System

Abstract

To provide a system.SOLUTION: A system includes: means for collecting data about harassment from each department in a company; means for preprocessing the collected data, inputting the preprocessed data into a generative AI, and analyzing a trend of harassment; means for using the generative AI to analyze a relationship between feeling information of an employee analyzed using a feeling engine and occurrence of harassment; means for proposing measures and preventive measures against harassment on the basis of an analysis result of the generative AI and an analysis result of the feeling engine.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] The classification and filtering of inquiries and reports related to harassment within the company is done manually, resulting in delayed responses and increased risks. There is also a lack of effective means to identify trends and patterns of harassment and propose countermeasures and preventive measures. [Means for solving the problem]

[0005] By using generative AI to automatically classify inquiries and reports related to harassment within the company and filter them according to importance and urgency, it is possible to respond quickly and provide a means to hedge risks.Furthermore, by utilizing generative AI to identify trends and patterns of harassment, and by visualizing the data and generating reports, it provides a means to propose measures and preventive measures against harassment. [Brief description of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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. 2 is a sequence diagram showing a process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16] FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. [Figure 19] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system according to the embodiment 2 of the second embodiment in the case where an emotion engine is combined. [Figure 20] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when combined with an emotion engine. [Figure 21] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in the embodiment 3 of the form example 3 in the case where an emotion engine is combined. [Figure 22] FIG. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0007] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] In the following embodiments, a signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the processor.

[0011] 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.

[0012] In the following embodiments, a communication I / F (Interface) with a code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "and / or."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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 wide area network (WAN) and / or a local area network (LAN).

[0018] 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.

[0019] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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.

[0020] 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

[0022] FIG. 2 shows an example of main functions of the data processing device 12 and the smart device 14.

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process program 56 executed on the RAM 30.

[0024] 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.

[0025] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One embodiment of the present invention is a system that uses generative AI to automatically classify inquiries and reports related to harassment in the workplace. Specifically, generative AI analyzes text data collected through anonymous reporting channels using chatbots, and automatically classifies content related to harassment. Furthermore, the results can be filtered according to importance and urgency, allowing for rapid response.

[0029] "Example 2"

[0030] Another embodiment of the present invention is a system that uses generative AI to identify trends and patterns of harassment, visualize the data, and generate reports. Specifically, based on the results of the generative AI analysis, the system extracts trends and patterns of harassment and visualizes them. Based on the results, the system automatically generates reports and suggests measures and preventative measures against harassment.

[0031] "Example 3"

[0032] As a further embodiment of the present invention, there is a system that utilizes generative AI to propose measures and preventive measures against harassment. Specifically, the system proposes measures and preventive measures against harassment based on the results of analysis by generative AI. For example, it identifies departments, time periods, and types of harassment where harassment occurs frequently, and proposes specific measures and preventive measures against them.

[0033] The process flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: Collect text data from an anonymous reporting channel using a chatbot.

[0036] Step 2: Input the collected text data into a generative AI system to automatically classify harassment-related content.

[0037] Step 3: Filter the results of the generative AI's classification according to importance and urgency, and take necessary action quickly.

[0038] "Example 2"

[0039] Step 1: Based on the results of the generative AI analysis, extract trends and patterns of harassment.

[0040] Step 2: Visualize the extracted trends and patterns.

[0041] Step 3: Automatically generate a report based on the visualized results and suggest measures to combat and prevent harassment.

[0042] "Example 3"

[0043] Step 1: Based on the results of the generative AI's analysis, propose countermeasures and preventive measures against harassment.

[0044] Step 2: Identify the departments, times of day, and types of harassment where harassment is most frequent.

[0045] Step 3: Propose specific countermeasures and preventive measures for the identified information.

[0046] Example 1

[0047] Next, a description will be given of Example 1 of the embodiment 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".

[0048] There is a need to efficiently classify inquiries and reports related to harassment within the company and respond quickly according to their importance and urgency. However, traditional manual responses run the risk of delaying the processing of reports or overlooking important reports. It is also difficult to identify trends and patterns of harassment and propose countermeasures and preventive measures. To solve these issues, automatic classification and filtering of reports, rapid response, data visualization and report generation, and proposal of countermeasures and preventive measures are required.

[0049] 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.

[0050] In this invention, the server includes a means for collecting anonymous reports using a chatbot, a means for transmitting collected text data to the server, a means for analyzing the text data using a generative AI model and automatically classifying content related to harassment, a means for filtering the classification results according to importance and urgency, a means for notifying the person in charge of the filtered results, a means for enabling a rapid response and leading to risk hedging, a means for identifying trends and patterns of harassment using generative AI, a means for visualizing data and generating reports, and a means for proposing measures and preventative measures against harassment. This makes it possible to efficiently classify inquiries and reports related to harassment within the company and to respond quickly according to importance and urgency.

[0051] A "chatbot" is software that automates dialogue with users and has the ability to collect and respond to information through text and voice.

[0052] An "anonymous report" is a report made without revealing the reporter's identity, providing a means of providing information while protecting privacy.

[0053] "Text data" is information expressed as a character string, and includes the contents of reports and inquiries.

[0054] A "server" is a computer system that processes and stores data on a network, and provides services in response to requests from clients.

[0055] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to analyze data and automatically perform specific tasks.

[0056] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[0057] Classification is the process of separating data into specific categories or groups, grouping data that share common characteristics.

[0058] "Filtering" is the process of sorting through data based on specific criteria to extract only the information you need.

[0059] A "notification" is a means of informing relevant parties of specific information, and is done via email, dashboard, etc.

[0060] "Rapid response" refers to dealing with a problem quickly when it occurs, and is an action taken to minimize risk.

[0061] "Risk hedging" is the process of predicting potential risks and taking measures to reduce the impact of those risks.

[0062] A "trend" refers to a general movement or pattern of data or events moving in a particular direction.

[0063] A "pattern" refers to a repeating structure or arrangement in data or events.

[0064] "Visualization" is the process of making information easier to understand intuitively by representing data visually.

[0065] A "report" is a document that compiles information on a particular topic and includes analytical findings and recommendations.

[0066] A "measure" refers to a specific action or plan to address a particular problem.

[0067] "Preventive measures" refer to measures or actions taken to prevent problems before they occur.

[0068] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0069] This invention is a system that uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is described below.

[0070] Hardware and Software Used

[0071] The system uses the following hardware and software:

[0072] Server: A computer system that processes and stores data, and also serves as the execution environment for generative AI models.

[0073] Device: The device used by the user (PC, smartphone, tablet, etc.).

[0074] Chatbot: Software that automates dialogue with users. It runs on communication tools such as Slack and MICROSOFT(registered trademark) TEAMS(registered trademark).

[0075] Generative AI model: An algorithm for analyzing text data and automatically performing specific tasks, such as GPT-4 by OpenAI.

[0076] Data processing and calculation

[0077] This system performs the following data processing and calculations.

[0078] 1. Collect reports: Users anonymously report harassment through the chatbot. For example, a user may report, “My boss yells at me every day.”

[0079] 2. Data transmission: The terminal transmits the text data collected through the chatbot to the server, which temporarily stores the received text data.

[0080] 3. Text Analysis and Classification: The server inputs the stored text data into the generative AI model, which analyzes the text data using the following prompt sentence:

[0081] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[0082] The generative AI model analyzes text data and classifies it as "power harassment."

[0083] 4. Filtering of classification results: The server evaluates the importance and urgency of reports based on the classification results obtained from the generative AI model. For example, reports classified as "power harassment" are deemed to be of high importance. The server filters reports taking into account their content, frequency, and the strength of the words used.

[0084] 5. Notify the person in charge: The server notifies the person in charge based on the filtered results. The notification is done, for example, via email or a dedicated management dashboard. The person in charge can receive the notification and take the necessary action promptly.

[0085] Examples

[0086] As a concrete example, consider the following scenario.

[0087] scenario:

[0088] A user anonymously reports to a chatbot on Slack, "My boss yells at me every day." This report is sent to a server and analyzed by a generative AI model.

[0089] Example prompt:

[0090] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[0091] The generative AI model receives this prompt and classifies the report as "power harassment." The server then determines the importance of the report as "high" based on this classification and notifies the person in charge by email.

[0092] The above is a specific embodiment for carrying out the present invention.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1:

[0095] A user anonymously reports harassment through the chatbot. For example, a user reports, "My boss yells at me every day." This report becomes input data. The chatbot receives this text data and saves the report.

[0096] Step 2:

[0097] The terminal transmits the text data collected through the chatbot to the server. The input data is the text data reported by the user. The server temporarily stores the received text data. Specifically, it stores it in a database.

[0098] Step 3:

[0099] The server inputs the stored text data into the generative AI model. The input data is the stored text data. The generative AI model parses the text data using the following prompt sentence:

[0100] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[0101] The generative AI model analyzes the text data and classifies it as "power harassment." The output data is the classification result.

[0102] Step 4:

[0103] The server evaluates the importance and urgency of reports based on the classification results obtained from the generative AI model. The input data is the classification results from the generative AI model. The server filters the reports taking into account their content, frequency, and the strength of the words used. The output data is the filtered results.

[0104] Step 5:

[0105] The server notifies the person in charge based on the filtered results. The input data is the filtered results. The notification is sent, for example, via email or a dedicated management dashboard. The output data is the notification content. The person in charge can receive the notification and take the necessary action promptly.

[0106] The above is the specific flow of the program processing of this system.

[0107] (Application example 1)

[0108] Next, a description will be given of Application Example 1 of Form 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."

[0109] In conventional harassment reporting systems, classification of reports and judgment of their importance were often done manually, making it difficult to respond quickly. In addition, there was a lack of a mechanism to properly filter important reports and notify the person in charge immediately while ensuring anonymity. This created a risk of delaying the early detection and countermeasures of harassment.

[0110] 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.

[0111] In this invention, the server includes a means for automatically classifying inquiries and reports related to workplace harassment using generative AI and filtering them according to importance and urgency, a means for analyzing text data collected through anonymous reporting channels, and a means for immediately notifying the person in charge when an important report is received. This enables a quick response and leads to risk hedging.

[0112] "Generative AI" is an artificial intelligence technology that generates new data and information based on input information such as text data and image data.

[0113] "Workplace harassment" refers to inappropriate behavior such as harassment, bullying, and discrimination that occurs in the workplace.

[0114] An "inquiry or report" refers to an employee communicating an issue or question about harassment to the company.

[0115] "Automatic classification" refers to the process in which generative AI analyzes input data and automatically classifies it based on specific categories or importance.

[0116] "Filtering based on importance and urgency" refers to the process of selecting data classified by generative AI based on its importance and urgency.

[0117] "Anonymous reporting channel" means a means of communication through which a report of harassment may be made without revealing the reporter's identity.

[0118] "Text data" refers to data expressed as character information.

[0119] "Analyze" refers to the process in which generative AI examines the input data in detail to understand and classify its contents.

[0120] "Immediate notification to responsible parties" refers to the process of immediately notifying designated responsible parties when important reports are received.

[0121] "Prompt response" refers to taking appropriate measures without delay when a problem occurs.

[0122] "Risk hedging" refers to minimizing risks by detecting potential risks in advance and taking measures to address them.

[0123] The system for implementing this invention uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is described below.

[0124] System Configuration

[0125] The system consists of the following main components:

[0126] 1. Server: Runs the generative AI model to analyze and classify text data.

[0127] 2. Device: The device (e.g., smartphone) through which a user reports harassment via the anonymous reporting channel.

[0128] 3. Notification system: Immediately notify the responsible person when there is an important report.

[0129] Hardware and software used

[0130] Hardware: Smartphones, servers

[0131] Software: Python, OpenAI API

[0132] Data processing and calculation

[0133] 1. Text data collection

[0134] Users can use their smartphones to access the anonymous reporting channel and report on harassment. The report content is sent to the server as text data.

[0135] 2. Generative AI analysis

[0136] The server analyzes the collected text data using the OpenAI API, and inputs the text data into the generative AI model using the following prompt:

[0137] Example prompt:

[0138] Analyze the text below and classify the content as harassment related.

[0139] Text: My boss keeps harassing me. Please help.

[0140] Classification results:

[0141] The generative AI model analyzes the text data based on this prompt and classifies the content as harassment-related.

[0142] 3. Filtering and Notifications

[0143] The server determines the importance and urgency of the report based on the analysis results obtained from the generative AI model. If an important report is received, the person in charge is notified immediately via the notification system.

[0144] Examples

[0145] For example, if a user reports, "My boss continues to harass me. Please help me," the server inputs this text data into a generative AI model, and obtains the classification result as "This report is important. My boss continues to harass me, so urgent action is required." Based on this result, the server immediately notifies the person in charge, enabling a prompt response.

[0146] In this way, a harassment reporting system using generative AI can enable quick and appropriate responses, helping to hedge risks.

[0147] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0148] Step 1:

[0149] A user accesses the anonymous reporting channel using a smartphone to report harassment. The input is text data entered by the user. The output is text data sent to the server.

[0150] Step 2:

[0151] The server inputs the received text data into the generative AI model. Specifically, it analyzes the text data using the following prompt sentence. The input is the text data sent by the user. The output is the analysis result by the generative AI model.

[0152] Example prompt:

[0153] Analyze the text below and classify the content as harassment related.

[0154] Text: My boss keeps harassing me. Please help.

[0155] Classification results:

[0156] Step 3:

[0157] The server judges the importance and urgency of the report content based on the analysis results obtained from the generative AI model. The input is the analysis results of the generative AI model. The output is the filtering results according to the importance and urgency.

[0158] Step 4:

[0159] The server immediately notifies the person in charge through the notification system when there is an important report based on the filtering result. The input is the filtering result. The output is the notification to the person in charge.

[0160] Step 5:

[0161] The person in charge receives the notification and takes prompt action. The input is the notification from the server. The output is the implementation of the action.

[0162] In this way, a harassment reporting system using generative AI can enable quick and appropriate responses, helping to hedge risks.

[0163] Example 2

[0164] Next, a second embodiment of the second embodiment will be described. 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."

[0165] With conventional harassment prevention systems, it was difficult to efficiently classify inquiries and reports related to harassment within the company and quickly respond to them according to their importance and urgency. It was also difficult to identify trends and patterns of harassment and propose countermeasures and preventative measures based on them. This led to problems such as the inability to properly manage the risk of harassment and delays in improving the working environment within the company.

[0166] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for collecting data from a database, a means for preprocessing the collected data, a means for analyzing data using a generative AI model and identifying trends and patterns of harassment, a means for visualizing the analysis results, and a means for automatically generating a report based on the visualized data. This makes it possible to efficiently identify trends and patterns of harassment, and to propose rapid responses and appropriate countermeasures and preventive measures.

[0167] "Generative AI" is a system that uses artificial intelligence technology to generate, analyze, and classify data.

[0168] A "database" is a system for efficiently storing, managing, and searching data.

[0169] "Preprocessing" refers to the initial process of preparing data for analysis, and specifically includes data cleaning and tokenization.

[0170] A "generative AI model" is a part of generative AI, an algorithm that analyzes data and generates results based on specific prompts.

[0171] A "prompt sentence" is an input sentence that gives specific instructions or questions to a generative AI model.

[0172] "Visualization" refers to the display of data analysis results in a visual format such as a graph or chart.

[0173] A "report" is a written summary of data analysis results and recommendations.

[0174] "Harassment" refers to inappropriate behavior or remarks towards others in the workplace or any other environment.

[0175] "Inquiry" means a question or request made for specific information or assistance.

[0176] A "report" is a written or oral communication providing information about a particular event or situation.

[0177] "Classification" means grouping data based on specific criteria.

[0178] "Filtering" means selecting data based on specific conditions.

[0179] A "trend" refers to a recurring pattern or trend in data.

[0180] A "pattern" is a collection of elements in data that have a certain regularity or commonality.

[0181] A "measure" is a specific action or plan to address a particular problem.

[0182] A "prevention" is a specific action or plan to prevent a problem before it occurs.

[0183] This invention is a system that uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to importance and urgency. It also collects data from a database, pre-processes it, and uses a generative AI model to analyze the data and identify trends and patterns of harassment. It visualizes the analysis results and automatically generates reports to suggest countermeasures and preventive measures against harassment.

[0184] Hardware and Software Used

[0185] Hardware:

[0186] Server: Database server (e.g. MySQL (registered trademark))

[0187] Terminal: A computer used to view data and review reports.

[0188] software:

[0189] Database Management System: MySQL

[0190] Natural Language Processing Libraries: NLTK, spaCy

[0191] Generative AI model: GPT-4

[0192] Data visualization tools: Tableau, Matplotlib

[0193] Report generation tools: LaTeX, Microsoft Word

[0194] Explanation of program processing

[0195] Data collection:

[0196] The server collects data such as chat logs, emails, and survey results within the company. Specifically, it connects to a database server and obtains the required data with a query. For example, execute the query "SELECT FROM chat_logs WHERE date BETWEEN (registered trademark) '2023-01-01' AND '2023-01-31'" to obtain chat logs for January.

[0197] Data preprocessing:

[0198] The server preprocesses the collected data. Specifically, it cleans the text data (removes unnecessary characters and spaces) and tokenizes it (splits it into words and phrases). The preprocessed data is temporarily stored on the terminal. For example, the cleaned text data is saved as a CSV file.

