A remote computer system for analyzing, storing, and reporting data.

[0706] Generative AI: AI systems that generate natural language and engage in dialogue.

[0707] Natural Language Processing (NLP) engine: Software that analyzes text data (e.g., spaCy, NLTK).

[0708] Emotion engine: Software that analyzes user emotions (e.g., Microsoft Azure Cognitive Services' Text Analytics API).

[0709] Processing flow

[0710] 1. The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[0711] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0712] 2. The device sends the user's input (text data or voice data) to the server in real time. The device sends the data using the HTTP protocol.

[0713] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether it is suspected of harassment. The server uses a Python-based NLP library (e.g., spaCy or NLTK) to perform text analysis and an emotion engine to analyze emotions.

[0714] 4. If the server determines that harassment is highly suspected, it sends a command to the device to automatically start recording and filming. The server sends the command in real time using the WebSocket protocol.

[0715] 5. The device securely encrypts the collected evidence data (audio, video) and uploads it to the server. The device uses the AES encryption algorithm and transmits the data using the HTTPS protocol.

[0716] 6. The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), and extracts key parts.

[0717] 7. The server uses a template engine (e.g., Jinja2) to create a standardized report format based on the analysis results. This report includes a summary of the problem, links to collected evidence data, and the analysis results.

[0718] 8. The server automatically sends the report to the relevant departments or public institutions by email using the SMTP protocol or by sending the data via a dedicated portal API.

[0719] 9. After the server reports the incident, it sends a notification to the user to provide feedback on the status update and next steps. The server uses a push notification API (e.g., Firebase Cloud Messaging) to send the notification to the user's device.

[0720] 10. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental clinic. The server will send an email or a notification to the user, and if an appointment with a specialist is made online, it will use the reservation system's API.

[0721] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[0722] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[0723] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0724] Step 1:

[0725] The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[0726] Input: Text or voice input from the user.

[0727] Output: Beginning of dialogue with generative AI.

[0728] What happens: The user taps "Open app" and then types "Lately, my boss at work has been verbally abusing me almost every day," or types the same thing out loud.

[0729] Step 2:

[0730] The device sends the user's input (text data or voice data) to the server in real time.

[0731] Input: Text or voice data entered by the user.

[0732] Output: The data sent to the server.

[0733] Specific operation: The terminal sends text data and audio data to the server using the HTTP protocol.

[0734] Step 3:

[0735] The server analyzes the conversation content received using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected.

[0736] Input: Text or voice data sent from the device.

[0737] Output: The result of the judgment on suspected harassment.

[0738] How it works: The server performs text analysis using a Python-based NLP library (e.g., spaCy or NLTK) and analyzes emotions using the Microsoft Azure Cognitive Services Text Analytics API. The emotion engine recognizes that the user is feeling stressed or anxious based on their tone of voice and choice of words.

[0739] Step 4:

[0740] If the server determines that there is a strong suspicion of harassment, it sends instructions to the device to begin automatic recording and filming.

[0741] Input: Judgment result.

[0742] Output: Instructions to the terminal.

[0743] Specific operation: The server sends instructions to the terminal in real time using the WebSocket protocol.

[0744] Step 5:

[0745] The evidence data (audio, video) collected by the device is securely encrypted and uploaded to the server.

[0746] Input: Evidence data obtained as a result of automatic recording and photography.

[0747] Output: The encrypted data.

[0748] Specific operation: The terminal encrypts the evidence data using the AES encryption algorithm and sends it to the server using the HTTPS protocol.

[0749] Step 6:

[0750] The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology, and extracts the important parts.

[0751] Input: Encrypted evidence data.

[0752] Output: Text data with important parts extracted.

[0753] How it works: The server uses the speech recognition APIs of Google Cloud Speech-to-Text and Amazon Transcribe to analyze the audio data and extract the key parts.

[0754] Step 7:

[0755] The server creates a standardized report format based on the analysis results.

[0756] Input: Text data with important parts extracted.

[0757] Output: Report format.

[0758] Specific behavior: The server uses a template engine (e.g., Jinja2) to generate a report that includes a summary of the problem and links to supporting data.

[0759] Step 8:

[0760] The server automatically sends the report to the relevant department or public institution.

[0761] Input: Report format.

[0762] Output: The report sent.

[0763] Specific operation: The server sends an email using the SMTP protocol or sends data via a dedicated portal API.

[0764] Step 9:

[0765] Once the server has notified the user, it will send a notification to provide feedback on the status update and next steps.

[0766] Input: Reported report.

[0767] Output: Feedback to the user.

[0768] Specific operation: The server uses a push notification API (e.g., Firebase Cloud Messaging) to send a notification to the user's device.

[0769] Step 10:

[0770] If the server determines using the emotion engine that the user needs mental care, it will automatically contact a mental clinic.

[0771] Input: Analysis results of the emotion engine.

[0772] Output: Contact mental health clinic.

[0773] Specific operation: The server sends emails and notifications to the user, and uses the reservation system's API to make an appointment with a specialist online.

[0774] (Application example 2)

[0775] 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."

[0776] Conventional harassment reporting systems are only effective when the user is in a fixed environment, making it difficult to respond when the user is in a car or on the move. In addition, they often do not provide appropriate mental health support that takes the user's emotional state into consideration, which can increase the user's mental burden. Therefore, there is a need for a system that can instantly report and record harassment even while on the move, monitor the user's emotional state, and provide appropriate mental health support.

[0777] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0778] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content and the user's emotional data obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording within the autonomous vehicle if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, and a mental care means for continuously monitoring the user's emotional state and providing mental care support as needed. This enables harassment to be immediately reported and recorded even while on the move, and appropriate mental care support that takes the user's emotional state into consideration.

[0779] "User" refers to an individual who uses the system to report harassment issues.

[0780] "Terminal" refers to an electronic device operated by a user, including smartphones and in-car infotainment systems.

[0781] "Generative AI" refers to an artificial intelligence system that supports dialogue with users and has the ability to perform natural language processing and emotion analysis.

[0782] "Dialogue management means" refers to the management function that allows users to interact with generative AI via a terminal.

[0783] The "determination means" refers to a function that analyzes the content of the dialogue and the user's emotional data obtained via the dialogue management means and determines whether harassment is suspected.

[0784] "Evidence collection means" refers to a function that automatically starts recording and filming within an autonomous vehicle if it is determined that harassment is suspected.

[0785] "Data management means" refers to a function that safely encrypts evidence data collected by evidence collection means and uploads it to a server.

[0786] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0787] "Mental care means" refers to a function that continuously monitors the user's emotional state and provides mental care support as needed.

[0788] "Emotion data" refers to data that indicates the user's emotional state and that has been analyzed by the emotion engine.

[0789] An "emotion engine" refers to a system that recognizes emotions from user input and voice data and reflects them in the analysis results.

[0790] This invention provides a system that allows users to report harassment issues in autonomous vehicles and receive appropriate support. Specific embodiments of this invention are described below. This system includes both hardware and software, and its main components are a user terminal and a server.

[0791] Program Overview

[0792] 1. How users interact with generative AI via their devices:

[0793] The user initiates a dialogue with the generative AI using the infotainment system or smartphone installed in the autonomous vehicle. A dedicated application is installed on the device, and the user interacts with the AI ​​using voice or text input.

[0794] 2. Analysis of dialogue content and emotion data:

[0795] The user's input and voice data are sent to a server in real time, where a natural language processing engine (NLP engine) and an emotion engine analyze the data and determine whether it is suspected harassment. The emotion engine recognizes the user's emotional state and feeds that data back to the AI ​​model.

[0796] 3. Collecting evidence:

[0797] If the server determines that harassment is highly suspected, it automatically sends instructions to the device to start recording and filming. The device collects evidence data using the in-car camera and microphone, encrypts it, and then uploads the encrypted data to the server.

[0798] 4. Data Management and Analysis:

[0799] The server analyzes the uploaded evidence data and uses natural language processing technology to extract key information, which is then converted into a standardized reporting format and automatically sent to the relevant departments and public institutions.

[0800] 5. Mental health support:

[0801] The server determines whether the user needs mental care based on the results of the emotion engine. If necessary, it introduces the user to a specialized institution that provides mental care support and arranges for a reservation.

[0802] The specific hardware and software used

[0803] Hardware:

[0804] Smartphone

[0805] Autonomous vehicle infotainment systems

[0806] In-car camera and microphone

[0807] software:

[0808] SpeechRecognition library: Used to convert voice input to text.

[0809] EmotionRecognition library: Used to analyze the user's emotional state.

[0810] VideoCapture library: Provides audio and video recording functions.

[0811] CloudStorage module: Encrypts and uploads evidence data to the cloud.

[0812] ReportGenerator module: Provides automatic report generation functionality.

[0813] Notifications module: Notifies the user.

[0814] Mental Care module: Contact and schedule mental health support.

[0815] Specific examples

[0816] For example, if a user shouts "harassment" inside an autonomous vehicle, the system immediately performs sentiment analysis and automatically starts recording. The collected evidence data is encrypted and securely uploaded to the cloud. The server then analyzes the collected data, generates a standardized report, and automatically sends it to the designated department. For example, if a user says, "My boss is verbally abusing me at work," the system will detect harassment and begin responding.

[0817] Example prompt sentence:

[0818] "I would like to report harassment at my workplace. Please start recording and collecting evidence."

[0819] "Now, record any problematic conversations you hear while riding alone."

[0820] The above is a specific embodiment of the present invention. This system allows users to easily and safely report harassment even while on the move, enabling a prompt response. Furthermore, the introduction of an emotion engine provides analysis that takes into account the user's mental state and provides appropriate mental care support.

[0821] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0822] Step 1:

[0823] The user initiates a dialogue with the generative AI via a device. The user inputs voice or text, which the device sends to the server in real time. Input: Voice data or text data. Output: Data sent to the server.

[0824] Step 2:

[0825] The server analyzes the received voice or text data using a natural language processing engine (NLP engine) to understand what the user is saying. The server then analyzes the voice data using an emotion engine to recognize the user's emotions. Input: Data sent to the server. Output: Analysis results (text content and emotion data).

[0826] Step 3:

[0827] Based on the analysis results, the server determines whether there is any suspicion of harassment. The server analyzes the content of the user's remarks and emotional state, and if it determines that there is suspicion of harassment, it sends instructions to the device to automatically record and film. Input: Analysis results. Output: Instruction to start recording and filming.