[0199] Analysis by generative AI models:

[0200] The server inputs the preprocessed data into a generative AI model (GPT-4) to analyze harassment trends and patterns. The prompt text to be input into the generative AI model is created by the user. For example, the prompt text "Please identify the harassment trends from the following chat logs" is used.

[0201] Data Visualization:

[0202] The server visualizes harassment trends and patterns based on the results of the generative AI model's analysis. Specifically, it uses Matplotlib to create graphs and display bar graphs showing the time periods when certain keywords frequently appear. The visualized data is then displayed on the terminal.

[0203] Generate report:

[0204] The server automatically generates a "January Harassment Trend Report" using LaTeX based on the visualized data and saves it in PDF format. Users can check the generated report and make corrections or additional comments as necessary.

[0205] Examples of concrete examples and prompts

[0206] Examples:

[0207] Identify the times and departments in which specific keywords (e.g. "harassment" or "ignoring") appear frequently from company chat logs.

[0208] From the survey results, the names of departments and superiors with the most reports of harassment will be extracted.

[0209] Example prompt:

[0210] Please identify harassment trends from the chat logs below. In particular, please extract frequently occurring keywords and the time periods in which they occurred.

[0211] "Based on the results of this survey, please identify departments with a high number of harassment reports and analyze the causes."

[0212] The above is an embodiment of the present invention.

[0213] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0214] Step 1: Data collection

[0215] The server collects data such as chat logs, emails, and survey results within the company. Specifically, it connects to a database server and retrieves the required data with a query. For example, execute the query "SELECT FROM chat_logs WHERE date BETWEEN '2023-01-01' AND '2023-01-31'" to retrieve chat logs for January. The input is the database query, and the output is the collected raw data.

[0216] Step 2: Data Preprocessing

[0217] The server preprocesses the collected data. Specifically, it cleans the text data (removes unnecessary characters and spaces) and tokenizes it (splits it into words and phrases). The preprocessed data is temporarily stored on the terminal. For example, the cleaned text data is saved as a CSV file. The input is the collected raw data, and the output is the preprocessed clean data.

[0218] Step 3: Analysis by generative AI model

[0219] The server inputs the preprocessed data into a generative AI model (GPT-4) to analyze harassment trends and patterns. The user creates a prompt to input to the generative AI model. For example, the prompt could be, "Please identify the harassment trends from the chat logs below." The input is the preprocessed data and the prompt, and the output is the analysis results by the generative AI model.

[0220] Step 4: Visualize the data

[0221] The server visualizes harassment trends and patterns based on the results of the generative AI model's analysis. Specifically, it uses Matplotlib to create graphs, and displays time periods when specific keywords frequently appear as bar graphs. The visualized data is displayed on the terminal. The input is the analysis results from the generative AI model, and the output is the visualized graph or chart.

[0222] Step 5: Generate reports

[0223] The server automatically generates a "January Harassment Trend Report" using LaTeX based on the visualized data and saves it in PDF format. The user checks the generated report and makes corrections or additional comments as necessary. The input is the visualized data, and the output is the automatically generated report.

[0224] (Application example 2)

[0225] Next, a description will be given of Application Example 2 of Form 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."

[0226] Conventional harassment prevention systems make it difficult to efficiently classify inquiries and reports related to harassment within the company and respond quickly according to their importance and urgency. It is also time-consuming to identify trends and patterns of harassment, visualize them, and generate reports. Furthermore, there is a lack of functionality to suggest specific countermeasures and preventive measures, which makes it difficult to take effective measures against harassment.

[0227] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for identifying trends and patterns of harassment using generative AI, a means for visualizing data and generating reports, a means for proposing measures and preventive measures against harassment, a means for collecting text data such as reports, chat logs, and emails from users through an application installed on a smartphone, a means for identifying trends and patterns of harassment from the collected data using a generative AI model, a means for visualizing the analysis results in graphs and charts, and a means for automatically generating a report based on the analysis results and proposing specific measures and preventive measures. This makes it possible to efficiently classify inquiries and reports related to harassment and to quickly respond to them, and to identify and visualize trends and patterns of harassment and propose specific measures and preventive measures.

[0228] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[0229] "Harassment" refers to inappropriate language or behavior toward others in the workplace or any other environment.

[0230] "Inquiry" means a question or request for specific information or assistance.

[0231] "Reporting" refers to the act of providing information about a particular event or situation.

[0232] "Classification" refers to the grouping of data or information based on specific criteria.

[0233] "Filtering" refers to selecting data or information based on specific conditions.

[0234] A "trend" refers to a movement or flow toward a particular direction or pattern.

[0235] A "pattern" refers to a particular repeated form or arrangement.

[0236] "Visualization" refers to the visual representation of data or information.

[0237] "Report" means a document that compiles specific information or analytical results.

[0238] A "measure" refers to a specific action or measure to address a particular problem or issue.

[0239] "Preventive measures" refer to specific actions or steps taken to head off problems or issues before they occur.

[0240] A "smartphone" refers to a type of mobile phone that can connect to the Internet and use applications.

[0241] "Application" refers to a software program designed to provide a specific function or service.

[0242] "Chat log" refers to a record of conversations held in chat format.

[0243] "Email" refers to messages sent and received electronically.

[0244] "Data collection" refers to the act of gathering data for a specific purpose.

[0245] A "graph" refers to a diagram for visually representing data.

[0246] A "chart" refers to a table or diagram that visually represents data.

[0247] The system for implementing this invention uses generative AI to automatically classify inquiries and reports related to harassment in the workplace and filter them according to importance and urgency. It also uses generative AI to identify trends and patterns of harassment, visualize the data, and generate reports. It also has the ability to suggest countermeasures and preventative measures against harassment.

[0248] Hardware and Software Used

[0249] Hardware: Smartphones, servers

[0250] Software: Python, OpenAI API, Matplotlib, Pandas

[0251] Data processing and calculation

[0252] Data collection

[0253] Users input text data such as reports of harassment, chat logs, and emails through an application installed on their smartphones. This data is sent to a server and stored in a database.

[0254] AI analysis

[0255] The server inputs the collected data into a generative AI model (e.g., GPT-3 (registered trademark)) to identify trends and patterns of harassment. In this case, it uses prompt sentences such as the following:

[0256] Examples of prompt statements

[0257] Identify trends and patterns of harassment in the text data below.

[0258] Text: My boss is nasty to me every day

[0259] Text: Colleagues ignoring me

[0260] Data Visualization

[0261] Based on the analysis results obtained from the generative AI model, the server uses Pandas and Matplotlib to visualize the data in graphs and charts, allowing users to visually confirm trends and patterns of harassment.

[0262] Report Generation

[0263] The server automatically generates a report based on the analysis results, which includes trends and patterns of harassment, as well as specific countermeasures and preventative measures, and outputs the report as a text file that users can download.

[0264] Examples

[0265] For example, if a user reports that "my boss is nasty every day," the generative AI model will identify the pattern of "nasty." Based on this information, the server will generate a graph showing that there are many reports of nasty behavior and suggest measures such as "regular counseling" in the report.

[0266] In this way, the invention is able to efficiently categorize and rapidly respond to harassment-related inquiries and reports, identify and visualize harassment trends and patterns, and suggest specific countermeasures and preventative measures.

[0267] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0268] Step 1:

[0269] Users input text data such as reports of harassment, chat logs, and emails through an application installed on their smartphones. The input data is then sent to a server by the application. The input data includes the specific details of the harassment, as well as the date and time.

[0270] Step 2:

[0271] The server saves the received text data in a database. At this time, it checks the format and content of the data and converts it into an appropriate format. For example, it converts the text data into JSON format and saves it.

[0272] Step 3:

[0273] The server inputs the stored text data into a generative AI model. The generative AI model (e.g., GPT-3) analyzes the data based on the prompt text and identifies harassment trends and patterns. Examples of prompt text are as follows:

[0274] Examples of prompt statements

[0275] Identify trends and patterns of harassment in the text data below.

[0276] Text: My boss is nasty to me every day

[0277] Text: Colleagues ignoring me

[0278] Step 4:

[0279] The server receives the analysis results from the generative AI model and stores them in a database, including any identified harassment trends or patterns.

[0280] Step 5:

[0281] The server visualizes the data based on the analysis results. It uses Pandas and Matplotlib to represent the analysis results in graphs and charts. For example, it generates a bar graph showing the high number of reports of sarcasm.

[0282] Step 6:

[0283] The server automatically generates reports based on the visualized data. The reports include trends and patterns of harassment, as well as specific countermeasures and preventative measures. The generated reports are output as text files.

[0284] Step 7:

[0285] Users can download and view the generated report through a smartphone application, which includes specific measures such as "regular counseling."

[0286] In this way, the system will be able to efficiently categorize and quickly respond to harassment-related inquiries and reports, identify and visualize harassment trends and patterns, and suggest specific countermeasures and preventive measures.

[0287] Example 3

[0288] Next, a third embodiment of the third embodiment will be described. 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."

[0289] In conventional harassment prevention systems, classification of harassment reports and inquiries, filtering of importance and urgency, and proposal of specific countermeasures and preventive measures are often done manually, making it difficult to respond quickly.In addition, there was a lack of means to identify trends and patterns of harassment and visualize the data, making it difficult to take effective measures.

[0290] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0291] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment within the company using generative AI and filtering them according to importance and urgency, a means for collecting data on harassment from each department within the company, a means for preprocessing the collected data and completing missing values ​​and correcting abnormal values, a means for inputting the preprocessed data into a generative AI model and identifying departments, time periods, and types of harassment with high frequency, a means for proposing specific countermeasures and preventive measures based on the analysis results of the generative AI model, and a means for notifying the user of the proposed contents. This enables rapid classification and filtering of harassment reports and inquiries, and allows for the proposal of effective countermeasures and preventive measures.

[0292] "Generative AI" is an artificial intelligence technology that generates new information and suggestions based on data.

[0293] "Harassment" refers to inappropriate verbal or physical actions taken against others in the workplace or in society, and is an act that causes mental or physical pain.

[0294] "Inquiry" means a question or inquiry made to request specific information or advice.

[0295] "Report" means a formal notification or recording made to convey information about a particular event or situation.

[0296] "Classification" refers to the grouping of collected data or information based on specific criteria.

[0297] "Filtering" refers to sorting data or information based on specific criteria and extracting only what is needed.

[0298] "Data collection" refers to the act of gathering information or data needed for a specific purpose.

[0299] "Preprocessing" refers to the process of preparing data for analysis by performing operations such as filling in missing values ​​and correcting outliers before conducting data analysis.

[0300] A "generative AI model" is a specific implementation of generative AI, and refers to algorithms and programs for generating new information and suggestions based on data.

[0301] "Analysis" refers to the act of analyzing collected data to find specific patterns or trends.

[0302] "Countermeasures" refers to specific actions or measures taken in response to a particular problem or issue.

[0303] "Preventive measures" refer to specific actions or steps taken to prevent a particular problem or issue before it occurs.

[0304] "Notice" means a formal communication or notification made to convey specific information or proposals to interested parties.

[0305] This invention is a system that uses generative AI to propose measures and preventive measures against harassment. A specific embodiment of this system is shown below.

[0306] The server first collects data on harassment from each department in the company, including the number of reported cases, the time of occurrence, the location of occurrence, the type of harassment, etc. For example, it collects report data from the sales department and survey results.

[0307] The server then preprocesses the collected data by completing missing values, detecting and correcting outliers, and standardizing the data and converting it into a format suitable for generative AI models, such as converting text data into numerical data.

[0308] The server inputs the preprocessed data into a generative AI model (for example, OpenAI's GPT-4) and performs analysis. The generative AI model analyzes the data and identifies departments, time periods, and types of harassment that occur frequently. For example, it identifies that harassment occurs frequently in the sales department between 3:00 and 5:00 p.m.

[0309] The server then uses the results of the generative AI model's analysis to suggest specific countermeasures and preventative measures, such as providing harassment prevention training to the sales department and strengthening monitoring between 3:00 and 5:00 p.m.

[0310] Finally, the server notifies the user of the proposed content. Specifically, it sends the content to the relevant parties via email or the company's internal messaging system. For example, it notifies the sales department manager that harassment prevention training should be conducted.

[0311] As a concrete example, consider the following scenario.

[0312] scenario:

[0313] Data was collected showing that harassment reports were more frequent during a certain time period (3:00 to 5:00 pm) in the sales department of a certain company. Based on this data, a generative AI model analyzes and proposes countermeasures.

[0314] Example prompt:

[0315] "There have been many reports of harassment in the sales department between 3:00 and 5:00 p.m. Please suggest measures and preventative measures for harassment during this time period."

[0316] Example output of a generative AI model:

[0317] "To combat harassment between the hours of 3pm and 5pm, here are some suggestions:

[0318] 1. Strengthen surveillance during this time period.

[0319] 2. Conduct harassment prevention training for all employees in the sales department.

[0320] 3. Improve the harassment reporting system and allow anonymous reporting.

[0321] 4. Make adjustments to reduce work load during this time.”

[0322] In this way, the server utilizes the generative AI model to provide a system that proposes measures and preventive measures against harassment and notifies the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0323] Step 1:

[0324] The server collects data on harassment from each department within the company. The inputs are the databases and survey results of each department. In concrete terms, the server accesses the databases of each department and obtains report data such as "October 1, 2023, 3:00 p.m., Sales department, verbal violence." The output is the collected harassment data.

[0325] Step 2:

[0326] The server preprocesses the collected data. As input, there is the harassment data collected in step 1. Specifically, the server complements missing values ​​in the data, detects and corrects outliers, and standardizes the data and converts it into a format suitable for the generative AI model. For example, for data where the "occurrence time" is missing, it complements the average occurrence time. As output, the preprocessed data is obtained.

[0327] Step 3:

[0328] The server inputs the preprocessed data into a generative AI model and performs analysis. The input is the data preprocessed in step 2. Specifically, the server inputs the data into a generative AI model (for example, OpenAI's GPT-4) and identifies departments, time periods, and types of harassment where harassment occurs frequently. For example, it identifies a pattern that "verbal abuse frequently occurs in the sales department between 3:00 and 5:00 p.m." The output is the analysis results.

[0329] Step 4:

[0330] The server proposes specific countermeasures and preventive measures based on the analysis results of the generative AI model. The input is the analysis results obtained in step 3. As specific actions, the server proposes to the sales department to "strengthen the monitoring system between 3:00 and 5:00 pm" and "conduct training to prevent harassment." The proposals are obtained as output.

[0331] Step 5:

[0332] The server notifies the user of the proposal. The input is the proposal obtained in step 4. In concrete terms, the server sends the proposal to the relevant parties via email or the internal messaging system. For example, it sends an email to the manager of the sales department saying, "Please consider strengthening the monitoring system between 3:00 and 5:00 p.m." The output is that the notification has been completed.

[0333] (Application example 3)

[0334] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0335] In conventional harassment prevention systems, reporting and analysis of harassment was often done manually, making it difficult to respond quickly. In addition, data analysis to identify trends and patterns of harassment was insufficient, making it difficult to propose specific countermeasures and preventive measures. Furthermore, the system lacked the ability to detect high-risk situations of harassment in real time and send appropriate alerts, making it difficult to effectively hedge risks.

[0336] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using a generative AI and filtering them according to importance and urgency, a means for analyzing the report contents using a generative AI model and identifying the frequency, type, location, and time of harassment, a means for proposing specific harassment countermeasures and preventive measures based on the analysis results, and a means for detecting high-risk situations of harassment in real time and sending an alert to the user. This makes it possible to quickly respond to harassment, identify trends and patterns, propose specific countermeasures and preventive measures, and detect risks in real time and send alerts.

[0337] "Generative AI" is a type of artificial intelligence technology, a system that has the ability to generate new data and information based on input data.

[0338] "Inquiry" means a question or request for specific information or assistance.

[0339] A "report" is a written or oral communication made to provide information about a particular event or situation.

[0340] "Classification" is the process of grouping data or information based on specific criteria.

[0341] "Filtering" is the process of selecting data or information based on specific conditions and removing unnecessary information.

[0342] A "generative AI model" is a specific implementation of generative AI, an artificial intelligence model trained to perform a specific task.

[0343] "Analysis" is the process of examining data or information in detail to identify certain patterns or trends.

[0344] "Frequency" refers to the number of times or the rate at which a particular event or situation occurs.

[0345] A "type" is a category that is classified based on a particular characteristic or property.

[0346] "Location" refers to the physical location or environment in which a particular event or situation occurs.

[0347] A "time period" is a specific division or range of time.

[0348] A "countermeasure" is a specific action or measure to address a particular problem or risk.

[0349] A "prevention measure" is a specific action or measure taken to prevent a particular problem or risk before it occurs.

[0350] "Real-time" refers to immediate processing or response without delay.

[0351] An "alert" is a notification or warning intended to draw attention to a particular situation or risk.

[0352] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[0353] System Configuration

[0354] The system consists of the following main components:

[0355] 1. Server: Runs the generative AI model, analyzes harassment reports, suggests countermeasures and prevention measures, and sends real-time alerts.

[0356] 2. Terminal: The device on which a user enters a harassment report and receives analysis results and countermeasures / prevention measures. This applies to smartphones and computers.

[0357] 3. Network: A communications infrastructure that connects servers and terminals and transmits and receives data.

[0358] Hardware and software used

[0359] Hardware: Servers, smartphones, PCs

[0360] Software: OpenAI API, Python, Database Management System (e.g. MySQL)

[0361] Data processing and calculation

[0362] 1. Fill out a harassment report:

[0363] Users use the device to input reports of harassment using text, voice, images, etc.

[0364] The entered data is sent to the server and stored in a database.

[0365] 2. Analysis using generative AI models:

[0366] The server analyzes the reports using OpenAI's generative AI models (e.g. GPT-4).

[0367] The results of the analysis will include identifying the frequency, type, location, and time of occurrence of harassment.

[0368] 3. Suggested measures and prevention:

[0369] Based on the analysis results, the server uses a generative AI model to propose specific countermeasures and preventive measures.

[0370] The suggestions are sent to the device and notified to the user.

[0371] 4. Real-time alerts:

[0372] The server detects high risk situations of harassment in real time and sends alerts to users.

[0373] The alert will be displayed on the device to alert the user.

[0374] Examples

[0375] Examples of Harassment Reports

[0376] Report: "The sales department continues to receive excessive scolding from their superiors every Friday afternoon."

[0377] Example of analysis results

[0378] Analysis: "Sales department, Friday afternoon, scolding from boss"

[0379] Examples of proposed countermeasures and preventive measures

[0380] Countermeasures and prevention measures: "The sales department sent out a warning message on Friday afternoon. We conducted harassment prevention training for superiors."

[0381] Examples of prompt statements

[0382] Analysis prompt: "Analyze the following harassment reports to determine frequency, type, location, and time of day.\nReport: {report}"

[0383] Prompt for suggesting measures: "Please suggest specific measures and preventative measures against harassment based on the following analysis results.\nAnalysis results: {analysis}"

[0384] The above is an embodiment of the present invention. This system allows for rapid response to harassment, identification of trends and patterns, proposal of specific countermeasures and preventative measures, and real-time risk detection and alert sending.

[0385] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0386] Step 1:

[0387] Users use the device to input reports of harassment. Input can be done in the form of text, voice, image, etc. The input data is sent from the device to a server and stored in a database. Input data includes details of the harassment, the location where it occurred, the time of day, etc.

[0388] Step 2:

[0389] The server retrieves the report data from the database and analyzes the report contents using a generative AI model (e.g., GPT-4). Specifically, the report contents are input as prompts into the generative AI model to identify the frequency, type, location, time of day, etc. of harassment. The input data is the report contents, and the output data is the analysis results.

[0390] Step 3:

[0391] Based on the analysis results, the server uses a generative AI model to propose specific countermeasures and preventive measures. Using a prompt sentence, the server inputs the analysis results into the generative AI model to obtain suggested countermeasures and preventive measures. The input data is the analysis results, and the output data is the suggested countermeasures and preventive measures.

[0392] Step 4:

[0393] The server sends the proposed countermeasures and preventive measures to the terminal and notifies the user. The user can check the proposed countermeasures and preventive measures through the terminal and take necessary actions. The input data is the proposed countermeasures and preventive measures, and the output data is the notification to the user.

[0394] Step 5:

[0395] The server continuously monitors data to detect situations with a high risk of harassment in real time. If a high-risk situation is detected, the server generates an alert in real time and sends it to the terminal. The user receives the alert through the terminal and takes appropriate action. The input data is the real-time monitoring data, and the output data is the alert.

[0396] These are the specific processing steps of this system. The specific actions taken at each step enable rapid response to harassment, identification of trends and patterns, proposal of specific countermeasures and preventive measures, and real-time risk detection and alert sending.

[0397] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0398] "Example 1"

[0399] One embodiment of the present invention is a system that combines a generative AI and an emotion engine. This system collects text data from users, and the generative AI analyzes the data. As a result of the analysis, harassment-related content is automatically classified and filtered according to importance and urgency. Furthermore, the emotion engine recognizes the user's emotions and incorporates that information into the generative AI's analysis. Specifically, the emotion engine recognizes the user's emotional state (anger, fear, sadness, etc.) when making a report, and the generative AI uses that information for analysis. This makes it possible to more accurately determine the severity and urgency of harassment.

[0400] "Example 2"

[0401] Another embodiment of the present invention is a system that combines a generative AI and an emotion engine to identify trends and patterns of harassment. In this system, the results of the analysis by the generative AI are combined with the emotional information recognized by the emotion engine to identify trends and patterns of harassment. Specifically, if a specific emotional state is determined to be closely related to the occurrence of harassment, that information is used to identify trends and patterns of harassment. This makes it possible to more effectively plan preventive measures against harassment.

[0402] "Example 3"

[0403] As a further embodiment of the present invention, there is a system that combines a generative AI and an emotion engine to propose countermeasures and preventive measures against harassment. In this system, the results of the analysis by the generative AI are combined with the emotional information recognized by the emotion engine to propose countermeasures and preventive measures against harassment. Specifically, if a specific emotional state is determined to be closely related to the occurrence of harassment, that information is used to propose countermeasures and preventive measures against harassment. This makes it possible to plan preventive measures against harassment more effectively.

[0404] The process flow of each embodiment will be described below.

[0405] "Example 1"

[0406] Step 1: Collect text data from users.

[0407] Step 2: Generative AI analyzes the text data and automatically classifies content related to harassment.

[0408] Step 3: Filter the classified content according to importance and urgency.

[0409] Step 4: The emotion engine recognizes the user's emotion.

[0410] Step 5: Incorporate the recognized emotion information into the generative AI analysis.

[0411] "Example 2"

[0412] Step 1: Collect text data from users.

[0413] Step 2: Generative AI analyzes the text data and automatically classifies content related to harassment.

[0414] Step 3: The emotion engine recognizes the user's emotion.

[0415] Step 4: Combine the recognized emotional information with the results of generative AI analysis to identify harassment trends and patterns.

[0416] "Example 3"

[0417] Step 1: Collect text data from users.

[0418] Step 2: Generative AI analyzes the text data and automatically classifies content related to harassment.

[0419] Step 3: The emotion engine recognizes the user's emotion.

[0420] Step 4: Combine the recognized emotional information with the results of generative AI analysis to propose countermeasures and preventative measures against harassment.

[0421] Example 1

[0422] Next, a description will be given of Example 1 of the embodiment 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".

[0423] In conventional harassment reporting systems, classification of report contents and judgment of urgency are often done manually, which makes it difficult to respond quickly. In addition, because the report contents are processed without considering the emotional state of the user, it is difficult to accurately judge the seriousness of the harassment. Furthermore, there is a lack of systems that can take appropriate action while ensuring anonymity.

[0424] 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.

[0425] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using a generative AI, a means for filtering according to importance and urgency, a means for enabling a rapid response and leading to risk hedging, a means for recognizing the emotional state of a user using an emotion engine and incorporating the information into the generative AI analysis, a means for collecting text data through an anonymous reporting channel using a chatbot, a means for transmitting the collected text data to the server in real time, and a means for notifying an appropriate person in charge based on the results of the generative AI analysis. This makes it possible to quickly and accurately process reports related to harassment and respond in consideration of the emotional state of the user.

[0426] "Generative AI" is artificial intelligence that uses natural language processing technology to analyze text data and generate information for specific purposes.

[0427] An "emotion engine" is software that recognizes a user's emotional state (e.g., anger, fear, sadness, etc.) from text data and provides that information.

[0428] A "chatbot" is an automated response system that communicates with users in a dialogue format to collect specific information.

[0429] An "anonymous reporting channel" is a means of communication that allows users to report information without revealing their identity.

[0430] "Text data" refers to character information entered by a user, and is data that includes the contents of a report or inquiry.

[0431] "Classification" is the process of dividing collected text data into categories based on specific criteria.

[0432] "Filtering" is the process of selecting classified data according to its importance or urgency.

[0433] "Prompt response" means taking prompt and appropriate action based on the contents of the report.

[0434] "Risk hedging" refers to detecting potential risks in advance and taking measures to minimize their impact.

[0435] "Real-time" refers to data being processed as soon as it is generated.

[0436] "Appropriate person" refers to the person or department responsible for any work that requires action based on the contents of the report.

[0437] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0438] This invention uses a system that combines generative AI and an emotion engine to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is shown below.

[0439] 1. Program Generation

[0440] The server generates a program for the system that combines generative AI and an emotion engine. This program includes a series of processes for collecting, analyzing, classifying, filtering, and quickly responding to reports from users.

[0441] 2. Program Processing Explanation

[0442] The server executes programs using the following hardware and software.

[0443] Hardware: Servers, terminals

[0444] Software: Generative AI (e.g., OpenAI's GPT-4), emotion engines (e.g., IBM Watson®'s Tone Analyzer), chatbots

[0445] Data collection:

[0446] Users use the chatbot to input text data about the harassment through an anonymous reporting channel. For example, a user might enter, "My boss is continuing to harass me and it's taking a toll on me mentally."

[0447] Data transmission:

[0448] The terminal transmits the text data sent by the user to the server in real time.

[0449] Data Analysis:

[0450] The server inputs the collected text data into the generative AI and analyzes the content related to harassment. Specifically, the server inputs the text data into the generative AI as a prompt sentence, instructing it to "analyze this report and determine the severity and urgency of the harassment."

[0451] Emotion recognition:

[0452] The server uses an emotion engine to recognize the user's emotional state (e.g., anger, fear, sadness, etc.) and provides that information to the generative AI. The emotion engine analyzes the text data and recognizes the user's emotional state as "sadness."

[0453] Sorting and filtering:

[0454] The generative AI classifies the text data according to the severity and urgency of the harassment based on the emotional information provided by the emotion engine. The server filters the data according to importance and urgency based on this classification result. For example, the generative AI classifies the text data as "serious harassment" and determines the urgency as "high."

[0455] Response notification:

[0456] The server notifies the appropriate person in charge based on the filtered results and takes the necessary action promptly. Specifically, the server sends reports with a high level of urgency to the person in charge via email or a notification system, notifying them that "prompt action is required for this report."

[0457] 3. Examples of concrete examples and prompts

[0458] Examples:

[0459] If a user reports through an anonymous chatbot, "My boss is continuing to harass me and it's causing me mental distress," the following process will be followed:

[0460] 1. The user types into the chatbot, "My boss is continuing to harass me and it's causing me a lot of mental stress."

[0461] 2. The terminal sends this text data to the server.

[0462] 3. The server inputs the text data into the generative AI and instructs it to "analyze this report and determine the severity and urgency of the harassment."

[0463] 4. The server inputs the text data into the emotion engine, which then recognizes the emotion of "sadness."

[0464] 5. The generative AI classifies the text data as "serious harassment" and judges the urgency to be "high." The server filters this classification result and extracts reports with a high urgency.

[0465] 6. The server sends high-urgency reports to the responsible person via email or a notification system, notifying them that "this report requires immediate action."

[0466] Example prompt:

[0467] "I am being harassed by my boss and it is causing me a lot of mental stress. Please analyze this report and determine the severity and urgency of the harassment."

[0468] In this way, a system is realized in which the server, terminals, and users work together to quickly and accurately process reports related to harassment.

[0469] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0470] Step 1:

[0471] Users utilize the chatbot to input text data about harassment through an anonymous reporting channel.

[0472] Specifically, the user types into the chatbot's interface, "My boss is continuing to harass me and it's causing me a lot of mental stress."

[0473] Input: Text data entered by the user.

[0474] Output: Text data sent to the chatbot

[0475] Step 2:

[0476] The terminal transmits the text data sent by the user to the server in real time.

[0477] As a specific operation, the terminal immediately transfers the text data entered by the user to the server.

[0478] Input: Text data sent to the chatbot

[0479] Output: Text data sent to the server

[0480] Step 3:

[0481] The server inputs the collected text data into a generative AI system and analyzes it for harassment-related content.

[0482] Specifically, the server inputs the text data into the generative AI as a prompt, instructing it to "analyze this report and determine the severity and urgency of the harassment."

[0483] Input: Text data sent to the server

[0484] Output: Analysis results by generative AI

[0485] Step 4:

[0486] The server uses an emotion engine to recognize the user's emotional state (e.g., anger, fear, sadness, etc.) and provides that information to the generative AI.

[0487] Specifically, the server inputs the text data into an emotion engine, which then recognizes the emotion of "sadness."

[0488] Input: Text data sent to the server

[0489] Output: Emotion recognition results by the emotion engine

[0490] Step 5:

[0491] The generative AI classifies the text data according to the severity and urgency of the harassment based on the emotional information provided by the emotion engine.

[0492] Specifically, the generative AI classifies the text data as "serious harassment" and determines the urgency as "high."

[0493] Input: Analysis results by generative AI and emotion recognition results by emotion engine

[0494] Output: Classified harassment severity and urgency

[0495] Step 6:

[0496] Based on the classification results, the server performs filtering according to importance and urgency.

[0497] As a specific operation, the server extracts reports with a high level of urgency.

[0498] Input: Classified harassment severity and urgency

[0499] Output: Filtered report data

[0500] Step 7:

[0501] Based on the filtered results, the server notifies the appropriate person in charge and takes the necessary action promptly.

[0502] Specifically, the server will send high-urgency reports to the person in charge via email or a notification system, and notify them that "this report requires immediate action."

[0503] Input: Filtered report data

[0504] Output: Notification to the person in charge and instructions on how to respond

[0505] (Application example 1)

[0506] Next, a description will be given of Application Example 1 of Form 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."

[0507] Conventional harassment reporting systems often manually classify the contents of reports and determine their importance, making it difficult to respond quickly. In addition, because the reporter's emotional state is not taken into account, it is difficult to accurately determine the severity and urgency of the harassment. Furthermore, it is difficult to report anonymously, which can make reporters hesitant to report. There is a need for a system that can solve these problems and manage harassment reports more efficiently and accurately.

[0508] 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.

[0509] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for recognizing the emotional state of the user using an emotion engine and incorporating the information into the generative AI analysis, a means for accepting anonymous reports through an application installed on a smartphone, a means for proposing appropriate countermeasures based on the report contents, and a means for enabling a rapid response and leading to risk hedging. This automates the classification of the report contents and the determination of the importance, enabling a rapid and accurate response. In addition, by taking into account the reporter's emotional state, the severity and urgency of the harassment can be more accurately determined. Furthermore, it becomes easier to report anonymously, and reporters can report without hesitation.

[0510] "Generative AI" is an artificial intelligence technology that generates new information and results based on data provided by users.

[0511] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state from data such as text and voice.

[0512] A "smartphone" is a multi-function mobile device that can connect to the Internet and run applications in addition to the functions of a mobile phone.

[0513] An "anonymous report" is a method of reporting a problem or incident without disclosing the reporter's personal information.

[0514] "Importance" is an indicator of the magnitude of impact and priority of a reported event or problem.

[0515] "Urgency" is an indicator of how quickly a response is required to a reported event or problem.

[0516] "Filtering" is the process of sorting through data based on specific criteria to extract only the information you need.

[0517] "Prompt response" refers to taking appropriate measures promptly in response to a problem or incident.

[0518] "Risk hedging" refers to minimizing risks by predicting potential risks and taking measures against them.

[0519] "Appropriate response" refers to the most effective and appropriate solution or measure to address a reported event or problem.

[0520] The system for implementing this invention combines a generative AI and an emotion engine, and operates through an application installed on a smartphone. A specific embodiment of this system will be described below.

[0521] System Configuration

[0522] Hardware

[0523] Smartphone: A device for users to enter reports.

[0524] Server: A computer system for running the generative AI and emotion engine, and analysing data.

[0525] software

[0526] Generative AI: Uses OpenAI APIs to analyze and classify report content.

[0527] Emotion Engine: Uses TextBlob to analyze the user's emotional state.

[0528] Smartphone application: Provides an interface for users to enter and submit reports anonymously.

[0529] Data processing and calculation

[0530] Smartphone

[0531] Users can anonymously report harassment through a smartphone application, and the text data is sent to a server.

[0532] server

[0533] The server processes the received text data in the following procedure.

[0534] 1. Sentiment Analysis: Use TextBlob to analyze the emotional state of the report text, specifically, score the text for positive, negative, or neutral sentiment.

[0535] 2. Generative AI classification: Using OpenAI’s API, we classify the report text according to the severity and urgency of the harassment. We generate prompt text and let the AI ​​analyze it.

[0536] Examples

[0537] Report content

[0538] "My boss yells at me every day and I can't concentrate on my work. I'm very stressed."

[0539] Emotion analysis results

[0540] Strong negative emotions

[0541] Generative AI classification results

[0542] Severity: High, Urgency: High

[0543] Examples of prompt statements

[0544] Please classify the text below according to the severity and urgency of the harassment:

[0545] My boss yells at me every day and I can't concentrate on my work. I'm feeling very stressed.

[0546] Classification:

[0547] effect

[0548] This system automates the classification and prioritization of reports, enabling a fast and accurate response. It also takes into account the reporter's emotional state, allowing for a more accurate assessment of the severity and urgency of the harassment. It also makes it easier to report anonymously, allowing reporters to do so without hesitation.

[0549] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0550] Step 1:

[0551] Users anonymously enter reports of harassment through a smartphone application.

[0552] Input: Text data entered by the user.

[0553] Output: Text data sent from the smartphone to the server.

[0554] Specific actions: The user fills in the application's input form with the report details and presses the submit button.

[0555] Step 2:

[0556] The text data received by the server is passed to the emotion engine for emotion analysis.

[0557] Input: Text data sent from the smartphone.