[0828] Step 4:

[0829] The terminal receives instructions from the server and starts recording and capturing images using the camera and microphone inside the autonomous vehicle. Evidence data is collected and encrypted. Input: Instruction to start recording and capturing images. Output: Encrypted evidence data.

[0830] Step 5:

[0831] The terminal uploads the encrypted evidence data to the server. Input: Encrypted evidence data. Output: Data uploaded to the server.

[0832] Step 6:

[0833] The server analyzes the uploaded evidence data and extracts important information. It then converts the extracted information into a standardized report format and automatically notifies the relevant departments and public institutions. Input: Uploaded evidence data. Output: Report generation and notification.

[0834] Step 7:

[0835] The server determines whether the user needs mental care based on the results of the emotion engine. If it determines that mental care is necessary, it introduces the user to a specialized institution for mental care support and arranges an appointment. Input: Analysis results of the emotion engine. Output: Provision of mental care support.

[0836] The above are the specific processing steps in the system for realizing the present invention. The specific operations performed in each step, as well as the inputs and outputs, have also been explained.

[0837] 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.

[0838] 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.

[0839] 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.

[0840] [Third embodiment]

[0841] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0842] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0843] 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).

[0844] 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.

[0845] 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.

[0846] 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).

[0847] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0848] 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.

[0849] 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.

[0850] 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.

[0851] 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.

[0852] 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."

[0853] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[0854] Hearing phase

[0855] 1. The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[0856] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[0857] 2. The terminal transmits the user's input in real time to the server, which has a means of analyzing the content of the conversation and determining whether it constitutes harassment.

[0858] Judgment Phase

[0859] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine to determine whether it is suspected of harassment. At this time, the content is scored by a judgment means, and if it exceeds a certain threshold, the process proceeds to the next step.

[0860] Evidence Gathering Phase

[0861] 4. If the server judges that harassment is highly suspected, it sends a command to the device to start automatic recording or video recording. The device receives this command and automatically starts recording audio or video.

[0862] The device captures and encodes audio data to record what is happening around the user.

[0863] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[0864] 6. The device uploads the encrypted data to the server.

[0865] Reporting Phase

[0866] 7. The server receives the uploaded evidence data and analyzes it, using speech recognition technology to convert the audio data into text and extract the key parts.

[0867] 8. The server creates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0868] 9. The server automatically sends a report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The report is sent via email or a dedicated portal.

[0869] Feedback Phase

[0870] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[0871] For example: "Your report was successfully submitted. Please wait for our response."

[0872] Mental care support

[0873] 11. If the server determines that the user needs mental health care, it will automatically contact a mental health clinic and, with the user's consent, arrange an appointment with a specialist.

[0874] The above is a specific form for implementing the invention. This system allows victims to easily and safely report harassment and receive prompt support. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[0875] The processing flow will be explained below.

[0876] Step 1:

[0877] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[0878] Step 2:

[0879] The device sends the user's input, including text and voice data, to the server in real time.

[0880] Step 3:

[0881] The server analyzes the conversation content received using a natural language processing (NLP) engine to determine whether it is suspected of harassment. Based on the analysis results, a certain score is generated.

[0882] Step 4:

[0883] If the server finds that the score exceeds a certain threshold, it determines that harassment is suspected and moves on to the evidence collection phase.

[0884] Step 5:

[0885] The server sends a command to the device to start automatic recording and shooting. The device receives this command and automatically starts recording and shooting audio and video.

[0886] Step 6:

[0887] The device encrypts the evidence data (audio, video) collected and uploads the data to a server.

[0888] Step 7:

[0889] The server receives and analyzes the uploaded evidence data, converting audio data into text using speech recognition technology and extracting key parts.

[0890] Step 8:

[0891] The server generates a standardized report format based on the analysis results, which includes a summary of the problem and links to supporting data.

[0892] Step 9:

[0893] The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., police, labor standards inspection office) via email or a dedicated portal.

[0894] Step 10:

[0895] The server then provides the user with a status update and feedback on next steps. The user receives a notification within the application.

[0896] Step 11:

[0897] The server provides mental health support to the user as needed, and with the user's consent, contacts and arranges appointments with mental health clinics.

[0898] Example 1

[0899] 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."

[0900] In the past, proper reporting and support for harassment required specialized knowledge and time, making it difficult for victims to receive prompt action. Furthermore, there was no comprehensive system in place to handle the entire process, including collecting and safely managing evidence, properly reporting to the relevant authorities, and providing mental health care. This created a mental burden for victims, making them hesitant to report harassment.

[0901] 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.

[0902] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, a feedback means for sending a notification to the user after reporting and providing feedback, and a support means for determining the need for mental health care and contacting a medical institution if necessary. This enables prompt reporting of harassment, safe management of evidence, reporting to appropriate relevant institutions, and mental health care support for users.

[0903] "User" refers to a person who uses this system to report harassment issues and receive support.

[0904] "Terminal" refers to a device used by a user that has a dedicated application installed for interacting with generative AI.

[0905] "Generative AI" refers to artificial intelligence technology that understands user input and responds appropriately.

[0906] "Dialogue management means" refers to the function of managing the dialogue between the user and generative AI and processing the data appropriately.

[0907] "Determination means" refers to a function that analyzes the content of conversations with generative AI and determines whether there is any suspicion of harassment.

[0908] "Evidence collection means" refers to a function that automatically records and photographs audio and video on the device if harassment is suspected.

[0909] "Data management means" refers to the function for securely encrypting collected evidence data and uploading it to a server.

[0910] A "server" refers to a central computer that manages the entire system and analyzes and communicates various data.

[0911] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0912] "Feedback mechanism" refers to the functionality to send notifications to users after a report is made and provide feedback on status updates and next steps.

[0913] "Support measures" refers to the function of determining the need for mental care and contacting a medical institution when necessary.

[0914] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[0915] The system begins when a user interacts with the generative AI using a device with a dedicated application installed. The interaction is conducted via text input or voice input, and the content is sent to the server.

[0916] Dialogue Management

[0917] The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text input or voice input. For example, the user might type, "Recently, my boss at work has been verbally abusing me almost every day." The device then sends the user's input to the server in real time. At this time, the device temporarily stores the input in a buffer and transmits it over the internet using a secure communication protocol (e.g., HTTPS).

[0918] Judgment means

[0919] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API) to determine whether there is any suspicion of harassment. This determination is based on a scoring system, and if the score exceeds a certain threshold, the system proceeds to the next phase.

[0920] Evidence collection

[0921] If harassment is suspected, the server sends a command to the device to start automatic recording and filming. The device automatically starts recording audio or video when instructed to do so using its built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in the device's storage. The device then uploads the encrypted data to the server. The device uses the HTTPS protocol to securely and quickly send the data to the server.

[0922] Data Management and Reporting

[0923] The server receives the uploaded evidence data and, if it is audio data, converts it into text using speech recognition technology (e.g., IBM Watson Speech to Text API). Video data is analyzed in the same way. The server creates a standardized report format based on the analysis results. The report includes a summary of the problem, a link to the collected evidence data, and the analysis results. The server sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The server sends the report using a pre-configured mail server or dedicated portal.

[0924] Feedback tools and mental health support

[0925] After reporting, the server sends a notification to the user, providing an update on the situation and feedback on next steps. For example, a notification stating "The report was sent successfully. Please wait for our response" may be displayed on the device. Furthermore, if the server determines that the user needs mental health care, it can use the Google Calendar API to arrange an appointment with a mental health clinic and send a notification to the user.

[0926] This system allows victims to easily and safely report harassment and receive prompt action. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[0927] Prompt Sentence Examples

[0928] "I feel like I am being verbally abused by my boss at work every day. Please tell me the steps to report this and how to gather evidence."

[0929] When the user inputs information based on this prompt, the generative AI can provide appropriate support to the user and respond quickly and safely.

[0930] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0931] Step 1:

[0932] A user begins a dialogue with the generative AI using a device with a dedicated application installed. The user describes the harassment situation they are facing using text input or voice input. For example, they might say, "Recently, my boss at work has been verbally abusing me almost every day." The input data is then imported into the device in text format.

[0933] Input: The user inputs information about the harassment into the device using text or voice.

[0934] Output: The terminal temporarily stores the user's input as text data and sends it to the next process.

[0935] Step 2:

[0936] The device sends the user's input to the server in real time. The device stores the input in a buffer and sends it to the server using a secure communication protocol (e.g., HTTPS).

[0937] Input: User input (text data).

[0938] Output: The user's input sent to the server.

[0939] Step 3:

[0940] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API). Based on this analysis, the server scores the likelihood of harassment and proceeds to the next step if the score exceeds a certain threshold.

[0941] Input: User input sent to the server.

[0942] Output: Scoring data as the analysis result.

[0943] The server passes the input text data to a natural language processing engine, which analyzes it for keywords and context that suggest harassment, and scores it based on the results of this analysis.

[0944] Step 4:

[0945] If the server determines that there is a strong suspicion of harassment, it will send instructions to the device to automatically start recording and filming.

[0946] Input: Analysis results (scoring data).

[0947] Output: Automatic recording and shooting instructions to the device.

[0948] Step 5:

[0949] The device receives the command and automatically starts recording audio or video using the built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in storage.

[0950] Input: Automatic recording and shooting instructions from the server.

[0951] Output: Encrypted audio or video data.

[0952] Step 6:

[0953] The device uploads the encrypted evidence data to the server. The device uses the HTTPS protocol to send the data to the server safely and quickly.

[0954] Input: Encrypted audio or video data.

[0955] Output: The encrypted data uploaded to the server.

[0956] Step 7:

[0957] The server receives the uploaded evidence data and converts it into text using voice recognition technology (e.g., IBM Watson Speech to Text API) if it is audio data. Video data is also analyzed in the same way.

[0958] Input: Encrypted evidence data.

[0959] Output: Parsed data converted to text.

[0960] Step 8:

[0961] The server then generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[0962] Input: Parsed data converted to text.

[0963] Output: Standardized report.

[0964] Step 9:

[0965] The server automatically sends reports to the relevant departments and public institutions using a pre-configured mail server or dedicated portal.

[0966] Input: Standardized report.

[0967] Output: Reports sent to responsible departments and public authorities.

[0968] Step 10:

[0969] After the server reports, it will send a notification to the user to provide a status update and feedback on next steps, such as a notification displayed on the device stating "Report submitted successfully. Please wait for our response."