[0558] Output: Sentiment analysis results (positive, negative, neutral scores).

[0559] What happens: The server uses TextBlob to analyze the emotional state of the text data and generate an emotional score.

[0560] Step 3:

[0561] The server passes the results of the emotion analysis to a generative AI, which then classifies the report content.

[0562] Input: Sentiment analysis results and text data.

[0563] Output: Classification results (severity and urgency) generated by generative AI.

[0564] Specific operation: The server uses OpenAI's API to generate prompt text and classify the report content based on text data and sentiment analysis results.

[0565] Step 4:

[0566] The server then suggests appropriate countermeasures based on the classification results.

[0567] Input: Classification results from generative AI.

[0568] Output: A suggested action to take.

[0569] Specific operation: The server analyzes the classification results, selects and proposes the most appropriate countermeasure from a pre-configured countermeasure database.

[0570] Step 5:

[0571] The server sends the proposed countermeasures to the smartphone application and notifies the user.

[0572] Input: The proposed action.

[0573] Output: Countermeasures displayed on the smartphone application.

[0574] Specific operation: The server sends the countermeasures to the smartphone application and generates a message to notify the user.

[0575] Step 6:

[0576] The user reviews the proposed solutions and provides additional reporting and feedback as necessary.

[0577] Input: Proposed workaround and user feedback.

[0578] Output: Additional reporting and feedback data.

[0579] Specific Actions: The user reviews the proposed solutions through the application and provides additional reports and feedback if necessary.

[0580] Example 2

[0581] Next, a second embodiment of the second embodiment will be described. 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."

[0582] In conventional anti-harassment systems, analysis to identify trends and patterns of harassment is often performed manually, which is time-consuming and labor-intensive. In addition, since analysis does not take into account emotional information, it is difficult to devise effective measures to prevent the occurrence of harassment. Furthermore, data visualization and report generation are not automated, making it difficult to respond quickly. To solve these issues, a system that combines generative AI and an emotion engine is needed.

[0583] 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.

[0584] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for preprocessing collected data, a means for analyzing data using a generative AI model, a means for recognizing emotional information using an emotion engine, a means for visualizing data by integrating the analysis results of the generative AI and the emotional information of the emotion engine, a means for automatically generating a report based on the visualized data, and a means for enabling a rapid response and leading to risk hedging. This makes it possible to effectively identify trends and patterns of harassment and to plan preventive measures that take emotional information into account. In addition, the visualization of data and automatic generation of reports enable a rapid response.

[0585] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[0586] "Harassment" refers to inappropriate language or behavior toward others in the workplace or any other environment.

[0587] "Inquiry" means a question or request made for specific information or assistance.

[0588] A "report" is a communication made to provide information about a particular event or situation.

[0589] "Classification" is the process of grouping data or information based on specific criteria.

[0590] "Filtering" is the process of selecting data or information based on specific conditions.

[0591] "Preprocessing" is the initial stage of processing to convert data into a form suitable for analysis and processing.

[0592] "Generative AI model" refers to the specific implementation and algorithms of generative AI.

[0593] An "emotion engine" is a technology for recognizing emotional information from data such as text and voice.

[0594] "Emotion information" is information that indicates the emotional state or tendency contained in the data.

[0595] "Integration" is the process of bringing together multiple pieces of data or information into one.

[0596] "Visualization" is the process of representing data or information in a visual form, such as a graph or chart.

[0597] A "report" is a document that compiles specific information or analytical results.

[0598] "Rapid response" refers to taking quick and appropriate action in response to a problem or situation.

[0599] "Risk hedging" refers to taking measures or steps to reduce potential risks.

[0600] This invention is a system that uses generative AI and an emotion engine to identify trends and patterns of harassment, visualize the data, and generate reports. A specific embodiment of this system is described below.

[0601] Hardware and Software Used

[0602] Hardware: Servers, terminals

[0603] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva), data pre-processing tools (e.g. Python, NLTK, Pandas), visualization tools (e.g. Tableau)

[0604] System Overview

[0605] The system starts with users uploading harassment-related data from their devices to a server. The server preprocesses the collected data and analyzes it using a generative AI model. It then recognizes emotional information using an emotion engine and integrates the generative AI analysis results with the emotional information. The integrated data is visualized, and finally a report is automatically generated.

[0606] Specific operation example

[0607] 1. Data Collection

[0608] Users upload files such as internal chat logs, emails, and survey results from their devices to the server.

[0609] Specific behavior: A user opens a browser, accesses the system's upload page, opens a file selection dialog, selects a file to upload, and clicks the Upload button.

[0610] 2. Data Preprocessing

[0611] The server parses the received data and performs text cleaning (e.g., removing HTML tags and special characters), then tokenizes the text and converts it into a data format for sentiment analysis.

[0612] Software used: Python, NLTK, Pandas

[0613] 3. Generative AI Analysis

[0614] The server inputs prompt sentences into a generative AI model (e.g., GPT-4) to extract harassment trends and patterns.

[0615] Specific behavior: "This chat log contains a lot of offensive language."

[0616] 4. Sentiment Analysis Using an Emotion Engine

[0617] The server feeds the text data into an emotion engine (e.g., Affectiva) to detect specific emotional states (e.g., anger, sadness).

[0618] Specific behavior: "This email expresses strong feelings of anger."

[0619] 5. Data integration and visualization

[0620] The server combines the analysis results of the generative AI with the emotional information from the emotion engine, and inputs them into a visualization tool (e.g., Tableau) to create graphs and charts.

[0621] Specific behavior: "Harassment occurs more frequently in certain departments."

[0622] 6. Generate reports

[0623] The server uses a report generation tool to create a report including the analysis results and countermeasure proposals.

[0624] Specific action: "Implementing regular emotional check-ins can help prevent harassment."

[0625] Examples of prompt statements

[0626] "Analyze these chat logs to identify trends and patterns of harassment."

[0627] "Please recognize the emotional state of this email and determine if it is related to an incident of harassment."

[0628] This system makes it possible to effectively identify trends and patterns of harassment and develop preventive measures that take emotional information into account. It also enables rapid response by visualizing data and automatically generating reports.

[0629] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0630] Step 1:

[0631] Data collection

[0632] Users upload files such as internal chat logs, emails, and survey results from their devices to the server.

[0633] Input: Files selected by the user (e.g. chat logs, emails, survey results)

[0634] Specific behavior: A user opens a browser, accesses the system's upload page, opens a file selection dialog, selects a file to upload, and clicks the Upload button.

[0635] Output: The file uploaded to the server.

[0636] Step 2:

[0637] Data Preprocessing

[0638] The server pre-processes the data received.

[0639] Input: The uploaded file

[0640] What it does: The server cleans the text data, removing unnecessary characters and noise, then tokenizes the text and converts it into a data format for sentiment analysis.

[0641] Output: Preprocessed text data

[0642] Software used: Python, NLTK, Pandas

[0643] Step 3:

[0644] Generative AI Analysis

[0645] The server analyzes the pre-processed data using a generative AI model (e.g., GPT-4).

[0646] Input: Preprocessed text data

[0647] How it works: The server inputs prompt sentences into the generative AI model and extracts harassment trends and patterns.

[0648] Output: Analysis of harassment trends and patterns.

[0649] Example prompt: "Analyze this chat log to identify trends or patterns of harassment."

[0650] Step 4:

[0651] Sentiment analysis with emotion engine

[0652] The server uses an emotion engine (e.g., Affectiva) to recognize emotion information in the data.

[0653] Input: Preprocessed text data

[0654] What happens: The server inputs text data into the emotion engine to detect specific emotional states (e.g. anger, sadness).

[0655] Output: Analysis results on emotional information

[0656] Example prompt: "Please identify the emotional state of this email and determine if it is related to an incident of harassment."

[0657] Step 5:

[0658] Data integration and visualization

[0659] The server integrates the analysis results of the generative AI with the emotional information from the emotion engine and visualizes the data.

[0660] Input: Analysis results of generative AI, emotion information of emotion engine

[0661] Specific operation: The server inputs the consolidated data into a visualization tool (e.g. Tableau) to create graphs and charts.

[0662] Output: Visualized data (graphs and charts)

[0663] Step 6:

[0664] Generate reports

[0665] The server automatically generates reports on harassment trends and patterns based on the visualized data.

[0666] Input: Visualized data

[0667] Specific operations: The server uses a report generation tool to create a report that includes the analysis results and countermeasure suggestions.

[0668] Output: Auto-generated report

[0669] Specific example of how it works: Generate a report that includes the suggestion that "introducing regular emotional check-ins could help prevent harassment."

[0670] (Application example 2)

[0671] Next, a description will be given of Application Example 2 of Form 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."

[0672] Conventional anti-harassment systems have difficulty identifying trends and patterns of harassment, and also have difficulty in monitoring in real time and responding quickly. As a result, they have been unable to effectively reduce the risk of harassment, and there have been many delays in protecting victims and formulating preventive measures. In addition, because emotion analysis using an emotion engine has not been performed, it has not been possible to accurately grasp the occurrence of harassment. To solve these issues, a system that combines generative AI and an emotion engine is needed.

[0673] 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.

[0674] In this invention, the server includes a means for automatically classifying inquiries and reports related to workplace harassment using generative AI and filtering them according to importance and urgency, a means for combining generative AI with an emotion engine to identify trends and patterns of harassment, and a means for visualizing data and generating reports, thereby enabling real-time monitoring of harassment risks and rapid response.

[0675] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[0676] An "emotion engine" is a technology that analyzes emotions from data such as text and voice, and identifies the emotional state.

[0677] "Harassment" is the act of causing mental or physical pain to another person through inappropriate verbal or physical actions in a workplace, school, or other environment.

[0678] A "trend" is a quality or pattern that a particular phenomenon or behavior moves in a certain direction.

[0679] A "pattern" is a regularity or form in which a particular phenomenon or behavior occurs repeatedly.

[0680] "Data visualization" is a technique for representing data in a visual format, such as in graphs or charts, to make it easier to understand.

[0681] "Report generation" is the process of automatically generating reports based on analysis results and data.

[0682] A "countermeasure" is a specific means or method taken to address a specific problem or risk.

[0683] A "preventive measure" is a means or method for preventing a problem or risk before it occurs.

[0684] A "smartphone" is a multi-function mobile device that, in addition to the functions of a mobile phone, can also connect to the Internet and use applications.

[0685] "Real-time" means that data and information are processed immediately and provided without delay.

[0686] "Filtering" is the process of sorting data based on specific conditions and extracting only the necessary information.

[0687] "Text data" is digital data that contains character information.

[0688] "Sentiment analysis" is a technology that analyzes emotional states from data such as text and voice, and identifies those emotions.

[0689] The system for implementing this invention combines generative AI and an emotion engine to identify trends and patterns of harassment, visualize the data, and generate reports. A specific embodiment of this system is described below.

[0690] System Configuration

[0691] The system consists of the following main components:

[0692] 1. Generative AI model: Artificial intelligence technology that generates new information and patterns based on data.

[0693] 2. Emotion engine: Technology that analyzes emotions from data such as text and voice and identifies the emotional state.

[0694] 3. Smartphone application: An interface for users to monitor harassment risk in real time and enter data.

[0695] 4. Data Visualization Tools: Use software such as Matplotlib or Pandas to create visual representations of your data.

[0696] 5. Report generation function: A function that automatically creates reports based on analysis results.

[0697] Program Processing

[0698] The server uses a generative AI model to identify trends and patterns of harassment from the input text. Specifically, it uses OpenAI's API to analyze the text data entered by the user and evaluate the risk of harassment. The emotion engine performs sentiment analysis on the text data and determines whether a specific emotional state is closely related to the occurrence of harassment.

[0699] Data Visualization and Reporting

[0700] The server uses Matplotlib and Pandas to visualize the emotion data analyzed by the emotion engine, allowing users to visually understand harassment trends and patterns. In addition, a report is automatically generated based on the analysis results of the generative AI model and the emotion engine. This report includes harassment trends and patterns, emotional states, and suggestions for countermeasures and prevention measures.

[0701] Examples

[0702] For example, if the input data were a log of a conversation at work, the user might enter the following text:

[0703] "In yesterday's meeting, the boss used very harsh words towards his subordinate. The subordinate was clearly uncomfortable."

[0704] Based on this text data, the generative AI model identifies harassment trends and patterns using the following prompts:

[0705] Identify trends or patterns of harassment in the following text:

[0706] "In yesterday's meeting, the boss used very harsh words towards his subordinate. The subordinate was clearly uncomfortable."

[0707] The emotion engine analyzes the emotional state of the text data and identifies strong emotions such as anger or sadness. Based on this data, the server visualizes the data and generates a report.

[0708] In this way, users can monitor harassment risks in real time and respond quickly.

[0709] The flow of the identification process in the application example 2 will be described with reference to FIG.

[0710] Step 1:

[0711] A user inputs text data such as conversation logs from work or school through a smartphone application.

[0712] Input: Text data such as conversation logs

[0713] Output: The text data entered

[0714] Step 2:

[0715] The server sends the input text data to a generative AI model and performs analysis to identify trends and patterns of harassment. Specifically, it uses OpenAI's API to analyze the text data.

[0716] Input: The text data entered.

[0717] Output: Analysis of harassment trends and patterns

[0718] Step 3:

[0719] The server uses an emotion engine to perform emotion analysis of the text data based on the analysis results. The emotion engine identifies emotional states such as "anger" or "sadness" from the text data.

[0720] Input: Input text data, analysis results of generative AI model

[0721] Output: Data about emotional state

[0722] Step 4:

[0723] The server uses Matplotlib and Pandas to visualize the emotion data analyzed by the emotion engine, allowing users to visually understand trends and patterns of harassment.

[0724] Input: Data about emotional state

[0725] Output: Visualized data (graphs and charts)

[0726] Step 5:

[0727] Based on the results of the generative AI model and emotion engine analysis, the server automatically generates a report that includes harassment trends and patterns, emotional states, and suggested countermeasures and prevention measures.

[0728] Input: Analysis results of generative AI model, data on emotional state

[0729] Output: Auto-generated report

[0730] Step 6:

[0731] Through a smartphone application, users can review the generated reports, monitor harassment risks in real time, and respond quickly.

[0732] Input: Auto-generated report

[0733] Output: Reports reviewed by the user

[0734] In this way, users can monitor harassment risks in real time and respond quickly.

[0735] Example 3

[0736] Next, a third embodiment of the third embodiment will be described. 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."

[0737] Conventional anti-harassment systems found it difficult to effectively propose specific measures and preventive measures to prevent harassment from occurring. In addition, there was a lack of measures that took into account the emotional state of employees, making it difficult to identify the root causes of harassment. Furthermore, the collection and analysis of data on harassment was often done manually, which meant insufficient risk hedging in situations where a rapid response was required.

[0738] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using a generative AI and filtering them according to importance and urgency, a means for identifying trends and patterns of harassment using a generative AI model, a means for collecting employee emotional information using an emotion engine and analyzing the relationship between the emotional state and the occurrence of harassment, a means for proposing measures and preventive measures against harassment based on the analysis results of the generative AI model and the recognition results of the emotion engine, a means for visualizing data and generating reports, and a means for enabling a rapid response and leading to risk hedging. This makes it possible to prevent the occurrence of harassment and propose effective measures and preventive measures that take into account the emotional state of employees.

[0739] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[0740] "Harassment" refers to acts of harassment or unfair treatment in the workplace or organization.

[0741] "Inquiry" means a question or request for specific information or assistance.

[0742] "Reporting" is the act of providing information about a particular event or situation.

[0743] "Classification" is the process of grouping data or information based on specific criteria.

[0744] "Filtering" is the process of selecting data or information based on specific conditions.

[0745] "Generative AI model" refers to the specific implementation and algorithms of generative AI.

[0746] A "trend" is a movement in data that shows a particular direction or pattern.

[0747] A "pattern" is a recurring structure or regularity in data or events.

[0748] An "emotion engine" is a technology for analyzing and recognizing the emotional state of employees.

[0749] "Emotional information" is data regarding an employee's emotional state.

[0750] A "measure" is a specific action or measure to address a particular problem or issue.

[0751] A "prevention measure" is a specific action or step taken to head off a problem or issue before it occurs.

[0752] "Visualization" is the process of representing data or information visually.

[0753] A "report" is a document that compiles specific information or analytical results.

[0754] "Quick response" refers to the action of quickly dealing with problems or issues.

[0755] "Risk hedging" refers to measures or means for reducing potential risks.

[0756] This invention is a system that proposes measures and preventive measures against harassment by utilizing generative AI and an emotion engine. This system operates mainly with a server, a terminal, and a user.

[0757] Hardware and Software Used

[0758] Hardware: Servers, terminals

[0759] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva)

[0760] Specific operation of the system

[0761] Data collection

[0762] The server collects data on harassment from each department within the company. Specifically, the server accesses the management systems of each department and obtains data such as the frequency, time periods, and types of harassment. For example, the server automatically collects monthly reports and the results of internal investigations.

[0763] Data analysis

[0764] The server inputs the collected data into a generative AI model to analyze harassment trends. Specifically, the server preprocesses the collected data and inputs it into a generative AI model (e.g., GPT-4) using a prompt sentence. For example, the prompt sentence could be, "If harassment is frequent in a specific department, please identify that department."

[0765] Collecting emotional information

[0766] The device collects employees' emotional information using an emotion engine. Specifically, the device analyzes the employee's facial expressions and voice in real time, and the emotion engine (e.g., Affectiva) recognizes the emotional state. For example, the device captures the facial expressions of employees during a meeting with a camera, and the emotion engine analyzes emotions from the facial expressions.

[0767] Emotional information analysis

[0768] The server inputs the emotion information obtained from the emotion engine into the generative AI model and analyzes the correlation between the emotional state and the occurrence of harassment. Specifically, the server inputs the data obtained from the emotion engine into the generative AI model and uses a prompt sentence such as "If a specific emotional state is closely related to the occurrence of harassment, please identify that information." For example, the server identifies departments where emotional states such as "anger" and "anxiety" are frequently observed.

[0769] Proposals for countermeasures and prevention measures

[0770] The server proposes specific measures and prevention measures against harassment based on the analysis results of the generative AI model and the recognition results of the emotion engine. Specifically, the server inputs a prompt to the generative AI model, such as "If harassment is occurring frequently in a specific department, what measures should be proposed for that department?" and plans countermeasures based on the results obtained. For example, the server proposes regular harassment prevention training and counseling for stress management for a specific department.

[0771] Examples

[0772] Example 1: At the beginning of each month, a server accesses each department's management system and automatically downloads the previous month's harassment report.

[0773] Example 2: The report downloaded by the server is input into a generative AI model and analyzed using the prompt, "In which department is harassment most prevalent?"

[0774] Example 3: The device uses a camera to capture the facial expressions of employees during a meeting, and the emotion engine analyzes the facial expressions in real time to determine emotions such as "anger" or "anxiety."

[0775] Example 4: The server inputs the emotion data obtained from the emotion engine into a generative AI model and analyzes it using the prompt, "If a specific emotional state is closely related to the occurrence of harassment, please identify that information."

[0776] Example 5: Based on the analysis results of the generative AI model, the server suggests "harassment prevention training" or "stress management counseling" for a specific department.

[0777] The above is an embodiment of the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0778] Step 1: Data collection

[0779] The server collects data on harassment from each department in the company. Specifically, the server accesses each department's management system and obtains data such as the frequency, time of day, and type of harassment. The input is data from each department's management system, and the output is the collected harassment-related data. For example, the server automatically downloads monthly reports and the results of internal investigations.

[0780] Step 2: Data Preprocessing

[0781] The server preprocesses the collected data. Specifically, it performs tasks such as filling in missing values, detecting and correcting outliers, and normalizing the data. The input is the collected harassment-related data, and the output is the preprocessed data. For example, the server fills in missing values ​​with the average value and detects and corrects outliers.

[0782] Step 3: Data analysis

[0783] The server inputs the preprocessed data into a generative AI model to analyze harassment trends. Specifically, the server inputs the generative AI model (e.g., GPT-4) using a prompt sentence. The inputs are the preprocessed data and the prompt sentence, and the output is the analysis results regarding harassment trends and patterns. For example, the prompt sentence could be, "If harassment occurs frequently in a specific department, please identify that department."

[0784] Step 4: Collecting emotional information

[0785] The device collects employees' emotional information using an emotion engine. Specifically, the device analyzes the employee's facial expressions and voice in real time, and the emotion engine (e.g., Affectiva) recognizes the employee's emotional state. The input is the employee's facial expressions and voice data, and the output is the recognized emotional information. For example, the device uses a camera to capture the facial expressions of employees during a meeting, and the emotion engine analyzes emotions from the facial expressions.

[0786] Step 5: Analyze sentiment information

[0787] The server inputs the emotion information obtained from the emotion engine into the generative AI model and analyzes the correlation between the emotional state and the occurrence of harassment. Specifically, the server inputs the data obtained from the emotion engine into the generative AI model and uses a prompt sentence such as "If a specific emotional state is closely related to the occurrence of harassment, please identify that information." The inputs are the emotion information and the prompt sentence, and the output is the analysis results regarding the correlation between the emotional state and harassment. For example, the server identifies departments where emotional states such as "anger" and "anxiety" are frequently observed.

[0788] Step 6: Proposing countermeasures and preventative measures

[0789] The server proposes specific countermeasures and preventive measures against harassment based on the analysis results of the generative AI model and the recognition results of the emotion engine. Specifically, the server inputs a prompt to the generative AI model, such as "If harassment occurs frequently in a specific department, what countermeasures should be proposed for that department?" and plans countermeasures based on the results obtained. The inputs are the analysis results and the prompt, and the output is the proposed countermeasures and preventive measures. For example, the server might propose regular harassment prevention training or counseling for stress management for a specific department.

[0790] (Application example 3)

[0791] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0792] Conventional harassment prevention systems have difficulty efficiently classifying and quickly responding to inquiries and reports related to harassment within the company. They also have difficulty identifying trends and patterns of harassment and proposing specific countermeasures and preventative measures. In particular, there is a need for early detection and countermeasures of harassment using voice data in communication between employees within factories.

[0793] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0794] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the workplace using generative AI and filtering them according to importance and urgency, a means for enabling a rapid response and leading to risk hedging, a means for converting conversation into text using voice recognition, a means for recognizing the emotional state of the conversation using an emotion engine, a means for analyzing the content of the conversation using generative AI and detecting signs of harassment, and a means for proposing specific countermeasures and preventive measures for the detected signs of harassment. This enables early detection and countermeasures of harassment in communication between employees in a factory.

[0795] "Generative AI" is an artificial intelligence technology that generates new information and content based on data.

[0796] "Speech recognition" is a technology that converts voice data into text data.

[0797] An "emotion engine" is a technology that recognizes emotional states from text and voice.

[0798] "Filtering" is the process of sorting data based on specific criteria.

[0799] "Risk hedging" refers to taking measures to reduce potential risks.

[0800] A "indicator of harassment" is a pattern of behavior or conduct that indicates that harassment may be occurring.

[0801] "Countermeasures and preventive measures" are specific actions or means to prevent the occurrence of harassment.

[0802] "Conversation content analysis" is the process of analyzing text data of a conversation to understand its meaning and intent.

[0803] The system for carrying out the present invention is configured as an application installed on a robot working in a factory. A specific embodiment of the system will be described below.

[0804] System Configuration

[0805] 1. Voice Recognition

[0806] The server uses voice recognition technology to convert conversations in the factory into text data in real time. Specifically, it uses the speech_recognition library.

[0807] 2. Generative AI Models

[0808] The server uses a generative AI model to analyze the text data and detect signs of harassment. To do this, it uses the GPT-3 model from the transformers library.

[0809] 3. Emotion Engine

[0810] The server uses an emotion engine to recognize emotional states from text data. Specifically, it uses the emotion_recognition library.

[0811] 4. Filtering and risk hedging

[0812] The server uses generative AI to automatically categorize harassment-related inquiries and reports, filtering them according to importance and urgency, enabling a rapid response and hedging risks.

[0813] 5. Proposals for countermeasures and preventive measures

[0814] The server uses a generative AI model to suggest specific countermeasures and preventive measures for detected signs of harassment.

[0815] Processing flow

[0816] 1. Acquiring audio data

[0817] The terminal (robot) picks up conversations within the factory through a microphone.

[0818] 2. Converting voice data to text

[0819] The server converts the acquired voice data into text data using the speech_recognition library.

[0820] 3. Recognizing Emotional States

[0821] The server recognizes the emotional state of the text data using the emotion_recognition library.

[0822] 4. Detecting signs of harassment

[0823] The server uses a generative AI model (GPT-3) to analyze text data and detect signs of harassment.

[0824] 5. Proposals for countermeasures and preventive measures

[0825] The server uses a generative AI model to suggest specific countermeasures and preventive measures for detected signs of harassment.

[0826] Examples

[0827] For example, the following conversation might take place in a factory:

[0828] Employee A: "You've been working slow lately. You need to work harder."

[0829] Employee B: "Sorry, I'm not feeling well..."

[0830] This conversation is captured as audio data and input to the program. The server inputs the following prompt sentence into the generative AI model:

[0831] Analyze the following conversation for harassment: "Recently, your work has been slow. You need to work harder." "I'm sorry, I'm not feeling well."

[0832] Based on this prompt, the server analyzes signs of harassment and suggests appropriate countermeasures and preventive measures.

[0833] The flow of the specific process in the application example 3 will be described with reference to FIG.

[0834] Step 1:

[0835] The terminal (robot) picks up conversations in the factory through a microphone. The input is voice data, and the output is the same voice data. This voice data is processed in the next step.

[0836] Step 2:

[0837] The server converts the acquired voice data into text data using the speech_recognition library. The input is voice data, and the output is text data. This conversion allows the voice information to be treated as text information.

[0838] Step 3:

[0839] The server recognizes the emotional state of the text data using the emotion_recognition library. The input is text data, and the output is the emotional state (e.g. anger, sadness, joy, etc.). This processing allows the emotional nuances of the conversation to be understood.

[0840] Step 4:

[0841] The server uses a generative AI model (GPT-3) to analyze text data and detect signs of harassment. The input is text data and emotional state, and the output is the analysis results on signs of harassment. This analysis determines whether the conversation corresponds to harassment.

[0842] Step 5:

[0843] The server uses a generative AI model to propose specific countermeasures and preventive measures for the detected signs of harassment. The input is the analysis results on the signs of harassment, and the output is specific countermeasures and preventive measures. This proposal provides appropriate countermeasures.

[0844] Examples

[0845] For example, the following conversation might take place in a factory:

[0846] Employee A: "You've been working slow lately. You need to work harder."

[0847] Employee B: "Sorry, I'm not feeling well..."

[0848] This conversation is captured as audio data and input to the program. The server inputs the following prompt sentence into the generative AI model:

[0849] Analyze the following conversation for harassment: "Recently, your work has been slow. You need to work harder." "I'm sorry, I'm not feeling well."

[0850] Based on this prompt, the server analyzes signs of harassment and suggests appropriate countermeasures and preventive measures.

[0851] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0852] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0853] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0854] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0855] [Second embodiment]

[0856] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0857] 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.

[0858] 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 wide area network (WAN) and / or a local area network (LAN).

[0859] 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.

[0860] 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 the voice according to instructions from the processor 46.

[0861] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0862] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0863] Fig. 4 shows an example of 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0868] "Example 1"

[0869] One embodiment of the present invention is a system that uses generative AI to automatically classify inquiries and reports related to harassment in the workplace. Specifically, generative AI analyzes text data collected through anonymous reporting channels using chatbots, and automatically classifies content related to harassment. Furthermore, the results can be filtered according to importance and urgency, allowing for rapid response.

[0870] "Example 2"

[0871] Another embodiment of the present invention is a system that uses generative AI to identify trends and patterns of harassment, visualize the data, and generate reports. Specifically, based on the results of the generative AI analysis, the system extracts trends and patterns of harassment and visualizes them. Based on the results, the system automatically generates reports and suggests measures and preventative measures against harassment.

[0872] "Example 3"

[0873] As a further embodiment of the present invention, there is a system that utilizes generative AI to propose measures and preventive measures against harassment. Specifically, the system proposes measures and preventive measures against harassment based on the results of analysis by generative AI. For example, it identifies departments, time periods, and types of harassment where harassment occurs frequently, and proposes specific measures and preventive measures against them.

[0874] The process flow of each embodiment will be described below.

[0875] "Example 1"

[0876] Step 1: Collect text data from an anonymous reporting channel using a chatbot.

[0877] Step 2: Input the collected text data into a generative AI system to automatically classify harassment-related content.

[0878] Step 3: Filter the results of the generative AI's classification according to importance and urgency, and take necessary action quickly.

[0879] "Example 2"

[0880] Step 1: Based on the results of the generative AI analysis, extract trends and patterns of harassment.

[0881] Step 2: Visualize the extracted trends and patterns.

[0882] Step 3: Automatically generate a report based on the visualized results and suggest measures to combat and prevent harassment.

[0883] "Example 3"

[0884] Step 1: Based on the results of the generative AI's analysis, propose countermeasures and preventive measures against harassment.

[0885] Step 2: Identify the departments, times of day, and types of harassment where harassment is most frequent.

[0886] Step 3: Propose specific countermeasures and preventive measures for the identified information.

[0887] Example 1

[0888] Next, a description will be given of Example 1 of Form 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".

[0889] There is a need to efficiently classify inquiries and reports related to harassment within the company and respond quickly according to their importance and urgency. However, traditional manual responses run the risk of delaying the processing of reports or overlooking important reports. It is also difficult to identify trends and patterns of harassment and propose countermeasures and preventive measures. To solve these issues, automatic classification and filtering of reports, rapid response, data visualization and report generation, and proposal of countermeasures and preventive measures are required.

[0890] 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.

[0891] In this invention, the server includes a means for collecting anonymous reports using a chatbot, a means for transmitting collected text data to the server, a means for analyzing the text data using a generative AI model and automatically classifying content related to harassment, a means for filtering the classification results according to importance and urgency, a means for notifying the person in charge of the filtered results, a means for enabling a rapid response and leading to risk hedging, a means for identifying trends and patterns of harassment using generative AI, a means for visualizing data and generating reports, and a means for proposing measures and preventative measures against harassment. This makes it possible to efficiently classify inquiries and reports related to harassment within the company and to respond quickly according to importance and urgency.

[0892] A "chatbot" is software that automates dialogue with users and has the ability to collect and respond to information through text and voice.

[0893] An "anonymous report" is a report made without revealing the reporter's identity, providing a means of providing information while protecting privacy.

[0894] "Text data" is information expressed as a character string, and includes the contents of reports and inquiries.

[0895] A "server" is a computer system that processes and stores data on a network, and provides services in response to requests from clients.

[0896] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to analyze data and automatically perform specific tasks.

[0897] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[0898] Classification is the process of separating data into specific categories or groups, grouping data that share common characteristics.

[0899] "Filtering" is the process of sorting through data based on specific criteria to extract only the information you need.

[0900] A "notification" is a means of informing relevant parties of specific information, and is done via email, dashboard, etc.

[0901] "Rapid response" refers to dealing with a problem quickly when it occurs, and is an action taken to minimize risk.

[0902] "Risk hedging" is the process of predicting potential risks and taking measures to reduce the impact of those risks.

[0903] A "trend" refers to a general movement or pattern of data or events moving in a particular direction.

[0904] A "pattern" refers to a repeating structure or arrangement in data or events.

[0905] "Visualization" is the process of making information easier to understand intuitively by representing data visually.

[0906] A "report" is a document that compiles information on a particular topic and includes analytical findings and recommendations.

[0907] A "measure" refers to a specific action or plan to address a particular problem.

[0908] "Preventive measures" refer to measures or actions taken to prevent problems before they occur.

[0909] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0910] This invention is a system that uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is described below.

[0911] Hardware and Software Used

[0912] The system uses the following hardware and software:

[0913] Server: A computer system that processes and stores data, and also serves as the execution environment for generative AI models.

[0914] Device: The device used by the user (PC, smartphone, tablet, etc.).

[0915] Chatbot: Software that automates conversations with users. It runs on communication tools such as Slack and Microsoft Teams.

[0916] Generative AI model: An algorithm that analyzes text data and performs specific tasks automatically, such as OpenAI's GPT-4.

[0917] Data processing and calculation

[0918] This system performs the following data processing and calculations.

[0919] 1. Collect reports: Users anonymously report harassment through the chatbot. For example, a user may report, “My boss yells at me every day.”

[0920] 2. Data transmission: The terminal transmits the text data collected through the chatbot to the server, which temporarily stores the received text data.

[0921] 3. Text Analysis and Classification: The server inputs the stored text data into the generative AI model, which analyzes the text data using the following prompt sentence:

[0922] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[0923] The generative AI model analyzes text data and classifies it as "power harassment."

[0924] 4. Filtering of classification results: The server evaluates the importance and urgency of reports based on the classification results obtained from the generative AI model. For example, reports classified as "power harassment" are deemed to be of high importance. The server filters reports taking into account their content, frequency, and the strength of the words used.

[0925] 5. Notify the person in charge: The server notifies the person in charge based on the filtered results. The notification is done, for example, via email or a dedicated management dashboard. The person in charge can receive the notification and take the necessary action promptly.

[0926] Examples

[0927] As a concrete example, consider the following scenario.

[0928] scenario:

[0929] A user anonymously reports to a chatbot on Slack, "My boss yells at me every day." This report is sent to a server and analyzed by a generative AI model.

[0930] Example prompt:

[0931] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[0932] The generative AI model receives this prompt and classifies the report as "power harassment." The server then determines the importance of the report as "high" based on this classification and notifies the person in charge by email.

[0933] The above is a specific embodiment for carrying out the present invention.

[0934] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0935] Step 1:

[0936] A user anonymously reports harassment through the chatbot. For example, a user reports, "My boss yells at me every day." This report becomes input data. The chatbot receives this text data and saves the report.

[0937] Step 2:

[0938] The terminal transmits the text data collected through the chatbot to the server. The input data is the text data reported by the user. The server temporarily stores the received text data. Specifically, it stores it in a database.

[0939] Step 3:

[0940] The server inputs the stored text data into the generative AI model. The input data is the stored text data. The generative AI model parses the text data using the following prompt sentence:

[0941] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[0942] The generative AI model analyzes the text data and classifies it as "power harassment." The output data is the classification result.

[0943] Step 4:

[0944] The server evaluates the importance and urgency of reports based on the classification results obtained from the generative AI model. The input data is the classification results from the generative AI model. The server filters the reports taking into account their content, frequency, and the strength of the words used. The output data is the filtered results.