[0970] Input: Report status data.

[0971] Output: Feedback notification to the user.

[0972] Step 11:

[0973] If the server determines that the user needs mental health care, it will automatically contact a mental health clinic. The server can use the Google Calendar API or similar to arrange an appointment with the mental health clinic and send a notification to the user.

[0974] Input: A determination of the user's mental health needs.

[0975] Output: Mental clinic appointment notification.

[0976] (Application example 1)

[0977] 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."

[0978] Conventional harassment reporting systems require users to manually collect evidence, create a report, and report to a public institution or department in charge, which is time-consuming and makes it difficult to respond quickly.The present invention aims to provide a system that allows users to quickly and easily report harassment and receive appropriate support promptly.

[0979] 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.

[0980] In this invention, the server includes a dialogue management means for a user to dialogue with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and a hearing means for the generative AI to transmit the dialogue content to the server in real time when the user inputs voice or text into a predetermined input means. This enables users to easily report harassment and quickly receive appropriate support and mental care.

[0981] The "dialogue management means" provides a function that allows users to interact with generative AI via a terminal.

[0982] The "determination means" has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[0983] The "evidence collection means" is a function that automatically starts recording or photographing on the terminal when the assessment means determines that harassment is suspected.

[0984] The "data management means" has a function for safely encrypting the evidence data collected by the evidence collection means and uploading it to a server.

[0985] The "reporting means" has the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[0986] A "hearing means" is a function that allows the generative AI to send the content of the dialogue to a server in real time when the user inputs voice or text into a specified input means.

[0987] "Generative AI" refers to artificial intelligence technology that generates dialogue based on user input and analyzes the content of the dialogue.

[0988] "Device" refers to a terminal used by a user, such as a smartphone, smart glasses, a head-mounted display, or a robot.

[0989] "Encryption" refers to a technology for protecting data from being leaked to third parties while maintaining its security.

[0990] A "natural language processing engine" includes technology for analyzing and understanding the meaning of user input.

[0991] This invention provides a system that allows users to quickly and easily report harassment issues and receive appropriate support. Specifically, it has the following configuration.

[0992] System Overview

[0993] The system includes the following means for interacting with generative AI using a user's device to determine whether harassment is suspected.

[0994] Dialogue Management Tools

[0995] Judgment means

[0996] Evidence collection methods

[0997] Data Management Measures

[0998] Reporting means

[0999] Hearing methods

[1000] Hardware and software used

[1001] Hardware: Smartphones, smart glasses, head-mounted displays, robots, etc.

[1002] Software: Python, Requests library, SpeechRecognition library, Natural Language Processing engine (e.g. spaCy or NLTK)

[1003] Program processing

[1004] User Input and Hearing Phase

[1005] The user uses a designated device (e.g., a smartphone) to initiate a dialogue with the generative AI. The user registers details of the harassment through voice or text input. At this time, the generative AI sends the user's input to the server in real time. Examples of prompt sentences include the following:

[1006] "I'm having trouble with verbal abuse from my boss at work."

[1007] "I'm being harassed by my classmates at school."

[1008] Assessment and evidence gathering phase

[1009] The server analyzes the received user input using a natural language processing engine to determine whether there is any suspicion of harassment. If there is any suspicion, the server sends instructions to the device to automatically record and record audio and video. The device then receives the instructions, automatically collects audio and video from the surrounding area, and securely encrypts the data.

[1010] Data management and analysis phase

[1011] The encrypted evidence data is uploaded to a server, which analyzes the uploaded data and automatically notifies the relevant departments and public institutions. Specifically, the collected evidence data is converted into a standardized report format and sent via email or a dedicated portal.

[1012] Feedback Phase

[1013] If the report is successful, the user is notified and given feedback on progress and next steps, and the server is available to assist the user in providing additional information or asking questions.

[1014] Mental care support

[1015] Finally, if the server determines that the user needs mental health care, it will automatically schedule an appointment with a specialist with the user's consent, allowing the user to receive appropriate support promptly.

[1016] The above is a specific embodiment of the present invention. This system allows users to easily report harassment and receive prompt support and assistance. Furthermore, the system automatically notifies the appropriate authorities and provides mental health care, allowing users to use the system with peace of mind.

[1017] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1018] Step 1:

[1019] The user initiates a dialogue with the generative AI via a device. The user registers details of the harassment using voice or text input. Examples of input include:

[1020] "I'm having trouble with verbal abuse from my boss at work."

[1021] "I'm being harassed by my classmates at school."

[1022] Input data is sent from the terminal to the server in real time.

[1023] Step 2:

[1024] The server analyzes the received user input data using a natural language processing engine. Specifically, it tokenizes the input text and analyzes its meaning. The server determines whether the input is suspected of harassment and assigns a score. This analysis uses a generative AI model.

[1025] Input: User-entered text or voice data

[1026] Output: Suspected harassment score

[1027] Step 3:

[1028] If the server determines that harassment is suspected, it will send an instruction to the device to automatically record and record. When the device receives this instruction, it will automatically collect audio and video from the surrounding area. The collected data is immediately encrypted.

[1029] Input: Server recording start instruction

[1030] Output: Encrypted audio and video data

[1031] Step 4:

[1032] The evidence data encrypted on the device is uploaded to a server, where it is analyzed and reported to the relevant departments and public institutions. Specifically, the evidence data is converted into a standardized reporting format and sent via email or a dedicated portal.

[1033] Input: Encrypted evidence data

[1034] Output: Report and transmission log

[1035] Step 5:

[1036] If the report is successful, the server sends a notification to the user. The feedback includes information about the report result and next steps. The user can also provide additional information or ask questions, and an interface is provided for this.

[1037] Input: Report result, additional information

[1038] Output: Notification and feedback to the user

[1039] Step 6:

[1040] The server determines the user's mental health needs and automatically schedules appointments with specialists if necessary. This appointment requires the user's consent, and arrangements are made only after the consent is confirmed.

[1041] Input: User consent, mental health care need data

[1042] Output: Specialist appointment information and user notification

[1043] The above are the specific processing steps for carrying out the present invention, which enable users to quickly and easily report harassment and receive appropriate support.

[1044] 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.

[1045] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system improves analysis accuracy and provides appropriate mental health support.

[1046] Hearing phase

[1047] 1. A user initiates a conversation with a generative AI chatbot on their device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[1048] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[1049] 2. The device sends the user's input, including text and voice data, to the server in real time.

[1050] Judgment Phase

[1051] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected. The emotion engine recognizes emotions from the user's input and voice data and reflects them in the analysis results.

[1052] Example: The emotion engine recognizes that a user is stressed or anxious based on their tone of voice and the way they use words.

[1053] Evidence Gathering Phase

[1054] 4. If the server determines that harassment is highly suspected based on the analysis results of the emotion engine, it sends a command to the device to start automatic recording and filming. The device receives this command and automatically starts recording and filming audio and video.

[1055] The device captures and encodes audio data to record what is happening around the user.

[1056] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[1057] 6. The device uploads the encrypted data to the server.

[1058] Reporting Phase

[1059] 7. The server receives the uploaded evidence data and analyzes it. Audio data is converted into text using speech recognition technology, and key parts are extracted.

[1060] 8. The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[1061] 9. The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). It is sent via email or a dedicated portal.

[1062] Feedback Phase

[1063] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[1064] For example: "Your report was successfully submitted. Please wait for our response."

[1065] Mental care support

[1066] 11. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic. With the user's consent, it can arrange an appointment with a specialist.

[1067] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[1068] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[1069] The processing flow will be explained below.

[1070] Step 1:

[1071] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[1072] Step 2:

[1073] The device sends the user's input, including text and voice data, to the server in real time.

[1074] Step 3:

[1075] The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine, and determines whether the dialogue is suspected of harassment and the user's emotional state.

[1076] Step 4:

[1077] If the server detects suspicion of harassment and the emotion engine detects high stress or anger, it sends instructions to the terminal to proceed to the evidence collection phase.

[1078] Step 5:

[1079] The device receives instructions from the server and automatically starts recording and capturing images. When instructed to record or capture images, the device captures audio and video data around the user.

[1080] Step 6:

[1081] The device encrypts the evidence data (audio, video) collected, converts it into a secure format, and uploads it to the server.

[1082] Step 7:

[1083] The server receives the uploaded evidence data, converts the audio data into text using voice recognition technology, and extracts and analyzes the important parts.

[1084] Step 8:

[1085] The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[1086] Step 9:

[1087] The server automatically sends the report to the relevant department or public institution via email or a dedicated portal.

[1088] Step 10:

[1089] The server then provides the user with a status update and feedback on next steps. The user receives a notification from the application.

[1090] Step 11:

[1091] If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic to provide appropriate mental health care support. With the user's consent, it will arrange an appointment with a specialist.

[1092] Step 12:

[1093] If the user wishes to provide feedback or additional information, they can continue to interact with the generative AI through their device. The server will analyze the new information and, if necessary, perform the evidence gathering and reporting phases again.

[1094] The above is a specific embodiment of the invention, and a detailed step-by-step explanation of the overall system flow. This system allows users to easily and safely report harassment, and also allows them to receive mental health support through the emotion engine.

[1095] Example 2

[1096] 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."

[1097] Conventional anti-harassment systems make it difficult for users to receive appropriate support promptly, and the need to manually collect evidence and report incidents places an excessive burden on victims. Furthermore, support provided often does not take into account the user's mental state, resulting in insufficient mental care.

[1098] 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.

[1099] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the content of the dialogue obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and an emotion engine that recognizes the user's emotions. This enables victims to quickly and efficiently report harassment and also enables them to receive appropriate mental care that takes into account the user's mental state.

[1100] "User" refers to an individual who uses the system to report a harassment issue.

[1101] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1102] "Generative AI" refers to an artificial intelligence model that generates natural language and engages in dialogue.

[1103] "Dialogue management means" refers to a software module with the function of managing and recording dialogue between a user and a generative AI.

[1104] The "determination means" refers to a software module that has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[1105] "Evidence collection means" refers to a software module that has the function of automatically starting recording and filming on a device when it is determined that harassment is suspected.

[1106] "Data management means" refers to a software module that has the function of securely encrypting collected evidence data and uploading it to a server.

[1107] "Reporting means" refers to a software module that has the function of analyzing evidence data uploaded to the server and automatically reporting to relevant departments and public institutions.