[0945] Step 5:

[0946] The server notifies the person in charge based on the filtered results. The input data is the filtered results. The notification is sent, for example, via email or a dedicated management dashboard. The output data is the notification content. The person in charge can receive the notification and take the necessary action promptly.

[0947] The above is the specific flow of the program processing of this system.

[0948] (Application example 1)

[0949] Next, a description will be given of Application Example 1 of Form 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".

[0950] In conventional harassment reporting systems, classification of reports and judgment of their importance were often done manually, making it difficult to respond quickly. In addition, there was a lack of a mechanism to properly filter important reports and notify the person in charge immediately while ensuring anonymity. This created a risk of delaying the early detection and countermeasures of harassment.

[0951] 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.

[0952] In this invention, the server includes a means for automatically classifying inquiries and reports related to workplace harassment using generative AI and filtering them according to importance and urgency, a means for analyzing text data collected through anonymous reporting channels, and a means for immediately notifying the person in charge when an important report is received. This enables a quick response and leads to risk hedging.

[0953] "Generative AI" is an artificial intelligence technology that generates new data and information based on input information such as text data and image data.

[0954] "Workplace harassment" refers to inappropriate behavior such as harassment, bullying, and discrimination that occurs in the workplace.

[0955] An "inquiry or report" refers to an employee communicating an issue or question about harassment to the company.

[0956] "Automatic classification" refers to the process in which generative AI analyzes input data and automatically classifies it based on specific categories or importance.

[0957] "Filtering based on importance and urgency" refers to the process of selecting data classified by generative AI based on its importance and urgency.

[0958] "Anonymous reporting channel" means a means of communication through which a report of harassment may be made without revealing the reporter's identity.

[0959] "Text data" refers to data expressed as character information.

[0960] "Analyze" refers to the process in which generative AI examines the input data in detail to understand and classify its contents.

[0961] "Immediate notification to responsible parties" refers to the process of immediately notifying designated responsible parties when important reports are received.

[0962] "Prompt response" refers to taking appropriate measures without delay when a problem occurs.

[0963] "Risk hedging" refers to minimizing risks by detecting potential risks in advance and taking measures to address them.

[0964] The system for implementing this invention uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is described below.

[0965] System Configuration

[0966] The system consists of the following main components:

[0967] 1. Server: Runs the generative AI model to analyze and classify text data.

[0968] 2. Device: The device (e.g., smartphone) through which a user reports harassment via the anonymous reporting channel.

[0969] 3. Notification system: Immediately notify the responsible person when there is an important report.

[0970] Hardware and software used

[0971] Hardware: Smartphones, servers

[0972] Software: Python, OpenAI API

[0973] Data processing and calculation

[0974] 1. Text data collection

[0975] Users can use their smartphones to access the anonymous reporting channel and report on harassment. The report content is sent to the server as text data.

[0976] 2. Generative AI analysis

[0977] The server analyzes the collected text data using the OpenAI API, and inputs the text data into the generative AI model using the following prompt:

[0978] Example prompt:

[0979] Analyze the text below and classify the content as harassment related.

[0980] Text: My boss keeps harassing me. Please help.

[0981] Classification results:

[0982] The generative AI model analyzes the text data based on this prompt and classifies the content as harassment-related.

[0983] 3. Filtering and Notifications

[0984] The server determines the importance and urgency of the report based on the analysis results obtained from the generative AI model. If an important report is received, the person in charge is notified immediately via the notification system.

[0985] Examples

[0986] For example, if a user reports, "My boss continues to harass me. Please help me," the server inputs this text data into a generative AI model, and obtains the classification result as "This report is important. My boss continues to harass me, so urgent action is required." Based on this result, the server immediately notifies the person in charge, enabling a prompt response.

[0987] In this way, a harassment reporting system using generative AI can enable quick and appropriate responses, helping to hedge risks.

[0988] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0989] Step 1:

[0990] A user accesses the anonymous reporting channel using a smartphone to report harassment. The input is text data entered by the user. The output is text data sent to the server.

[0991] Step 2:

[0992] The server inputs the received text data into the generative AI model. Specifically, it analyzes the text data using the following prompt sentence. The input is the text data sent by the user. The output is the analysis result by the generative AI model.

[0993] Example prompt:

[0994] Analyze the text below and classify the content as harassment related.

[0995] Text: My boss keeps harassing me. Please help.

[0996] Classification results:

[0997] Step 3:

[0998] The server judges the importance and urgency of the report content based on the analysis results obtained from the generative AI model. The input is the analysis results of the generative AI model. The output is the filtering results according to the importance and urgency.

[0999] Step 4:

[1000] The server immediately notifies the person in charge through the notification system when there is an important report based on the filtering result. The input is the filtering result. The output is the notification to the person in charge.

[1001] Step 5:

[1002] The person in charge receives the notification and takes prompt action. The input is the notification from the server. The output is the implementation of the action.

[1003] In this way, a harassment reporting system using generative AI can enable quick and appropriate responses, helping to hedge risks.

[1004] Example 2

[1005] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1006] With conventional harassment prevention systems, it was difficult to efficiently classify inquiries and reports related to harassment within the company and quickly respond to them according to their importance and urgency. It was also difficult to identify trends and patterns of harassment and propose countermeasures and preventative measures based on them. This led to problems such as the inability to properly manage the risk of harassment and delays in improving the working environment within the company.

[1007] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for collecting data from a database, a means for preprocessing the collected data, a means for analyzing data using a generative AI model and identifying trends and patterns of harassment, a means for visualizing the analysis results, and a means for automatically generating a report based on the visualized data. This makes it possible to efficiently identify trends and patterns of harassment, and to propose rapid responses and appropriate countermeasures and preventive measures.

[1008] "Generative AI" is a system that uses artificial intelligence technology to generate, analyze, and classify data.

[1009] A "database" is a system for efficiently storing, managing, and searching data.

[1010] "Preprocessing" refers to the initial process of preparing data for analysis, and specifically includes data cleaning and tokenization.

[1011] A "generative AI model" is a part of generative AI, an algorithm that analyzes data and generates results based on specific prompts.

[1012] A "prompt sentence" is an input sentence that gives specific instructions or questions to a generative AI model.

[1013] "Visualization" refers to the display of data analysis results in a visual format such as a graph or chart.

[1014] A "report" is a written summary of data analysis results and recommendations.

[1015] "Harassment" refers to inappropriate behavior or remarks towards others in the workplace or any other environment.

[1016] "Inquiry" means a question or request made for specific information or assistance.

[1017] A "report" is a written or oral communication providing information about a particular event or situation.

[1018] "Classification" means grouping data based on specific criteria.

[1019] "Filtering" means selecting data based on specific conditions.

[1020] A "trend" refers to a recurring pattern or trend in data.

[1021] A "pattern" is a collection of elements in data that have a certain regularity or commonality.

[1022] A "measure" is a specific action or plan to address a particular problem.

[1023] A "prevention" is a specific action or plan to prevent a problem before it occurs.

[1024] This invention is a system that uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to importance and urgency. It also collects data from a database, pre-processes it, and uses a generative AI model to analyze the data and identify trends and patterns of harassment. It visualizes the analysis results and automatically generates reports to suggest countermeasures and preventive measures against harassment.

[1025] Hardware and Software Used

[1026] Hardware:

[1027] Server: Database server (e.g. MySQL)

[1028] Terminal: A computer used to view data and review reports.

[1029] software:

[1030] Database Management System: MySQL

[1031] Natural Language Processing Libraries: NLTK, spaCy

[1032] Generative AI model: GPT-4

[1033] Data visualization tools: Tableau, Matplotlib

[1034] Report generation tools: LaTeX, Microsoft Word

[1035] Explanation of program processing

[1036] Data collection:

[1037] The server collects data such as chat logs, emails, and survey results within the company. Specifically, it connects to the database server and retrieves the required data with a query. For example, execute the query "SELECT FROM chat_logs WHERE date BETWEEN '2023-01-01' AND '2023-01-31'" to retrieve chat logs for January.

[1038] Data preprocessing:

[1039] The server preprocesses the collected data. Specifically, it cleans the text data (removes unnecessary characters and spaces) and tokenizes it (splits it into words and phrases). The preprocessed data is temporarily stored on the terminal. For example, the cleaned text data is saved as a CSV file.

[1040] Analysis by generative AI models:

[1041] The server inputs the preprocessed data into a generative AI model (GPT-4) to analyze harassment trends and patterns. The prompt text to be input into the generative AI model is created by the user. For example, the prompt text "Please identify the harassment trends from the following chat logs" is used.

[1042] Data Visualization:

[1043] The server visualizes harassment trends and patterns based on the results of the generative AI model's analysis. Specifically, it uses Matplotlib to create graphs and display bar graphs showing the time periods when certain keywords frequently appear. The visualized data is then displayed on the terminal.

[1044] Generate report:

[1045] The server automatically generates a "January Harassment Trend Report" using LaTeX based on the visualized data and saves it in PDF format. Users can check the generated report and make corrections or additional comments as necessary.

[1046] Examples of concrete examples and prompts

[1047] Examples:

[1048] Identify the times and departments in which specific keywords (e.g. "harassment" or "ignoring") appear frequently from company chat logs.

[1049] From the survey results, the names of departments and superiors with the most reports of harassment will be extracted.

[1050] Example prompt:

[1051] Please identify harassment trends from the chat logs below. In particular, please extract frequently occurring keywords and the time periods in which they occurred.

[1052] "Based on the results of this survey, please identify departments with a high number of harassment reports and analyze the causes."

[1053] The above is an embodiment of the present invention.

[1054] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1055] Step 1: Data collection

[1056] The server collects data such as chat logs, emails, and survey results within the company. Specifically, it connects to a database server and retrieves the required data with a query. For example, execute the query "SELECT FROM chat_logs WHERE date BETWEEN '2023-01-01' AND '2023-01-31'" to retrieve chat logs for January. The input is the database query, and the output is the collected raw data.

[1057] Step 2: Data Preprocessing

[1058] The server preprocesses the collected data. Specifically, it cleans the text data (removes unnecessary characters and spaces) and tokenizes it (splits it into words and phrases). The preprocessed data is temporarily stored on the terminal. For example, the cleaned text data is saved as a CSV file. The input is the collected raw data, and the output is the preprocessed clean data.

[1059] Step 3: Analysis by generative AI model

[1060] The server inputs the preprocessed data into a generative AI model (GPT-4) to analyze harassment trends and patterns. The user creates a prompt to input to the generative AI model. For example, the prompt could be, "Please identify the harassment trends from the chat logs below." The input is the preprocessed data and the prompt, and the output is the analysis results by the generative AI model.

[1061] Step 4: Visualize the data

[1062] The server visualizes harassment trends and patterns based on the results of the generative AI model's analysis. Specifically, it uses Matplotlib to create graphs, and displays time periods when specific keywords frequently appear as bar graphs. The visualized data is displayed on the terminal. The input is the analysis results from the generative AI model, and the output is the visualized graph or chart.

[1063] Step 5: Generate reports

[1064] The server automatically generates a "January Harassment Trend Report" using LaTeX based on the visualized data and saves it in PDF format. The user checks the generated report and makes corrections or additional comments as necessary. The input is the visualized data, and the output is the automatically generated report.

[1065] (Application example 2)

[1066] Next, a description will be given of Application Example 2 of Form 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".

[1067] Conventional harassment prevention systems make it difficult to efficiently classify inquiries and reports related to harassment within the company and respond quickly according to their importance and urgency. It is also time-consuming to identify trends and patterns of harassment, visualize them, and generate reports. Furthermore, there is a lack of functionality to suggest specific countermeasures and preventive measures, which makes it difficult to take effective measures against harassment.

[1068] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for identifying trends and patterns of harassment using generative AI, a means for visualizing data and generating reports, a means for proposing measures and preventive measures against harassment, a means for collecting text data such as reports, chat logs, and emails from users through an application installed on a smartphone, a means for identifying trends and patterns of harassment from the collected data using a generative AI model, a means for visualizing the analysis results in graphs and charts, and a means for automatically generating a report based on the analysis results and proposing specific measures and preventive measures. This makes it possible to efficiently classify inquiries and reports related to harassment and to quickly respond to them, and to identify and visualize trends and patterns of harassment and propose specific measures and preventive measures.

[1069] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[1070] "Harassment" refers to inappropriate language or behavior toward others in the workplace or any other environment.

[1071] "Inquiry" means a question or request for specific information or assistance.

[1072] "Reporting" refers to the act of providing information about a particular event or situation.

[1073] "Classification" refers to the grouping of data or information based on specific criteria.

[1074] "Filtering" refers to selecting data or information based on specific conditions.

[1075] A "trend" refers to a movement or flow toward a particular direction or pattern.

[1076] A "pattern" refers to a particular repeated form or arrangement.

[1077] "Visualization" refers to the visual representation of data or information.

[1078] "Report" means a document that compiles specific information or analytical results.

[1079] A "measure" refers to a specific action or measure to address a particular problem or issue.

[1080] "Preventive measures" refer to specific actions or steps taken to head off problems or issues before they occur.

[1081] A "smartphone" refers to a type of mobile phone that can connect to the Internet and use applications.

[1082] "Application" refers to a software program designed to provide a specific function or service.

[1083] "Chat log" refers to a record of conversations held in chat format.

[1084] "Email" refers to messages sent and received electronically.

[1085] "Data collection" refers to the act of gathering data for a specific purpose.

[1086] A "graph" refers to a diagram for visually representing data.

[1087] A "chart" refers to a table or diagram that visually represents data.

[1088] The system for implementing this invention uses generative AI to automatically classify inquiries and reports related to harassment in the workplace and filter them according to importance and urgency. It also uses generative AI to identify trends and patterns of harassment, visualize the data, and generate reports. It also has the ability to suggest countermeasures and preventative measures against harassment.

[1089] Hardware and Software Used

[1090] Hardware: Smartphones, servers

[1091] Software: Python, OpenAI API, Matplotlib, Pandas

[1092] Data processing and calculation

[1093] Data collection

[1094] Users input text data such as reports of harassment, chat logs, and emails through an application installed on their smartphones. This data is sent to a server and stored in a database.

[1095] AI analysis

[1096] The server inputs the collected data into a generative AI model (e.g., GPT-3) to identify trends and patterns of harassment, using prompts such as the following:

[1097] Examples of prompt statements

[1098] Identify trends and patterns of harassment in the text data below.

[1099] Text: My boss is nasty to me every day

[1100] Text: Colleagues ignoring me

[1101] Data Visualization

[1102] Based on the analysis results obtained from the generative AI model, the server uses Pandas and Matplotlib to visualize the data in graphs and charts, allowing users to visually confirm trends and patterns of harassment.

[1103] Report Generation

[1104] The server automatically generates a report based on the analysis results, which includes trends and patterns of harassment, as well as specific countermeasures and preventative measures, and outputs the report as a text file that users can download.

[1105] Examples

[1106] For example, if a user reports that "my boss is nasty every day," the generative AI model will identify the pattern of "nasty." Based on this information, the server will generate a graph showing that there are many reports of nasty behavior and suggest measures such as "regular counseling" in the report.

[1107] In this way, the invention is able to efficiently categorize and rapidly respond to harassment-related inquiries and reports, identify and visualize harassment trends and patterns, and suggest specific countermeasures and preventative measures.

[1108] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1109] Step 1:

[1110] Users input text data such as reports of harassment, chat logs, and emails through an application installed on their smartphones. The input data is then sent to a server by the application. The input data includes the specific details of the harassment, as well as the date and time.

[1111] Step 2:

[1112] The server saves the received text data in a database. At this time, it checks the format and content of the data and converts it into an appropriate format. For example, it converts the text data into JSON format and saves it.

[1113] Step 3:

[1114] The server inputs the stored text data into a generative AI model. The generative AI model (e.g., GPT-3) analyzes the data based on the prompt text and identifies harassment trends and patterns. Examples of prompt text are as follows:

[1115] Examples of prompt statements

[1116] Identify trends and patterns of harassment in the text data below.

[1117] Text: My boss is nasty to me every day

[1118] Text: Colleagues ignoring me

[1119] Step 4:

[1120] The server receives the analysis results from the generative AI model and stores them in a database, including any identified harassment trends or patterns.

[1121] Step 5:

[1122] The server visualizes the data based on the analysis results. It uses Pandas and Matplotlib to represent the analysis results in graphs and charts. For example, it generates a bar graph showing the high number of reports of sarcasm.

[1123] Step 6:

[1124] The server automatically generates reports based on the visualized data. The reports include trends and patterns of harassment, as well as specific countermeasures and preventative measures. The generated reports are output as text files.

[1125] Step 7:

[1126] Users can download and view the generated report through a smartphone application, which includes specific measures such as "regular counseling."

[1127] In this way, the system will be able to efficiently categorize and quickly respond to harassment-related inquiries and reports, identify and visualize harassment trends and patterns, and suggest specific countermeasures and preventive measures.

[1128] Example 3

[1129] Next, a third embodiment of the third embodiment will be described. 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".

[1130] In conventional harassment prevention systems, classification of harassment reports and inquiries, filtering of importance and urgency, and proposal of specific countermeasures and preventive measures are often done manually, making it difficult to respond quickly.In addition, there was a lack of means to identify trends and patterns of harassment and visualize the data, making it difficult to take effective measures.