[1108] "Emotion engine" refers to a software module that has the function of analyzing and recognizing a user's emotions.

[1109] The system of the present invention provides a set of features that allow users to report harassment issues and receive appropriate assistance. The system is implemented using specific hardware and software.

[1110] Basic configuration

[1111] The system consists of the following main components:

[1112] Device: An electronic device used by a user, such as a smartphone or tablet.

[1113] Server: A remote computer system for analyzing, storing, and reporting data.

[1114] Generative AI: AI systems that generate natural language and engage in dialogue.

[1115] Natural Language Processing (NLP) engine: Software that analyzes text data (e.g., spaCy, NLTK).

[1116] Emotion engine: Software that analyzes user emotions (e.g., Microsoft Azure Cognitive Services' Text Analytics API).

[1117] Processing flow

[1118] 1. The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[1119] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[1120] 2. The device sends the user's input (text data or voice data) to the server in real time. The device sends the data using the HTTP protocol.

[1121] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether it is suspected of harassment. The server uses a Python-based NLP library (e.g., spaCy or NLTK) to perform text analysis and an emotion engine to analyze emotions.

[1122] 4. If the server determines that harassment is highly suspected, it sends a command to the device to automatically start recording and filming. The server sends the command in real time using the WebSocket protocol.

[1123] 5. The device securely encrypts the collected evidence data (audio, video) and uploads it to the server. The device uses the AES encryption algorithm and transmits the data using the HTTPS protocol.

[1124] 6. The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), and extracts key parts.

[1125] 7. The server uses a template engine (e.g., Jinja2) to create a standardized report format based on the analysis results. This report includes a summary of the problem, links to collected evidence data, and the analysis results.

[1126] 8. The server automatically sends the report to the relevant departments or public institutions by email using the SMTP protocol or by sending the data via a dedicated portal API.

[1127] 9. After the server reports the incident, it sends a notification to the user to provide feedback on the status update and next steps. The server uses a push notification API (e.g., Firebase Cloud Messaging) to send the notification to the user's device.

[1128] 10. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental clinic. The server will send an email or a notification to the user, and if an appointment with a specialist is made online, it will use the reservation system's API.

[1129] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[1130] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[1131] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1132] Step 1:

[1133] The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[1134] Input: Text or voice input from the user.

[1135] Output: Beginning of dialogue with generative AI.

[1136] What happens: The user taps "Open app" and then types "Lately, my boss at work has been verbally abusing me almost every day," or types the same thing out loud.

[1137] Step 2:

[1138] The device sends the user's input (text data or voice data) to the server in real time.

[1139] Input: Text or voice data entered by the user.

[1140] Output: The data sent to the server.

[1141] Specific operation: The terminal sends text data and audio data to the server using the HTTP protocol.

[1142] Step 3:

[1143] The server analyzes the conversation content received using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected.

[1144] Input: Text or voice data sent from the device.

[1145] Output: The result of the judgment on suspected harassment.

[1146] How it works: The server performs text analysis using a Python-based NLP library (e.g., spaCy or NLTK) and analyzes emotions using the Microsoft Azure Cognitive Services Text Analytics API. The emotion engine recognizes that the user is feeling stressed or anxious based on their tone of voice and choice of words.

[1147] Step 4:

[1148] If the server determines that there is a strong suspicion of harassment, it sends instructions to the device to begin automatic recording and filming.

[1149] Input: Judgment result.

[1150] Output: Instructions to the terminal.

[1151] Specific operation: The server sends instructions to the terminal in real time using the WebSocket protocol.

[1152] Step 5:

[1153] The evidence data (audio, video) collected by the device is securely encrypted and uploaded to the server.

[1154] Input: Evidence data obtained as a result of automatic recording and photography.

[1155] Output: The encrypted data.

[1156] Specific operation: The terminal encrypts the evidence data using the AES encryption algorithm and sends it to the server using the HTTPS protocol.

[1157] Step 6:

[1158] The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology, and extracts the important parts.

[1159] Input: Encrypted evidence data.

[1160] Output: Text data with important parts extracted.

[1161] How it works: The server uses the speech recognition APIs of Google Cloud Speech-to-Text and Amazon Transcribe to analyze the audio data and extract the key parts.

[1162] Step 7:

[1163] The server creates a standardized report format based on the analysis results.

[1164] Input: Text data with important parts extracted.

[1165] Output: Report format.

[1166] Specific behavior: The server uses a template engine (e.g., Jinja2) to generate a report that includes a summary of the problem and links to supporting data.

[1167] Step 8:

[1168] The server automatically sends the report to the relevant department or public institution.

[1169] Input: Report format.

[1170] Output: The report sent.

[1171] Specific operation: The server sends an email using the SMTP protocol or sends data via a dedicated portal API.

[1172] Step 9:

[1173] Once the server has notified the user, it will send a notification to provide feedback on the status update and next steps.

[1174] Input: Reported report.

[1175] Output: Feedback to the user.

[1176] Specific operation: The server uses a push notification API (e.g., Firebase Cloud Messaging) to send a notification to the user's device.

[1177] Step 10:

[1178] If the server determines using the emotion engine that the user needs mental care, it will automatically contact a mental clinic.

[1179] Input: Analysis results of the emotion engine.

[1180] Output: Contact mental health clinic.

[1181] Specific operation: The server sends emails and notifications to the user, and uses the reservation system's API to make an appointment with a specialist online.

[1182] (Application example 2)

[1183] 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."

[1184] Conventional harassment reporting systems are only effective when the user is in a fixed environment, making it difficult to respond when the user is in a car or on the move. In addition, they often do not provide appropriate mental health support that takes the user's emotional state into consideration, which can increase the user's mental burden. Therefore, there is a need for a system that can instantly report and record harassment even while on the move, monitor the user's emotional state, and provide appropriate mental health support.

[1185] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1186] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content and the user's emotional data obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording within the autonomous vehicle if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, and a mental care means for continuously monitoring the user's emotional state and providing mental care support as needed. This enables harassment to be immediately reported and recorded even while on the move, and appropriate mental care support that takes the user's emotional state into consideration.

[1187] "User" refers to an individual who uses the system to report harassment issues.

[1188] "Terminal" refers to an electronic device operated by a user, including smartphones and in-car infotainment systems.

[1189] "Generative AI" refers to an artificial intelligence system that supports dialogue with users and has the ability to perform natural language processing and emotion analysis.

[1190] "Dialogue management means" refers to the management function that allows users to interact with generative AI via a terminal.

[1191] The "determination means" refers to a function that analyzes the content of the dialogue and the user's emotional data obtained via the dialogue management means and determines whether harassment is suspected.

[1192] "Evidence collection means" refers to a function that automatically starts recording and filming within an autonomous vehicle if it is determined that harassment is suspected.

[1193] "Data management means" refers to a function that safely encrypts evidence data collected by evidence collection means and uploads it to a server.

[1194] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[1195] "Mental care means" refers to a function that continuously monitors the user's emotional state and provides mental care support as needed.

[1196] "Emotion data" refers to data that indicates the user's emotional state and that has been analyzed by the emotion engine.

[1197] An "emotion engine" refers to a system that recognizes emotions from user input and voice data and reflects them in the analysis results.

[1198] This invention provides a system that allows users to report harassment issues in autonomous vehicles and receive appropriate support. Specific embodiments of this invention are described below. This system includes both hardware and software, and its main components are a user terminal and a server.

[1199] Program Overview

[1200] 1. How users interact with generative AI via their devices:

[1201] The user initiates a dialogue with the generative AI using the infotainment system or smartphone installed in the autonomous vehicle. A dedicated application is installed on the device, and the user interacts with the AI ​​using voice or text input.

[1202] 2. Analysis of dialogue content and emotion data:

[1203] The user's input and voice data are sent to a server in real time, where a natural language processing engine (NLP engine) and an emotion engine analyze the data and determine whether it is suspected harassment. The emotion engine recognizes the user's emotional state and feeds that data back to the AI ​​model.

[1204] 3. Collecting evidence:

[1205] If the server determines that harassment is highly suspected, it automatically sends instructions to the device to start recording and filming. The device collects evidence data using the in-car camera and microphone, encrypts it, and then uploads the encrypted data to the server.

[1206] 4. Data Management and Analysis:

[1207] The server analyzes the uploaded evidence data and uses natural language processing technology to extract key information, which is then converted into a standardized reporting format and automatically sent to the relevant departments and public institutions.

[1208] 5. Mental health support:

[1209] The server determines whether the user needs mental care based on the results of the emotion engine. If necessary, it introduces the user to a specialized institution that provides mental care support and arranges for a reservation.

[1210] The specific hardware and software used

[1211] Hardware:

[1212] Smartphone

[1213] Autonomous vehicle infotainment systems

[1214] In-car camera and microphone

[1215] software:

[1216] SpeechRecognition library: Used to convert voice input to text.

[1217] EmotionRecognition library: Used to analyze the user's emotional state.

[1218] VideoCapture library: Provides audio and video recording functions.

[1219] CloudStorage module: Encrypts and uploads evidence data to the cloud.

[1220] ReportGenerator module: Provides automatic report generation functionality.

[1221] Notifications module: Notifies the user.

[1222] Mental Care module: Contact and schedule mental health support.

[1223] Specific examples

[1224] For example, if a user shouts "harassment" inside an autonomous vehicle, the system immediately performs sentiment analysis and automatically starts recording. The collected evidence data is encrypted and securely uploaded to the cloud. The server then analyzes the collected data, generates a standardized report, and automatically sends it to the designated department. For example, if a user says, "My boss is verbally abusing me at work," the system will detect harassment and begin responding.

[1225] Example prompt sentence:

[1226] "I would like to report harassment at my workplace. Please start recording and collecting evidence."

[1227] "Now, record any problematic conversations you hear while riding alone."

[1228] The above is a specific embodiment of the present invention. This system allows users to easily and safely report harassment even while on the move, enabling a prompt response. Furthermore, the introduction of an emotion engine provides analysis that takes into account the user's mental state and provides appropriate mental care support.

[1229] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1230] Step 1:

[1231] The user initiates a dialogue with the generative AI via a device. The user inputs voice or text, which the device sends to the server in real time. Input: Voice data or text data. Output: Data sent to the server.

[1232] Step 2:

[1233] The server analyzes the received voice or text data using a natural language processing engine (NLP engine) to understand what the user is saying. The server then analyzes the voice data using an emotion engine to recognize the user's emotions. Input: Data sent to the server. Output: Analysis results (text content and emotion data).

[1234] Step 3:

[1235] Based on the analysis results, the server determines whether there is any suspicion of harassment. The server analyzes the content of the user's remarks and emotional state, and if it determines that there is suspicion of harassment, it sends instructions to the device to automatically record and film. Input: Analysis results. Output: Instruction to start recording and filming.

[1236] Step 4:

[1237] The terminal receives instructions from the server and starts recording and capturing images using the camera and microphone inside the autonomous vehicle. Evidence data is collected and encrypted. Input: Instruction to start recording and capturing images. Output: Encrypted evidence data.

[1238] Step 5:

[1239] The terminal uploads the encrypted evidence data to the server. Input: Encrypted evidence data. Output: Data uploaded to the server.

[1240] Step 6:

[1241] The server analyzes the uploaded evidence data and extracts important information. It then converts the extracted information into a standardized report format and automatically notifies the relevant departments and public institutions. Input: Uploaded evidence data. Output: Report generation and notification.

[1242] Step 7:

[1243] The server determines whether the user needs mental care based on the results of the emotion engine. If it determines that mental care is necessary, it introduces the user to a specialized institution for mental care support and arranges an appointment. Input: Analysis results of the emotion engine. Output: Provision of mental care support.

[1244] The above are the specific processing steps in the system for realizing the present invention. The specific operations performed in each step, as well as the inputs and outputs, have also been explained.

[1245] 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.

[1246] 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.

[1247] 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.

[1248] [Fourth embodiment]

[1249] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1250] 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.

[1251] 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).

[1252] 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.

[1253] 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.

[1254] 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).

[1255] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] 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.

[1260] 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.

[1261] 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."

[1262] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[1263] Hearing phase

[1264] 1. The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[1265] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[1266] 2. The terminal transmits the user's input in real time to the server, which has a means of analyzing the content of the conversation and determining whether it constitutes harassment.

[1267] Judgment Phase

[1268] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine to determine whether it is suspected of harassment. At this time, the content is scored by a judgment means, and if it exceeds a certain threshold, the process proceeds to the next step.

[1269] Evidence Gathering Phase

[1270] 4. If the server judges that harassment is highly suspected, it sends a command to the device to start automatic recording or video recording. The device receives this command and automatically starts recording audio or video.

[1271] The device captures and encodes audio data to record what is happening around the user.

[1272] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[1273] 6. The device uploads the encrypted data to the server.

[1274] Reporting Phase

[1275] 7. The server receives the uploaded evidence data and analyzes it, using speech recognition technology to convert the audio data into text and extract the key parts.

[1276] 8. The server creates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[1277] 9. The server automatically sends a report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The report is sent via email or a dedicated portal.

[1278] Feedback Phase

[1279] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[1280] For example: "Your report was successfully submitted. Please wait for our response."

[1281] Mental care support

[1282] 11. If the server determines that the user needs mental health care, it will automatically contact a mental health clinic and, with the user's consent, arrange an appointment with a specialist.

[1283] The above is a specific form for implementing the invention. This system allows victims to easily and safely report harassment and receive prompt support. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[1284] The processing flow will be explained below.

[1285] Step 1:

[1286] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[1287] Step 2:

[1288] The device sends the user's input, including text and voice data, to the server in real time.

[1289] Step 3:

[1290] The server analyzes the conversation content received using a natural language processing (NLP) engine to determine whether it is suspected of harassment. Based on the analysis results, a certain score is generated.

[1291] Step 4:

[1292] If the server finds that the score exceeds a certain threshold, it determines that harassment is suspected and moves on to the evidence collection phase.

[1293] Step 5:

[1294] The server sends a command to the device to start automatic recording and shooting. The device receives this command and automatically starts recording and shooting audio and video.

[1295] Step 6:

[1296] The device encrypts the evidence data (audio, video) collected and uploads the data to a server.

[1297] Step 7:

[1298] The server receives and analyzes the uploaded evidence data, converting audio data into text using speech recognition technology and extracting key parts.

[1299] Step 8:

[1300] The server generates a standardized report format based on the analysis results, which includes a summary of the problem and links to supporting data.

[1301] Step 9:

[1302] The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., police, labor standards inspection office) via email or a dedicated portal.

[1303] Step 10:

[1304] The server then provides the user with a status update and feedback on next steps. The user receives a notification within the application.

[1305] Step 11:

[1306] The server provides mental health support to the user as needed, and with the user's consent, contacts and arranges appointments with mental health clinics.

[1307] Example 1

[1308] 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."

[1309] In the past, proper reporting and support for harassment required specialized knowledge and time, making it difficult for victims to receive prompt action. Furthermore, there was no comprehensive system in place to handle the entire process, including collecting and safely managing evidence, properly reporting to the relevant authorities, and providing mental health care. This created a mental burden for victims, making them hesitant to report harassment.

[1310] 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.

[1311] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, a feedback means for sending a notification to the user after reporting and providing feedback, and a support means for determining the need for mental health care and contacting a medical institution if necessary. This enables prompt reporting of harassment, safe management of evidence, reporting to appropriate relevant institutions, and mental health care support for users.

[1312] "User" refers to a person who uses this system to report harassment issues and receive support.

[1313] "Terminal" refers to a device used by a user that has a dedicated application installed for interacting with generative AI.

[1314] "Generative AI" refers to artificial intelligence technology that understands user input and responds appropriately.

[1315] "Dialogue management means" refers to the function of managing the dialogue between the user and generative AI and processing the data appropriately.

[1316] "Determination means" refers to a function that analyzes the content of conversations with generative AI and determines whether there is any suspicion of harassment.

[1317] "Evidence collection means" refers to a function that automatically records and photographs audio and video on the device if harassment is suspected.

[1318] "Data management means" refers to the function for securely encrypting collected evidence data and uploading it to a server.

[1319] A "server" refers to a central computer that manages the entire system and analyzes and communicates various data.

[1320] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[1321] "Feedback mechanism" refers to the functionality to send notifications to users after a report is made and provide feedback on status updates and next steps.

[1322] "Support measures" refers to the function of determining the need for mental care and contacting a medical institution when necessary.

[1323] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Specific embodiments of the system are described below.

[1324] The system begins when a user interacts with the generative AI using a device with a dedicated application installed. The interaction is conducted via text input or voice input, and the content is sent to the server.

[1325] Dialogue Management

[1326] The user initiates a dialogue with the generative AI via a device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text input or voice input. For example, the user might type, "Recently, my boss at work has been verbally abusing me almost every day." The device then sends the user's input to the server in real time. At this time, the device temporarily stores the input in a buffer and transmits it over the internet using a secure communication protocol (e.g., HTTPS).

[1327] Judgment means

[1328] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API) to determine whether there is any suspicion of harassment. This determination is based on a scoring system, and if the score exceeds a certain threshold, the system proceeds to the next phase.

[1329] Evidence collection

[1330] If harassment is suspected, the server sends a command to the device to start automatic recording and filming. The device automatically starts recording audio or video when instructed to do so using its built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in the device's storage. The device then uploads the encrypted data to the server. The device uses the HTTPS protocol to securely and quickly send the data to the server.

[1331] Data Management and Reporting

[1332] The server receives the uploaded evidence data and, if it is audio data, converts it into text using speech recognition technology (e.g., IBM Watson Speech to Text API). Video data is analyzed in the same way. The server creates a standardized report format based on the analysis results. The report includes a summary of the problem, a link to the collected evidence data, and the analysis results. The server sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). The server sends the report using a pre-configured mail server or dedicated portal.

[1333] Feedback tools and mental health support

[1334] After reporting, the server sends a notification to the user, providing an update on the situation and feedback on next steps. For example, a notification stating "The report was sent successfully. Please wait for our response" may be displayed on the device. Furthermore, if the server determines that the user needs mental health care, it can use the Google Calendar API to arrange an appointment with a mental health clinic and send a notification to the user.

[1335] This system allows victims to easily and safely report harassment and receive prompt action. It also automates the appropriate reporting to relevant authorities and mental health support, making it a system that users can use with peace of mind.

[1336] Prompt Sentence Examples

[1337] "I feel like I am being verbally abused by my boss at work every day. Please tell me the steps to report this and how to gather evidence."

[1338] When the user inputs information based on this prompt, the generative AI can provide appropriate support to the user and respond quickly and safely.

[1339] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1340] Step 1:

[1341] A user begins a dialogue with the generative AI using a device with a dedicated application installed. The user describes the harassment situation they are facing using text input or voice input. For example, they might say, "Recently, my boss at work has been verbally abusing me almost every day." The input data is then imported into the device in text format.

[1342] Input: The user inputs information about the harassment into the device using text or voice.

[1343] Output: The terminal temporarily stores the user's input as text data and sends it to the next process.

[1344] Step 2:

[1345] The device sends the user's input to the server in real time. The device stores the input in a buffer and sends it to the server using a secure communication protocol (e.g., HTTPS).

[1346] Input: User input (text data).

[1347] Output: The user's input sent to the server.

[1348] Step 3:

[1349] The server analyzes the received dialogue using a natural language processing engine (e.g., Google Cloud Natural Language API). Based on this analysis, the server scores the likelihood of harassment and proceeds to the next step if the score exceeds a certain threshold.

[1350] Input: User input sent to the server.

[1351] Output: Scoring data as the analysis result.

[1352] The server passes the input text data to a natural language processing engine, which analyzes it for keywords and context that suggest harassment, and scores it based on the results of this analysis.

[1353] Step 4:

[1354] If the server determines that there is a strong suspicion of harassment, it will send instructions to the device to automatically start recording and filming.

[1355] Input: Analysis results (scoring data).

[1356] Output: Automatic recording and shooting instructions to the device.

[1357] Step 5:

[1358] The device receives the command and automatically starts recording audio or video using the built-in microphone or camera. The collected data is encrypted in real time using encryption technology such as AES-256 and temporarily stored in storage.

[1359] Input: Automatic recording and shooting instructions from the server.

[1360] Output: Encrypted audio or video data.

[1361] Step 6:

[1362] The device uploads the encrypted evidence data to the server. The device uses the HTTPS protocol to send the data to the server safely and quickly.

[1363] Input: Encrypted audio or video data.

[1364] Output: The encrypted data uploaded to the server.

[1365] Step 7:

[1366] The server receives the uploaded evidence data and converts it into text using voice recognition technology (e.g., IBM Watson Speech to Text API) if it is audio data. Video data is also analyzed in the same way.