[1131] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1132] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment within the company using generative AI and filtering them according to importance and urgency, a means for collecting data on harassment from each department within the company, a means for preprocessing the collected data and completing missing values ​​and correcting abnormal values, a means for inputting the preprocessed data into a generative AI model and identifying departments, time periods, and types of harassment with high frequency, a means for proposing specific countermeasures and preventive measures based on the analysis results of the generative AI model, and a means for notifying the user of the proposed contents. This enables rapid classification and filtering of harassment reports and inquiries, and allows for the proposal of effective countermeasures and preventive measures.

[1133] "Generative AI" is an artificial intelligence technology that generates new information and suggestions based on data.

[1134] "Harassment" refers to inappropriate verbal or physical actions taken against others in the workplace or in society, and is an act that causes mental or physical pain.

[1135] "Inquiry" means a question or inquiry made to request specific information or advice.

[1136] "Report" means a formal notification or recording made to convey information about a particular event or situation.

[1137] "Classification" refers to the grouping of collected data or information based on specific criteria.

[1138] "Filtering" refers to sorting data or information based on specific criteria and extracting only what is needed.

[1139] "Data collection" refers to the act of gathering information or data needed for a specific purpose.

[1140] "Preprocessing" refers to the process of preparing data for analysis by performing operations such as filling in missing values ​​and correcting outliers before conducting data analysis.

[1141] A "generative AI model" is a specific implementation of generative AI, and refers to algorithms and programs for generating new information and suggestions based on data.

[1142] "Analysis" refers to the act of analyzing collected data to find specific patterns or trends.

[1143] "Countermeasures" refers to specific actions or measures taken in response to a particular problem or issue.

[1144] "Preventive measures" refer to specific actions or steps taken to prevent a particular problem or issue before it occurs.

[1145] "Notice" means a formal communication or notification made to convey specific information or proposals to interested parties.

[1146] This invention is a system that uses generative AI to propose measures and preventive measures against harassment. A specific embodiment of this system is shown below.

[1147] The server first collects data on harassment from each department in the company, including the number of reported cases, the time of occurrence, the location of occurrence, the type of harassment, etc. For example, it collects report data from the sales department and survey results.

[1148] The server then preprocesses the collected data by completing missing values, detecting and correcting outliers, and standardizing the data and converting it into a format suitable for generative AI models, such as converting text data into numerical data.

[1149] The server inputs the preprocessed data into a generative AI model (for example, OpenAI's GPT-4) and performs analysis. The generative AI model analyzes the data and identifies departments, time periods, and types of harassment that occur frequently. For example, it identifies that harassment occurs frequently in the sales department between 3:00 and 5:00 p.m.

[1150] The server then uses the results of the generative AI model's analysis to suggest specific countermeasures and preventative measures, such as providing harassment prevention training to the sales department and strengthening monitoring between 3:00 and 5:00 p.m.

[1151] Finally, the server notifies the user of the proposed content. Specifically, it sends the content to the relevant parties via email or the company's internal messaging system. For example, it notifies the sales department manager that harassment prevention training should be conducted.

[1152] As a concrete example, consider the following scenario.

[1153] scenario:

[1154] Data was collected showing that harassment reports were more frequent during a certain time period (3:00 to 5:00 pm) in the sales department of a certain company. Based on this data, a generative AI model analyzes and proposes countermeasures.

[1155] Example prompt:

[1156] "There have been many reports of harassment in the sales department between 3:00 and 5:00 p.m. Please suggest measures and preventative measures for harassment during this time period."

[1157] Example output of a generative AI model:

[1158] "To combat harassment between the hours of 3pm and 5pm, here are some suggestions:

[1159] 1. Strengthen surveillance during this time period.

[1160] 2. Conduct harassment prevention training for all employees in the sales department.

[1161] 3. Improve the harassment reporting system and allow anonymous reporting.

[1162] 4. Make adjustments to reduce work load during this time.”

[1163] In this way, the server utilizes the generative AI model to provide a system that proposes measures and preventive measures against harassment and notifies the user. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1164] Step 1:

[1165] The server collects data on harassment from each department within the company. The inputs are the databases and survey results of each department. In concrete terms, the server accesses the databases of each department and obtains report data such as "October 1, 2023, 3:00 p.m., Sales department, verbal violence." The output is the collected harassment data.

[1166] Step 2:

[1167] The server preprocesses the collected data. As input, there is the harassment data collected in step 1. Specifically, the server complements missing values ​​in the data, detects and corrects outliers, and standardizes the data and converts it into a format suitable for the generative AI model. For example, for data where the "occurrence time" is missing, it complements the average occurrence time. As output, the preprocessed data is obtained.

[1168] Step 3:

[1169] The server inputs the preprocessed data into a generative AI model and performs analysis. The input is the data preprocessed in step 2. Specifically, the server inputs the data into a generative AI model (for example, OpenAI's GPT-4) and identifies departments, time periods, and types of harassment where harassment occurs frequently. For example, it identifies a pattern that "verbal abuse frequently occurs in the sales department between 3:00 and 5:00 p.m." The output is the analysis results.

[1170] Step 4:

[1171] The server proposes specific countermeasures and preventive measures based on the analysis results of the generative AI model. The input is the analysis results obtained in step 3. As specific actions, the server proposes to the sales department to "strengthen the monitoring system between 3:00 and 5:00 pm" and "conduct training to prevent harassment." The proposals are obtained as output.

[1172] Step 5:

[1173] The server notifies the user of the proposal. The input is the proposal obtained in step 4. In concrete terms, the server sends the proposal to the relevant parties via email or the internal messaging system. For example, it sends an email to the manager of the sales department saying, "Please consider strengthening the monitoring system between 3:00 and 5:00 p.m." The output is that the notification has been completed.

[1174] (Application example 3)

[1175] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1176] In conventional harassment prevention systems, reporting and analysis of harassment was often done manually, making it difficult to respond quickly. In addition, data analysis to identify trends and patterns of harassment was insufficient, making it difficult to propose specific countermeasures and preventive measures. Furthermore, the system lacked the ability to detect high-risk situations of harassment in real time and send appropriate alerts, making it difficult to effectively hedge risks.

[1177] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using a generative AI and filtering them according to importance and urgency, a means for analyzing the report contents using a generative AI model and identifying the frequency, type, location, and time of harassment, a means for proposing specific harassment countermeasures and preventive measures based on the analysis results, and a means for detecting high-risk situations of harassment in real time and sending an alert to the user. This makes it possible to quickly respond to harassment, identify trends and patterns, propose specific countermeasures and preventive measures, and detect risks in real time and send alerts.

[1178] "Generative AI" is a type of artificial intelligence technology, a system that has the ability to generate new data and information based on input data.

[1179] "Inquiry" means a question or request for specific information or assistance.

[1180] A "report" is a written or oral communication made to provide information about a particular event or situation.

[1181] "Classification" is the process of grouping data or information based on specific criteria.

[1182] "Filtering" is the process of selecting data or information based on specific conditions and removing unnecessary information.

[1183] A "generative AI model" is a specific implementation of generative AI, an artificial intelligence model trained to perform a specific task.

[1184] "Analysis" is the process of examining data or information in detail to identify certain patterns or trends.

[1185] "Frequency" refers to the number of times or the rate at which a particular event or situation occurs.

[1186] A "type" is a category that is classified based on a particular characteristic or property.

[1187] "Location" refers to the physical location or environment in which a particular event or situation occurs.

[1188] A "time period" is a specific division or range of time.

[1189] A "countermeasure" is a specific action or measure to address a particular problem or risk.

[1190] A "prevention measure" is a specific action or measure taken to prevent a particular problem or risk before it occurs.

[1191] "Real-time" refers to immediate processing or response without delay.

[1192] An "alert" is a notification or warning intended to draw attention to a particular situation or risk.

[1193] As an embodiment of the present invention, the following system configuration and processing procedure will be described.

[1194] System Configuration

[1195] The system consists of the following main components:

[1196] 1. Server: Runs the generative AI model, analyzes harassment reports, suggests countermeasures and prevention measures, and sends real-time alerts.

[1197] 2. Terminal: The device on which a user enters a harassment report and receives analysis results and countermeasures / prevention measures. This applies to smartphones and computers.

[1198] 3. Network: A communications infrastructure that connects servers and terminals and transmits and receives data.

[1199] Hardware and software used

[1200] Hardware: Servers, smartphones, PCs

[1201] Software: OpenAI API, Python, Database Management System (e.g. MySQL)

[1202] Data processing and calculation

[1203] 1. Fill out a harassment report:

[1204] Users use the device to input reports of harassment using text, voice, images, etc.

[1205] The entered data is sent to the server and stored in a database.

[1206] 2. Analysis using generative AI models:

[1207] The server analyzes the reports using OpenAI's generative AI models (e.g. GPT-4).

[1208] The results of the analysis will include identifying the frequency, type, location, and time of occurrence of harassment.

[1209] 3. Suggested measures and prevention:

[1210] Based on the analysis results, the server uses a generative AI model to propose specific countermeasures and preventive measures.

[1211] The suggestions are sent to the device and notified to the user.

[1212] 4. Real-time alerts:

[1213] The server detects high risk situations of harassment in real time and sends alerts to users.

[1214] The alert will be displayed on the device to alert the user.

[1215] Examples

[1216] Examples of Harassment Reports

[1217] Report: "The sales department continues to receive excessive scolding from their superiors every Friday afternoon."

[1218] Example of analysis results

[1219] Analysis: "Sales department, Friday afternoon, scolding from boss"

[1220] Examples of proposed countermeasures and preventive measures

[1221] Countermeasures and prevention measures: "The sales department sent out a warning message on Friday afternoon. We conducted harassment prevention training for superiors."

[1222] Examples of prompt statements

[1223] Analysis prompt: "Analyze the following harassment reports to determine frequency, type, location, and time of day.\nReport: {report}"

[1224] Prompt for suggesting measures: "Please suggest specific measures and preventative measures against harassment based on the following analysis results.\nAnalysis results: {analysis}"

[1225] The above is an embodiment of the present invention. This system allows for rapid response to harassment, identification of trends and patterns, proposal of specific countermeasures and preventative measures, and real-time risk detection and alert sending.

[1226] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1227] Step 1:

[1228] Users use the device to input reports of harassment. Input can be done in the form of text, voice, image, etc. The input data is sent from the device to a server and stored in a database. Input data includes details of the harassment, the location where it occurred, the time of day, etc.

[1229] Step 2:

[1230] The server retrieves the report data from the database and analyzes the report contents using a generative AI model (e.g., GPT-4). Specifically, the report contents are input as prompts into the generative AI model to identify the frequency, type, location, time of day, etc. of harassment. The input data is the report contents, and the output data is the analysis results.

[1231] Step 3:

[1232] Based on the analysis results, the server uses a generative AI model to propose specific countermeasures and preventive measures. Using a prompt sentence, the server inputs the analysis results into the generative AI model to obtain suggested countermeasures and preventive measures. The input data is the analysis results, and the output data is the suggested countermeasures and preventive measures.

[1233] Step 4:

[1234] The server sends the proposed countermeasures and preventive measures to the terminal and notifies the user. The user can check the proposed countermeasures and preventive measures through the terminal and take necessary actions. The input data is the proposed countermeasures and preventive measures, and the output data is the notification to the user.

[1235] Step 5:

[1236] The server continuously monitors data to detect situations with a high risk of harassment in real time. If a high-risk situation is detected, the server generates an alert in real time and sends it to the terminal. The user receives the alert through the terminal and takes appropriate action. The input data is the real-time monitoring data, and the output data is the alert.

[1237] These are the specific processing steps of this system. The specific actions taken at each step enable rapid response to harassment, identification of trends and patterns, proposal of specific countermeasures and preventive measures, and real-time risk detection and alert sending.

[1238] In addition, 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.

[1239] "Example 1"

[1240] One embodiment of the present invention is a system that combines a generative AI and an emotion engine. This system collects text data from users, and the generative AI analyzes the data. As a result of the analysis, harassment-related content is automatically classified and filtered according to importance and urgency. Furthermore, the emotion engine recognizes the user's emotions and incorporates that information into the generative AI's analysis. Specifically, the emotion engine recognizes the user's emotional state (anger, fear, sadness, etc.) when making a report, and the generative AI uses that information for analysis. This makes it possible to more accurately determine the severity and urgency of harassment.

[1241] "Example 2"

[1242] Another embodiment of the present invention is a system that combines a generative AI and an emotion engine to identify trends and patterns of harassment. In this system, the results of the analysis by the generative AI are combined with the emotional information recognized by the emotion engine to identify trends and patterns of harassment. Specifically, if a specific emotional state is determined to be closely related to the occurrence of harassment, that information is used to identify trends and patterns of harassment. This makes it possible to more effectively plan preventive measures against harassment.

[1243] "Example 3"

[1244] As a further embodiment of the present invention, there is a system that combines a generative AI and an emotion engine to propose countermeasures and preventive measures against harassment. In this system, the results of the analysis by the generative AI are combined with the emotional information recognized by the emotion engine to propose countermeasures and preventive measures against harassment. Specifically, if a specific emotional state is determined to be closely related to the occurrence of harassment, that information is used to propose countermeasures and preventive measures against harassment. This makes it possible to plan preventive measures against harassment more effectively.

[1245] The process flow of each embodiment will be described below.

[1246] "Example 1"

[1247] Step 1: Collect text data from users.

[1248] Step 2: Generative AI analyzes the text data and automatically classifies content related to harassment.

[1249] Step 3: Filter the classified content according to importance and urgency.

[1250] Step 4: The emotion engine recognizes the user's emotion.

[1251] Step 5: Incorporate the recognized emotion information into the generative AI analysis.

[1252] "Example 2"

[1253] Step 1: Collect text data from users.

[1254] Step 2: Generative AI analyzes the text data and automatically classifies content related to harassment.

[1255] Step 3: The emotion engine recognizes the user's emotion.

[1256] Step 4: Combine the recognized emotional information with the results of generative AI analysis to identify harassment trends and patterns.

[1257] "Example 3"

[1258] Step 1: Collect text data from users.

[1259] Step 2: Generative AI analyzes the text data and automatically classifies content related to harassment.

[1260] Step 3: The emotion engine recognizes the user's emotion.

[1261] Step 4: Combine the recognized emotional information with the results of generative AI analysis to propose countermeasures and preventative measures against harassment.

[1262] Example 1

[1263] Next, a description will be given of Example 1 of Form 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".

[1264] In conventional harassment reporting systems, classification of report contents and judgment of urgency are often done manually, which makes it difficult to respond quickly. In addition, because the report contents are processed without considering the emotional state of the user, it is difficult to accurately judge the seriousness of the harassment. Furthermore, there is a lack of systems that can take appropriate action while ensuring anonymity.

[1265] 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.

[1266] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using a generative AI, a means for filtering according to importance and urgency, a means for enabling a rapid response and leading to risk hedging, a means for recognizing the emotional state of a user using an emotion engine and incorporating the information into the generative AI analysis, a means for collecting text data through an anonymous reporting channel using a chatbot, a means for transmitting the collected text data to the server in real time, and a means for notifying an appropriate person in charge based on the results of the generative AI analysis. This makes it possible to quickly and accurately process reports related to harassment and respond in consideration of the emotional state of the user.

[1267] "Generative AI" is artificial intelligence that uses natural language processing technology to analyze text data and generate information for specific purposes.

[1268] An "emotion engine" is software that recognizes a user's emotional state (e.g., anger, fear, sadness, etc.) from text data and provides that information.

[1269] A "chatbot" is an automated response system that communicates with users in a dialogue format to collect specific information.

[1270] An "anonymous reporting channel" is a means of communication that allows users to report information without revealing their identity.

[1271] "Text data" refers to character information entered by a user, and is data that includes the contents of a report or inquiry.

[1272] "Classification" is the process of dividing collected text data into categories based on specific criteria.

[1273] "Filtering" is the process of selecting classified data according to its importance or urgency.

[1274] "Prompt response" means taking prompt and appropriate action based on the contents of the report.

[1275] "Risk hedging" refers to detecting potential risks in advance and taking measures to minimize their impact.

[1276] "Real-time" refers to data being processed as soon as it is generated.

[1277] "Appropriate person" refers to the person or department responsible for any work that requires action based on the contents of the report.

[1278] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1279] This invention uses a system that combines generative AI and an emotion engine to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is shown below.

[1280] 1. Program Generation

[1281] The server generates a program for the system that combines generative AI and an emotion engine. This program includes a series of processes for collecting, analyzing, classifying, filtering, and quickly responding to reports from users.

[1282] 2. Program Processing Explanation

[1283] The server executes programs using the following hardware and software.

[1284] Hardware: Servers, terminals

[1285] Software: Generative AI (e.g. OpenAI's GPT-4), emotion engines (e.g. IBM Watson's Tone Analyzer), chatbots

[1286] Data collection:

[1287] Users use the chatbot to input text data about the harassment through an anonymous reporting channel. For example, a user might enter, "My boss is continuing to harass me and it's taking a toll on me mentally."

[1288] Data transmission:

[1289] The terminal transmits the text data sent by the user to the server in real time.

[1290] Data Analysis:

[1291] The server inputs the collected text data into the generative AI and analyzes the content related to harassment. Specifically, the server inputs the text data into the generative AI as a prompt sentence, instructing it to "analyze this report and determine the severity and urgency of the harassment."