[1367] Input: Encrypted evidence data.

[1368] Output: Parsed data converted to text.

[1369] Step 8:

[1370] The server then generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[1371] Input: Parsed data converted to text.

[1372] Output: Standardized report.

[1373] Step 9:

[1374] The server automatically sends reports to the relevant departments and public institutions using a pre-configured mail server or dedicated portal.

[1375] Input: Standardized report.

[1376] Output: Reports sent to responsible departments and public authorities.

[1377] Step 10:

[1378] After the server reports, it will send a notification to the user to provide a status update and feedback on next steps, such as a notification displayed on the device stating "Report submitted successfully. Please wait for our response."

[1379] Input: Report status data.

[1380] Output: Feedback notification to the user.

[1381] Step 11:

[1382] If the server determines that the user needs mental health care, it will automatically contact a mental health clinic. The server can use the Google Calendar API or similar to arrange an appointment with the mental health clinic and send a notification to the user.

[1383] Input: A determination of the user's mental health needs.

[1384] Output: Mental clinic appointment notification.

[1385] (Application example 1)

[1386] 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."

[1387] Conventional harassment reporting systems require users to manually collect evidence, create a report, and report to a public institution or department in charge, which is time-consuming and makes it difficult to respond quickly.The present invention aims to provide a system that allows users to quickly and easily report harassment and receive appropriate support promptly.

[1388] 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.

[1389] In this invention, the server includes a dialogue management means for a user to dialogue with a generative AI via a terminal, a determination means for analyzing the dialogue content obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and a hearing means for the generative AI to transmit the dialogue content to the server in real time when the user inputs voice or text into a predetermined input means. This enables users to easily report harassment and quickly receive appropriate support and mental care.

[1390] The "dialogue management means" provides a function that allows users to interact with generative AI via a terminal.

[1391] The "determination means" has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[1392] The "evidence collection means" is a function that automatically starts recording or photographing on the terminal when the assessment means determines that harassment is suspected.

[1393] The "data management means" has a function for safely encrypting the evidence data collected by the evidence collection means and uploading it to a server.

[1394] The "reporting means" has the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[1395] A "hearing means" is a function that allows the generative AI to send the content of the dialogue to a server in real time when the user inputs voice or text into a specified input means.

[1396] "Generative AI" refers to artificial intelligence technology that generates dialogue based on user input and analyzes the content of the dialogue.

[1397] "Device" refers to a terminal used by a user, such as a smartphone, smart glasses, a head-mounted display, or a robot.

[1398] "Encryption" refers to a technology for protecting data from being leaked to third parties while maintaining its security.

[1399] A "natural language processing engine" includes technology for analyzing and understanding the meaning of user input.

[1400] This invention provides a system that allows users to quickly and easily report harassment issues and receive appropriate support. Specifically, it has the following configuration.

[1401] System Overview

[1402] The system includes the following means for interacting with generative AI using a user's device to determine whether harassment is suspected.

[1403] Dialogue Management Tools

[1404] Judgment means

[1405] Evidence collection methods

[1406] Data Management Measures

[1407] Reporting means

[1408] Hearing methods

[1409] Hardware and software used

[1410] Hardware: Smartphones, smart glasses, head-mounted displays, robots, etc.

[1411] Software: Python, Requests library, SpeechRecognition library, Natural Language Processing engine (e.g. spaCy or NLTK)

[1412] Program processing

[1413] User Input and Hearing Phase

[1414] The user uses a designated device (e.g., a smartphone) to initiate a dialogue with the generative AI. The user registers details of the harassment through voice or text input. At this time, the generative AI sends the user's input to the server in real time. Examples of prompt sentences include the following:

[1415] "I'm having trouble with verbal abuse from my boss at work."

[1416] "I'm being harassed by my classmates at school."

[1417] Assessment and evidence gathering phase

[1418] The server analyzes the received user input using a natural language processing engine to determine whether there is any suspicion of harassment. If there is any suspicion, the server sends instructions to the device to automatically record and record audio and video. The device then receives the instructions, automatically collects audio and video from the surrounding area, and securely encrypts the data.

[1419] Data management and analysis phase

[1420] The encrypted evidence data is uploaded to a server, which analyzes the uploaded data and automatically notifies the relevant departments and public institutions. Specifically, the collected evidence data is converted into a standardized report format and sent via email or a dedicated portal.

[1421] Feedback Phase

[1422] If the report is successful, the user is notified and given feedback on progress and next steps, and the server is available to assist the user in providing additional information or asking questions.

[1423] Mental care support

[1424] Finally, if the server determines that the user needs mental health care, it will automatically schedule an appointment with a specialist with the user's consent, allowing the user to receive appropriate support promptly.

[1425] The above is a specific embodiment of the present invention. This system allows users to easily report harassment and receive prompt support and assistance. Furthermore, the system automatically notifies the appropriate authorities and provides mental health care, allowing users to use the system with peace of mind.

[1426] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1427] Step 1:

[1428] The user initiates a dialogue with the generative AI via a device. The user registers details of the harassment using voice or text input. Examples of input include:

[1429] "I'm having trouble with verbal abuse from my boss at work."

[1430] "I'm being harassed by my classmates at school."

[1431] Input data is sent from the terminal to the server in real time.

[1432] Step 2:

[1433] The server analyzes the received user input data using a natural language processing engine. Specifically, it tokenizes the input text and analyzes its meaning. The server determines whether the input is suspected of harassment and assigns a score. This analysis uses a generative AI model.

[1434] Input: User-entered text or voice data

[1435] Output: Suspected harassment score

[1436] Step 3:

[1437] If the server determines that harassment is suspected, it will send an instruction to the device to automatically record and record. When the device receives this instruction, it will automatically collect audio and video from the surrounding area. The collected data is immediately encrypted.

[1438] Input: Server recording start instruction

[1439] Output: Encrypted audio and video data

[1440] Step 4:

[1441] The evidence data encrypted on the device is uploaded to a server, where it is analyzed and reported to the relevant departments and public institutions. Specifically, the evidence data is converted into a standardized reporting format and sent via email or a dedicated portal.

[1442] Input: Encrypted evidence data

[1443] Output: Report and transmission log

[1444] Step 5:

[1445] If the report is successful, the server sends a notification to the user. The feedback includes information about the report result and next steps. The user can also provide additional information or ask questions, and an interface is provided for this.

[1446] Input: Report result, additional information

[1447] Output: Notification and feedback to the user

[1448] Step 6:

[1449] The server determines the user's mental health needs and automatically schedules appointments with specialists if necessary. This appointment requires the user's consent, and arrangements are made only after the consent is confirmed.

[1450] Input: User consent, mental health care need data

[1451] Output: Specialist appointment information and user notification

[1452] The above are the specific processing steps for carrying out the present invention, which enable users to quickly and easily report harassment and receive appropriate support.

[1453] 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.

[1454] The system of the present invention provides a series of functions that enable users to report harassment issues and receive appropriate support. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system improves analysis accuracy and provides appropriate mental health support.

[1455] Hearing phase

[1456] 1. A user initiates a conversation with a generative AI chatbot on their device. A dedicated application is installed on the device, and the user interacts with the AI ​​using text or voice input.

[1457] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[1458] 2. The device sends the user's input, including text and voice data, to the server in real time.

[1459] Judgment Phase

[1460] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected. The emotion engine recognizes emotions from the user's input and voice data and reflects them in the analysis results.

[1461] Example: The emotion engine recognizes that a user is stressed or anxious based on their tone of voice and the way they use words.

[1462] Evidence Gathering Phase

[1463] 4. If the server determines that harassment is highly suspected based on the analysis results of the emotion engine, it sends a command to the device to start automatic recording and filming. The device receives this command and automatically starts recording and filming audio and video.

[1464] The device captures and encodes audio data to record what is happening around the user.

[1465] 5. Evidence data (audio, video) collected by the device is securely encrypted and converted into a dedicated format, reducing the risk of data leaking to third parties.

[1466] 6. The device uploads the encrypted data to the server.

[1467] Reporting Phase

[1468] 7. The server receives the uploaded evidence data and analyzes it. Audio data is converted into text using speech recognition technology, and key parts are extracted.

[1469] 8. The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[1470] 9. The server automatically sends the report to the relevant department (e.g., human resources department, general affairs department) or public institution (e.g., labor standards inspection office, police). It is sent via email or a dedicated portal.

[1471] Feedback Phase

[1472] 10. After the server reports the issue, it will send a notification to the user, providing feedback on the status update and next steps. The user can also provide additional information or ask questions.

[1473] For example: "Your report was successfully submitted. Please wait for our response."

[1474] Mental care support

[1475] 11. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic. With the user's consent, it can arrange an appointment with a specialist.

[1476] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[1477] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[1478] The processing flow will be explained below.

[1479] Step 1:

[1480] The user initiates a conversation with a generative AI chatbot on their device by writing or speaking their complaint or question.

[1481] Step 2:

[1482] The device sends the user's input, including text and voice data, to the server in real time.

[1483] Step 3:

[1484] The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine, and determines whether the dialogue is suspected of harassment and the user's emotional state.

[1485] Step 4:

[1486] If the server detects suspicion of harassment and the emotion engine detects high stress or anger, it sends instructions to the terminal to proceed to the evidence collection phase.

[1487] Step 5:

[1488] The device receives instructions from the server and automatically starts recording and capturing images. When instructed to record or capture images, the device captures audio and video data around the user.

[1489] Step 6:

[1490] The device encrypts the evidence data (audio, video) collected, converts it into a secure format, and uploads it to the server.

[1491] Step 7:

[1492] The server receives the uploaded evidence data, converts the audio data into text using voice recognition technology, and extracts and analyzes the important parts.

[1493] Step 8:

[1494] The server generates a standardized report based on the analysis results, which includes a summary of the problem, links to collected evidence, and the analysis results.

[1495] Step 9:

[1496] The server automatically sends the report to the relevant department or public institution via email or a dedicated portal.

[1497] Step 10:

[1498] The server then provides the user with a status update and feedback on next steps. The user receives a notification from the application.

[1499] Step 11:

[1500] If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental health clinic to provide appropriate mental health care support. With the user's consent, it will arrange an appointment with a specialist.

[1501] Step 12:

[1502] If the user wishes to provide feedback or additional information, they can continue to interact with the generative AI through their device. The server will analyze the new information and, if necessary, perform the evidence gathering and reporting phases again.

[1503] The above is a specific embodiment of the invention, and a detailed step-by-step explanation of the overall system flow. This system allows users to easily and safely report harassment, and also allows them to receive mental health support through the emotion engine.

[1504] Example 2

[1505] 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."

[1506] Conventional anti-harassment systems make it difficult for users to receive appropriate support promptly, and the need to manually collect evidence and report incidents places an excessive burden on victims. Furthermore, support provided often does not take into account the user's mental state, resulting in insufficient mental care.

[1507] 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.

[1508] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the content of the dialogue obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording on the terminal when the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments or public institutions, and an emotion engine that recognizes the user's emotions. This enables victims to quickly and efficiently report harassment and also enables them to receive appropriate mental care that takes into account the user's mental state.

[1509] "User" refers to an individual who uses the system to report a harassment issue.

[1510] "Terminal" refers to an electronic device used by a user, such as a computer, smartphone, or tablet.

[1511] "Generative AI" refers to an artificial intelligence model that generates natural language and engages in dialogue.

[1512] "Dialogue management means" refers to a software module with the function of managing and recording dialogue between a user and a generative AI.

[1513] The "determination means" refers to a software module that has the function of analyzing the content of the dialogue obtained through the dialogue management means and determining whether there is suspicion of harassment.

[1514] "Evidence collection means" refers to a software module that has the function of automatically starting recording and filming on a device when it is determined that harassment is suspected.

[1515] "Data management means" refers to a software module that has the function of securely encrypting collected evidence data and uploading it to a server.

[1516] "Reporting means" refers to a software module that has the function of analyzing evidence data uploaded to the server and automatically reporting to relevant departments and public institutions.

[1517] "Emotion engine" refers to a software module that has the function of analyzing and recognizing a user's emotions.

[1518] The system of the present invention provides a set of features that allow users to report harassment issues and receive appropriate assistance. The system is implemented using specific hardware and software.

[1519] Basic configuration

[1520] The system consists of the following main components:

[1521] Device: An electronic device used by a user, such as a smartphone or tablet.

[1522] Server: A remote computer system for analyzing, storing, and reporting data.

[1523] Generative AI: AI systems that generate natural language and engage in dialogue.

[1524] Natural Language Processing (NLP) engine: Software that analyzes text data (e.g., spaCy, NLTK).

[1525] Emotion engine: Software that analyzes user emotions (e.g., Microsoft Azure Cognitive Services' Text Analytics API).

[1526] Processing flow

[1527] 1. The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[1528] For example, type, "Recently, my boss at work has been verbally abusing me almost every day."

[1529] 2. The device sends the user's input (text data or voice data) to the server in real time. The device sends the data using the HTTP protocol.

[1530] 3. The server analyzes the received dialogue using a natural language processing (NLP) engine and an emotion engine to determine whether it is suspected of harassment. The server uses a Python-based NLP library (e.g., spaCy or NLTK) to perform text analysis and an emotion engine to analyze emotions.

[1531] 4. If the server determines that harassment is highly suspected, it sends a command to the device to automatically start recording and filming. The server sends the command in real time using the WebSocket protocol.

[1532] 5. The device securely encrypts the collected evidence data (audio, video) and uploads it to the server. The device uses the AES encryption algorithm and transmits the data using the HTTPS protocol.

[1533] 6. The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology (e.g., Google Cloud Speech-to-Text or Amazon Transcribe), and extracts key parts.

[1534] 7. The server uses a template engine (e.g., Jinja2) to create a standardized report format based on the analysis results. This report includes a summary of the problem, links to collected evidence data, and the analysis results.

[1535] 8. The server automatically sends the report to the relevant departments or public institutions by email using the SMTP protocol or by sending the data via a dedicated portal API.

[1536] 9. After the server reports the incident, it sends a notification to the user to provide feedback on the status update and next steps. The server uses a push notification API (e.g., Firebase Cloud Messaging) to send the notification to the user's device.

[1537] 10. If the server determines that the user needs mental care using the emotion engine, it will automatically contact a mental clinic. The server will send an email or a notification to the user, and if an appointment with a specialist is made online, it will use the reservation system's API.

[1538] Example: The emotion engine determines that the user's stress level is high and that they should contact a mental health clinic.

[1539] The above is a specific example of how to implement the invention. This system allows victims to easily and safely report harassment and receive prompt support. Furthermore, the introduction of an emotion engine allows for analysis that takes into account the user's mental state and provides appropriate mental care.

[1540] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1541] Step 1:

[1542] The user installs the dedicated application on their device, launches the application, and begins a dialogue with the generative AI. The user can use text input or voice input.

[1543] Input: Text or voice input from the user.

[1544] Output: Beginning of dialogue with generative AI.

[1545] What happens: The user taps "Open app" and then types "Lately, my boss at work has been verbally abusing me almost every day," or types the same thing out loud.

[1546] Step 2:

[1547] The device sends the user's input (text data or voice data) to the server in real time.

[1548] Input: Text or voice data entered by the user.

[1549] Output: The data sent to the server.

[1550] Specific operation: The terminal sends text data and audio data to the server using the HTTP protocol.

[1551] Step 3:

[1552] The server analyzes the conversation content received using a natural language processing (NLP) engine and an emotion engine to determine whether harassment is suspected.

[1553] Input: Text or voice data sent from the device.

[1554] Output: The result of the judgment on suspected harassment.

[1555] How it works: The server performs text analysis using a Python-based NLP library (e.g., spaCy or NLTK) and analyzes emotions using the Microsoft Azure Cognitive Services Text Analytics API. The emotion engine recognizes that the user is feeling stressed or anxious based on their tone of voice and choice of words.

[1556] Step 4:

[1557] If the server determines that there is a strong suspicion of harassment, it sends instructions to the device to begin automatic recording and filming.

[1558] Input: Judgment result.

[1559] Output: Instructions to the terminal.

[1560] Specific operation: The server sends instructions to the terminal in real time using the WebSocket protocol.

[1561] Step 5:

[1562] The evidence data (audio, video) collected by the device is securely encrypted and uploaded to the server.

[1563] Input: Evidence data obtained as a result of automatic recording and photography.

[1564] Output: The encrypted data.

[1565] Specific operation: The terminal encrypts the evidence data using the AES encryption algorithm and sends it to the server using the HTTPS protocol.

[1566] Step 6:

[1567] The server analyzes the uploaded evidence data, converts the audio data into text using speech recognition technology, and extracts the important parts.

[1568] Input: Encrypted evidence data.

[1569] Output: Text data with important parts extracted.

[1570] How it works: The server uses the speech recognition APIs of Google Cloud Speech-to-Text and Amazon Transcribe to analyze the audio data and extract the key parts.

[1571] Step 7:

[1572] The server creates a standardized report format based on the analysis results.

[1573] Input: Text data with important parts extracted.

[1574] Output: Report format.

[1575] Specific behavior: The server uses a template engine (e.g., Jinja2) to generate a report that includes a summary of the problem and links to supporting data.

[1576] Step 8:

[1577] The server automatically sends the report to the relevant department or public institution.

[1578] Input: Report format.

[1579] Output: The report sent.

[1580] Specific operation: The server sends an email using the SMTP protocol or sends data via a dedicated portal API.

[1581] Step 9:

[1582] Once the server has notified the user, it will send a notification to provide feedback on the status update and next steps.

[1583] Input: Reported report.

[1584] Output: Feedback to the user.

[1585] Specific operation: The server uses a push notification API (e.g., Firebase Cloud Messaging) to send a notification to the user's device.

[1586] Step 10:

[1587] If the server determines using the emotion engine that the user needs mental care, it will automatically contact a mental clinic.

[1588] Input: Analysis results of the emotion engine.

[1589] Output: Contact mental health clinic.

[1590] Specific operation: The server sends emails and notifications to the user, and uses the reservation system's API to make an appointment with a specialist online.

[1591] (Application example 2)

[1592] 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."

[1593] Conventional harassment reporting systems are only effective when the user is in a fixed environment, making it difficult to respond when the user is in a car or on the move. In addition, they often do not provide appropriate mental health support that takes the user's emotional state into consideration, which can increase the user's mental burden. Therefore, there is a need for a system that can instantly report and record harassment even while on the move, monitor the user's emotional state, and provide appropriate mental health support.

[1594] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1595] In this invention, the server includes a dialogue management means for a user to interact with a generative AI via a terminal, a determination means for analyzing the dialogue content and the user's emotional data obtained via the dialogue management means and determining whether harassment is suspected, an evidence collection means for automatically starting audio and video recording within the autonomous vehicle if the determination means determines that harassment is suspected, a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading it to the server, a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to relevant departments and public institutions, and a mental care means for continuously monitoring the user's emotional state and providing mental care support as needed. This enables harassment to be immediately reported and recorded even while on the move, and appropriate mental care support that takes the user's emotional state into consideration.

[1596] "User" refers to an individual who uses the system to report harassment issues.

[1597] "Terminal" refers to an electronic device operated by a user, including smartphones and in-car infotainment systems.

[1598] "Generative AI" refers to an artificial intelligence system that supports dialogue with users and has the ability to perform natural language processing and emotion analysis.

[1599] "Dialogue management means" refers to the management function that allows users to interact with generative AI via a terminal.

[1600] The "determination means" refers to a function that analyzes the content of the dialogue and the user's emotional data obtained via the dialogue management means and determines whether harassment is suspected.

[1601] "Evidence collection means" refers to a function that automatically starts recording and filming within an autonomous vehicle if it is determined that harassment is suspected.

[1602] "Data management means" refers to a function that safely encrypts evidence data collected by evidence collection means and uploads it to a server.

[1603] "Means of reporting" refers to the function of analyzing evidence data uploaded to the server and automatically reporting to the relevant departments and public institutions.

[1604] "Mental care means" refers to a function that continuously monitors the user's emotional state and provides mental care support as needed.

[1605] "Emotion data" refers to data that indicates the user's emotional state and that has been analyzed by the emotion engine.

[1606] An "emotion engine" refers to a system that recognizes emotions from user input and voice data and reflects them in the analysis results.

[1607] This invention provides a system that allows users to report harassment issues in autonomous vehicles and receive appropriate support. Specific embodiments of this invention are described below. This system includes both hardware and software, and its main components are a user terminal and a server.

[1608] Program Overview

[1609] 1. How users interact with generative AI via their devices:

[1610] The user initiates a dialogue with the generative AI using the infotainment system or smartphone installed in the autonomous vehicle. A dedicated application is installed on the device, and the user interacts with the AI ​​using voice or text input.

[1611] 2. Analysis of dialogue content and emotion data:

[1612] The user's input and voice data are sent to a server in real time, where a natural language processing engine (NLP engine) and an emotion engine analyze the data and determine whether it is suspected harassment. The emotion engine recognizes the user's emotional state and feeds that data back to the AI ​​model.

[1613] 3. Collecting evidence:

[1614] If the server determines that harassment is highly suspected, it automatically sends instructions to the device to start recording and filming. The device collects evidence data using the in-car camera and microphone, encrypts it, and then uploads the encrypted data to the server.

[1615] 4. Data Management and Analysis:

[1616] The server analyzes the uploaded evidence data and uses natural language processing technology to extract key information, which is then converted into a standardized reporting format and automatically sent to the relevant departments and public institutions.

[1617] 5. Mental health support:

[1618] The server determines whether the user needs mental care based on the results of the emotion engine. If necessary, it introduces the user to a specialized institution that provides mental care support and arranges for a reservation.

[1619] The specific hardware and software used

[1620] Hardware:

[1621] Smartphone

[1622] Autonomous vehicle infotainment systems

[1623] In-car camera and microphone

[1624] software:

[1625] SpeechRecognition library: Used to convert voice input to text.

[1626] EmotionRecognition library: Used to analyze the user's emotional state.

[1627] VideoCapture library: Provides audio and video recording functions.

[1628] CloudStorage module: Encrypts and uploads evidence data to the cloud.

[1629] ReportGenerator module: Provides automatic report generation functionality.

[1630] Notifications module: Notifies the user.

[1631] Mental Care module: Contact and schedule mental health support.

[1632] Specific examples

[1633] For example, if a user shouts "harassment" inside an autonomous vehicle, the system immediately performs sentiment analysis and automatically starts recording. The collected evidence data is encrypted and securely uploaded to the cloud. The server then analyzes the collected data, generates a standardized report, and automatically sends it to the designated department. For example, if a user says, "My boss is verbally abusing me at work," the system will detect harassment and begin responding.

[1634] Example prompt sentence:

[1635] "I would like to report harassment at my workplace. Please start recording and collecting evidence."

[1636] "Now, record any problematic conversations you hear while riding alone."

[1637] The above is a specific embodiment of the present invention. This system allows users to easily and safely report harassment even while on the move, enabling a prompt response. Furthermore, the introduction of an emotion engine provides analysis that takes into account the user's mental state and provides appropriate mental care support.

[1638] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1639] Step 1:

[1640] The user initiates a dialogue with the generative AI via a device. The user inputs voice or text, which the device sends to the server in real time. Input: Voice data or text data. Output: Data sent to the server.

[1641] Step 2:

[1642] The server analyzes the received voice or text data using a natural language processing engine (NLP engine) to understand what the user is saying. The server then analyzes the voice data using an emotion engine to recognize the user's emotions. Input: Data sent to the server. Output: Analysis results (text content and emotion data).

[1643] Step 3:

[1644] Based on the analysis results, the server determines whether there is any suspicion of harassment. The server analyzes the content of the user's remarks and emotional state, and if it determines that there is suspicion of harassment, it sends instructions to the device to automatically record and film. Input: Analysis results. Output: Instruction to start recording and filming.

[1645] Step 4:

[1646] The terminal receives instructions from the server and starts recording and capturing images using the camera and microphone inside the autonomous vehicle. Evidence data is collected and encrypted. Input: Instruction to start recording and capturing images. Output: Encrypted evidence data.

[1647] Step 5:

[1648] The terminal uploads the encrypted evidence data to the server. Input: Encrypted evidence data. Output: Data uploaded to the server.

[1649] Step 6:

[1650] The server analyzes the uploaded evidence data and extracts important information. It then converts the extracted information into a standardized report format and automatically notifies the relevant departments and public institutions. Input: Uploaded evidence data. Output: Report generation and notification.

[1651] Step 7:

[1652] The server determines whether the user needs mental care based on the results of the emotion engine. If it determines that mental care is necessary, it introduces the user to a specialized institution for mental care support and arranges an appointment. Input: Analysis results of the emotion engine. Output: Provision of mental care support.

[1653] The above are the specific processing steps in the system for realizing the present invention. The specific operations performed in each step, as well as the inputs and outputs, have also been explained.

[1654] 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.

[1655] 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.

[1656] 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.

[1657] 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.

[1658] 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.

[1659] 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.

[1660] 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).

[1661] 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.

[1662] 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."

[1663] 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.

[1664] 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).

[1665] 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.

[1666] 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.

[1667] 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.

[1668] 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.

[1669] 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.

[1670] 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.

[1671] 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.

[1672] 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.

[1673] 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.

[1674] 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.

[1675] The following is further disclosed regarding the above embodiment.

[1676] (Claim 1)

[1677] A dialogue management means for a user to dialogue with the generative AI via a terminal;

[1678] a determination means for analyzing the content of the dialogue obtained through the dialogue management means and determining whether or not there is suspicion of harassment;

[1679] an evidence collection means that automatically starts recording and photographing on the terminal when the judgment means judges that harassment is suspected;

[1680] a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading the encrypted data to a server;

[1681] a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to the relevant department or public institution;

[1682] A system including:

[1683] (Claim 2)

[1684] 2. The system according to claim 1, wherein said dialogue management means further comprises means for analyzing user input contents with a natural language processing engine.

[1685] (Claim 3)

[1686] 2. The system according to claim 1, wherein the reporting means further comprises means for converting the collected evidence data into a standardized report format and transmitting the data via email or a dedicated portal.

[1687] "Example 1"

[1688] (Claim 1)

[1689] A dialogue management means for a user to dialogue with the generative AI via a terminal;

[1690] a determination means for analyzing the content of the dialogue obtained through the dialogue management means and determining whether or not there is suspicion of harassment;

[1691] an evidence collection means that automatically starts recording and photographing on the terminal when the judgment means judges that harassment is suspected;

[1692] a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading the encrypted data to a server;

[1693] a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to the relevant department or public institution;

[1694] a feedback means for sending a notification to the user and providing feedback after the report;

[1695] A support method to determine the need for mental care and contact a medical institution when necessary, and

[1696] A system including:

[1697] (Claim 2)

[1698] 2. The system according to claim 1, wherein said dialogue management means further comprises means for analyzing user input contents with a natural language processing engine.

[1699] (Claim 3)

[1700] 2. The system according to claim 1, wherein the reporting means further comprises means for converting the collected evidence data into a standardized report format and transmitting the data via email or a dedicated portal.

[1701] "Application Example 1"

[1702] (Claim 1)

[1703] A dialogue management means for a user to dialogue with the generative AI via a terminal;

[1704] a determination means for analyzing the content of the dialogue obtained through the dialogue management means and determining whether or not there is suspicion of harassment;

[1705] an evidence collection means that automatically starts recording and photographing on the terminal when the judgment means judges that harassment is suspected;

[1706] a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading the encrypted data to a server;

[1707] a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to the relevant department or public institution;

[1708] A hearing means in which a user inputs voice or text into a predetermined input means, and the generative AI transmits the dialogue content to a server in real time;

[1709] A system including:

[1710] (Claim 2)

[1711] 2. The system according to claim 1, wherein said dialogue management means further comprises means for analyzing user input contents with a natural language processing engine.

[1712] (Claim 3)

[1713] 2. The system according to claim 1, wherein the reporting means further comprises means for converting the collected evidence data into a standardized report format and transmitting the data via email or a dedicated portal.

[1714] "Example 2: Combining Emotion Engines"

[1715] (Claim 1)

[1716] A dialogue management means for a user to dialogue with the generative AI via a terminal;

[1717] a determination means for analyzing the content of the dialogue obtained through the dialogue management means and determining whether or not there is suspicion of harassment;

[1718] an evidence collection means that automatically starts recording and photographing on the terminal when the judgment means judges that harassment is suspected;

[1719] a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading the encrypted data to a server;

[1720] a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to the relevant department or public institution;

[1721] A system including an emotion engine that recognizes user emotions.

[1722] (Claim 2)

[1723] 2. The system according to claim 1, wherein said dialogue management means further comprises means for analyzing user input contents using a natural language processing engine and an emotion engine.

[1724] (Claim 3)

[1725] The system of claim 1, wherein the reporting means further comprises means for converting the collected evidence data into a standardized reporting format and transmitting it to relevant departments or public institutions via email or a dedicated portal.

[1726] "Application example 2 when combining emotion engines"

[1727] (Claim 1)

[1728] A dialogue management means for a user to dialogue with the generative AI via a terminal;

[1729] a determination means for analyzing the content of the dialogue and the user's emotional data obtained through the dialogue management means and determining whether harassment is suspected;

[1730] an evidence collection means that automatically starts recording and photographing inside the autonomous vehicle when the determination means determines that harassment is suspected;

[1731] a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading the encrypted data to a server;

[1732] a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to the relevant department or public institution;

[1733] A mental care means for continuously monitoring the user's emotional state and providing mental care support as needed;

[1734] A system including:

[1735] (Claim 2)

[1736] 2. The system according to claim 1, wherein said dialogue management means further comprises means for analyzing user input contents with a natural language processing engine.

[1737] (Claim 3)

[1738] 2. The system according to claim 1, wherein the reporting means further comprises means for converting the collected evidence data into a standardized report format and transmitting the data via email or a dedicated portal. [Explanation of symbols]

[1739] 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 dialogue management means for a user to dialogue with the generative AI via a terminal; a determination means for analyzing the content of the dialogue obtained through the dialogue management means and determining whether or not there is suspicion of harassment; an evidence collection means that automatically starts recording and photographing on the terminal when the determination means determines that harassment is suspected; a data management means for securely encrypting the evidence data collected by the evidence collection means and uploading the encrypted data to a server; a reporting means for analyzing the evidence data uploaded to the server and automatically reporting it to the relevant department or public institution; A system including:

2. 2. The system according to claim 1, wherein said dialogue management means further comprises means for analyzing the contents of a user's input with a natural language processing engine.

3. 2. The system according to claim 1, wherein the reporting means further comprises means for converting the collected evidence data into a standardized report format and transmitting the data via email or a dedicated portal.

Images