[1292] Emotion recognition:

[1293] The server uses an emotion engine to recognize the user's emotional state (e.g., anger, fear, sadness, etc.) and provides that information to the generative AI. The emotion engine analyzes the text data and recognizes the user's emotional state as "sadness."

[1294] Sorting and filtering:

[1295] The generative AI classifies the text data according to the severity and urgency of the harassment based on the emotional information provided by the emotion engine. The server filters the data according to importance and urgency based on this classification result. For example, the generative AI classifies the text data as "serious harassment" and determines the urgency as "high."

[1296] Response notification:

[1297] The server notifies the appropriate person in charge based on the filtered results and takes the necessary action promptly. Specifically, the server sends reports with a high level of urgency to the person in charge via email or a notification system, notifying them that "prompt action is required for this report."

[1298] 3. Examples of concrete examples and prompts

[1299] Examples:

[1300] If a user reports through an anonymous chatbot, "My boss is continuing to harass me and it's causing me mental distress," the following process will be followed:

[1301] 1. The user types into the chatbot, "My boss is continuing to harass me and it's causing me a lot of mental stress."

[1302] 2. The terminal sends this text data to the server.

[1303] 3. The server inputs the text data into the generative AI and instructs it to "analyze this report and determine the severity and urgency of the harassment."

[1304] 4. The server inputs the text data into the emotion engine, which then recognizes the emotion of "sadness."

[1305] 5. The generative AI classifies the text data as "serious harassment" and judges the urgency to be "high." The server filters this classification result and extracts reports with a high urgency.

[1306] 6. The server sends high-urgency reports to the responsible person via email or a notification system, notifying them that "this report requires immediate action."

[1307] Example prompt:

[1308] "I am being harassed by my boss and it is causing me a lot of mental stress. Please analyze this report and determine the severity and urgency of the harassment."

[1309] In this way, a system is realized in which the server, terminals, and users work together to quickly and accurately process reports related to harassment.

[1310] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] Users utilize the chatbot to input text data about harassment through an anonymous reporting channel.

[1313] Specifically, the user types into the chatbot's interface, "My boss is continuing to harass me and it's causing me a lot of mental stress."

[1314] Input: Text data entered by the user.

[1315] Output: Text data sent to the chatbot

[1316] Step 2:

[1317] The terminal transmits the text data sent by the user to the server in real time.

[1318] As a specific operation, the terminal immediately transfers the text data entered by the user to the server.

[1319] Input: Text data sent to the chatbot

[1320] Output: Text data sent to the server

[1321] Step 3:

[1322] The server inputs the collected text data into a generative AI system and analyzes it for harassment-related content.

[1323] Specifically, the server inputs the text data into the generative AI as a prompt, instructing it to "analyze this report and determine the severity and urgency of the harassment."

[1324] Input: Text data sent to the server

[1325] Output: Analysis results by generative AI

[1326] Step 4:

[1327] The server uses an emotion engine to recognize the user's emotional state (e.g., anger, fear, sadness, etc.) and provides that information to the generative AI.

[1328] Specifically, the server inputs the text data into an emotion engine, which then recognizes the emotion of "sadness."

[1329] Input: Text data sent to the server

[1330] Output: Emotion recognition results by the emotion engine

[1331] Step 5:

[1332] The generative AI classifies the text data according to the severity and urgency of the harassment based on the emotional information provided by the emotion engine.

[1333] Specifically, the generative AI classifies the text data as "serious harassment" and determines the urgency as "high."

[1334] Input: Analysis results by generative AI and emotion recognition results by emotion engine

[1335] Output: Classified harassment severity and urgency

[1336] Step 6:

[1337] Based on the classification results, the server performs filtering according to importance and urgency.

[1338] As a specific operation, the server extracts reports with a high level of urgency.

[1339] Input: Classified harassment severity and urgency

[1340] Output: Filtered report data

[1341] Step 7:

[1342] Based on the filtered results, the server notifies the appropriate person in charge and takes the necessary action promptly.

[1343] Specifically, the server will send high-urgency reports to the person in charge via email or a notification system, and notify them that "this report requires immediate action."

[1344] Input: Filtered report data

[1345] Output: Notification to the person in charge and instructions on how to respond

[1346] (Application example 1)

[1347] Next, a description will be given of Application Example 1 of Form 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".

[1348] Conventional harassment reporting systems often manually classify the contents of reports and determine their importance, making it difficult to respond quickly. In addition, because the reporter's emotional state is not taken into account, it is difficult to accurately determine the severity and urgency of the harassment. Furthermore, it is difficult to report anonymously, which can make reporters hesitant to report. There is a need for a system that can solve these problems and manage harassment reports more efficiently and accurately.

[1349] 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.

[1350] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for recognizing the emotional state of the user using an emotion engine and incorporating the information into the generative AI analysis, a means for accepting anonymous reports through an application installed on a smartphone, a means for proposing appropriate countermeasures based on the report contents, and a means for enabling a rapid response and leading to risk hedging. This automates the classification of the report contents and the determination of the importance, enabling a rapid and accurate response. In addition, by taking into account the reporter's emotional state, the severity and urgency of the harassment can be more accurately determined. Furthermore, it becomes easier to report anonymously, and reporters can report without hesitation.

[1351] "Generative AI" is an artificial intelligence technology that generates new information and results based on data provided by users.

[1352] An "emotion engine" is a technology that analyzes and recognizes a user's emotional state from data such as text and voice.

[1353] A "smartphone" is a multi-function mobile device that can connect to the Internet and run applications in addition to the functions of a mobile phone.

[1354] An "anonymous report" is a method of reporting a problem or incident without disclosing the reporter's personal information.

[1355] "Importance" is an indicator of the magnitude of impact and priority of a reported event or problem.

[1356] "Urgency" is an indicator of how quickly a response is required to a reported event or problem.

[1357] "Filtering" is the process of sorting through data based on specific criteria to extract only the information you need.

[1358] "Prompt response" refers to taking appropriate measures promptly in response to a problem or incident.

[1359] "Risk hedging" refers to minimizing risks by predicting potential risks and taking measures against them.

[1360] "Appropriate response" refers to the most effective and appropriate solution or measure to address a reported event or problem.

[1361] The system for implementing this invention combines a generative AI and an emotion engine, and operates through an application installed on a smartphone. A specific embodiment of this system will be described below.

[1362] System Configuration

[1363] Hardware

[1364] Smartphone: A device for users to enter reports.

[1365] Server: A computer system for running the generative AI and emotion engine, and analysing data.

[1366] software

[1367] Generative AI: Uses OpenAI APIs to analyze and classify report content.

[1368] Emotion Engine: Uses TextBlob to analyze the user's emotional state.

[1369] Smartphone application: Provides an interface for users to enter and submit reports anonymously.

[1370] Data processing and calculation

[1371] Smartphone

[1372] Users can anonymously report harassment through a smartphone application, and the text data is sent to a server.

[1373] server

[1374] The server processes the received text data in the following procedure.

[1375] 1. Sentiment Analysis: Use TextBlob to analyze the emotional state of the report text, specifically, score the text for positive, negative, or neutral sentiment.

[1376] 2. Generative AI classification: Using OpenAI’s API, we classify the report text according to the severity and urgency of the harassment. We generate prompt text and let the AI ​​analyze it.

[1377] Examples

[1378] Report content

[1379] "My boss yells at me every day and I can't concentrate on my work. I'm very stressed."

[1380] Emotion analysis results

[1381] Strong negative emotions

[1382] Generative AI classification results

[1383] Severity: High, Urgency: High

[1384] Examples of prompt statements

[1385] Please classify the text below according to the severity and urgency of the harassment:

[1386] My boss yells at me every day and I can't concentrate on my work. I'm feeling very stressed.

[1387] Classification:

[1388] effect

[1389] This system automates the classification and prioritization of reports, enabling a fast and accurate response. It also takes into account the reporter's emotional state, allowing for a more accurate assessment of the severity and urgency of the harassment. It also makes it easier to report anonymously, allowing reporters to do so without hesitation.

[1390] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1391] Step 1:

[1392] Users anonymously enter reports of harassment through a smartphone application.

[1393] Input: Text data entered by the user.

[1394] Output: Text data sent from the smartphone to the server.

[1395] Specific actions: The user fills in the application's input form with the report details and presses the submit button.

[1396] Step 2:

[1397] The text data received by the server is passed to the emotion engine for emotion analysis.

[1398] Input: Text data sent from the smartphone.

[1399] Output: Sentiment analysis results (positive, negative, neutral scores).

[1400] What happens: The server uses TextBlob to analyze the emotional state of the text data and generate an emotional score.

[1401] Step 3:

[1402] The server passes the results of the emotion analysis to a generative AI, which then classifies the report content.

[1403] Input: Sentiment analysis results and text data.

[1404] Output: Classification results (severity and urgency) generated by generative AI.

[1405] Specific operation: The server uses OpenAI's API to generate prompt text and classify the report content based on text data and sentiment analysis results.

[1406] Step 4:

[1407] The server then suggests appropriate countermeasures based on the classification results.

[1408] Input: Classification results from generative AI.

[1409] Output: A suggested action to take.

[1410] Specific operation: The server analyzes the classification results, selects and proposes the most appropriate countermeasure from a pre-configured countermeasure database.

[1411] Step 5:

[1412] The server sends the proposed countermeasures to the smartphone application and notifies the user.

[1413] Input: The proposed action.

[1414] Output: Countermeasures displayed on the smartphone application.

[1415] Specific operation: The server sends the countermeasures to the smartphone application and generates a message to notify the user.

[1416] Step 6:

[1417] The user reviews the proposed solutions and provides additional reporting and feedback as necessary.

[1418] Input: Proposed workaround and user feedback.

[1419] Output: Additional reporting and feedback data.

[1420] Specific Actions: The user reviews the proposed solutions through the application and provides additional reports and feedback if necessary.

[1421] Example 2

[1422] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[1423] In conventional anti-harassment systems, analysis to identify trends and patterns of harassment is often performed manually, which is time-consuming and labor-intensive. In addition, since analysis does not take into account emotional information, it is difficult to devise effective measures to prevent the occurrence of harassment. Furthermore, data visualization and report generation are not automated, making it difficult to respond quickly. To solve these issues, a system that combines generative AI and an emotion engine is needed.

[1424] 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.

[1425] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for preprocessing collected data, a means for analyzing data using a generative AI model, a means for recognizing emotional information using an emotion engine, a means for visualizing data by integrating the analysis results of the generative AI and the emotional information of the emotion engine, a means for automatically generating a report based on the visualized data, and a means for enabling a rapid response and leading to risk hedging. This makes it possible to effectively identify trends and patterns of harassment and to plan preventive measures that take emotional information into account. In addition, the visualization of data and automatic generation of reports enable a rapid response.

[1426] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[1427] "Harassment" refers to inappropriate language or behavior toward others in the workplace or any other environment.

[1428] "Inquiry" means a question or request made for specific information or assistance.

[1429] A "report" is a communication made to provide information about a particular event or situation.

[1430] "Classification" is the process of grouping data or information based on specific criteria.

[1431] "Filtering" is the process of selecting data or information based on specific conditions.

[1432] "Preprocessing" is the initial stage of processing to convert data into a form suitable for analysis and processing.

[1433] "Generative AI model" refers to the specific implementation and algorithms of generative AI.

[1434] An "emotion engine" is a technology for recognizing emotional information from data such as text and voice.

[1435] "Emotion information" is information that indicates the emotional state or tendency contained in the data.

[1436] "Integration" is the process of bringing together multiple pieces of data or information into one.

[1437] "Visualization" is the process of representing data or information in a visual form, such as a graph or chart.

[1438] A "report" is a document that compiles specific information or analytical results.

[1439] "Rapid response" refers to taking quick and appropriate action in response to a problem or situation.

[1440] "Risk hedging" refers to taking measures or steps to reduce potential risks.

[1441] This invention is a system that uses generative AI and an emotion engine to identify trends and patterns of harassment, visualize the data, and generate reports. A specific embodiment of this system is described below.

[1442] Hardware and Software Used

[1443] Hardware: Servers, terminals

[1444] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva), data pre-processing tools (e.g. Python, NLTK, Pandas), visualization tools (e.g. Tableau)

[1445] System Overview

[1446] The system starts with users uploading harassment-related data from their devices to a server. The server preprocesses the collected data and analyzes it using a generative AI model. It then recognizes emotional information using an emotion engine and integrates the generative AI analysis results with the emotional information. The integrated data is visualized, and finally a report is automatically generated.

[1447] Specific operation example

[1448] 1. Data Collection

[1449] Users upload files such as internal chat logs, emails, and survey results from their devices to the server.

[1450] Specific behavior: A user opens a browser, accesses the system's upload page, opens a file selection dialog, selects a file to upload, and clicks the Upload button.

[1451] 2. Data Preprocessing

[1452] The server parses the received data and performs text cleaning (e.g., removing HTML tags and special characters), then tokenizes the text and converts it into a data format for sentiment analysis.

[1453] Software used: Python, NLTK, Pandas

[1454] 3. Generative AI Analysis

[1455] The server inputs prompt sentences into a generative AI model (e.g., GPT-4) to extract harassment trends and patterns.

[1456] Specific behavior: "This chat log contains a lot of offensive language."

[1457] 4. Sentiment Analysis Using an Emotion Engine

[1458] The server feeds the text data into an emotion engine (e.g., Affectiva) to detect specific emotional states (e.g., anger, sadness).

[1459] Specific behavior: "This email expresses strong feelings of anger."

[1460] 5. Data integration and visualization

[1461] The server combines the analysis results of the generative AI with the emotional information from the emotion engine, and inputs them into a visualization tool (e.g., Tableau) to create graphs and charts.

[1462] Specific behavior: "Harassment occurs more frequently in certain departments."

[1463] 6. Generate reports

[1464] The server uses a report generation tool to create a report including the analysis results and countermeasure proposals.

[1465] Specific action: "Implementing regular emotional check-ins can help prevent harassment."

[1466] Examples of prompt statements

[1467] "Analyze these chat logs to identify trends and patterns of harassment."

[1468] "Please recognize the emotional state of this email and determine if it is related to an incident of harassment."

[1469] This system makes it possible to effectively identify trends and patterns of harassment and develop preventive measures that take emotional information into account. It also enables rapid response by visualizing data and automatically generating reports.

[1470] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1471] Step 1:

[1472] Data collection

[1473] Users upload files such as internal chat logs, emails, and survey results from their devices to the server.

[1474] Input: Files selected by the user (e.g. chat logs, emails, survey results)

[1475] Specific behavior: A user opens a browser, accesses the system's upload page, opens a file selection dialog, selects a file to upload, and clicks the Upload button.

[1476] Output: The file uploaded to the server.

[1477] Step 2:

[1478] Data Preprocessing

[1479] The server pre-processes the data received.

[1480] Input: The uploaded file

[1481] What it does: The server cleans the text data, removing unnecessary characters and noise, then tokenizes the text and converts it into a data format for sentiment analysis.

[1482] Output: Preprocessed text data

[1483] Software used: Python, NLTK, Pandas

[1484] Step 3:

[1485] Generative AI Analysis

[1486] The server analyzes the pre-processed data using a generative AI model (e.g., GPT-4).

[1487] Input: Preprocessed text data

[1488] How it works: The server inputs prompt sentences into the generative AI model and extracts harassment trends and patterns.

[1489] Output: Analysis of harassment trends and patterns.

[1490] Example prompt: "Analyze this chat log to identify trends or patterns of harassment."

[1491] Step 4:

[1492] Sentiment analysis with emotion engine

[1493] The server uses an emotion engine (e.g., Affectiva) to recognize emotion information in the data.

[1494] Input: Preprocessed text data

[1495] What happens: The server inputs text data into the emotion engine to detect specific emotional states (e.g. anger, sadness).

[1496] Output: Analysis results on emotional information

[1497] Example prompt: "Please identify the emotional state of this email and determine if it is related to an incident of harassment."

[1498] Step 5:

[1499] Data integration and visualization

[1500] The server integrates the analysis results of the generative AI with the emotional information from the emotion engine and visualizes the data.

[1501] Input: Analysis results of generative AI, emotion information of emotion engine

[1502] Specific operation: The server inputs the consolidated data into a visualization tool (e.g. Tableau) to create graphs and charts.

[1503] Output: Visualized data (graphs and charts)

[1504] Step 6:

[1505] Generate reports

[1506] The server automatically generates reports on harassment trends and patterns based on the visualized data.

[1507] Input: Visualized data

[1508] Specific operations: The server uses a report generation tool to create a report that includes the analysis results and countermeasure suggestions.

[1509] Output: Auto-generated report

[1510] Specific example of how it works: Generate a report that includes the suggestion that "introducing regular emotional check-ins could help prevent harassment."

[1511] (Application example 2)

[1512] Next, a description will be given of Application Example 2 of Form 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".

[1513] Conventional anti-harassment systems have difficulty identifying trends and patterns of harassment, and also have difficulty in monitoring in real time and responding quickly. As a result, they have been unable to effectively reduce the risk of harassment, and there have been many delays in protecting victims and formulating preventive measures. In addition, because emotion analysis using an emotion engine has not been performed, it has not been possible to accurately grasp the occurrence of harassment. To solve these issues, a system that combines generative AI and an emotion engine is needed.

[1514] 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.

[1515] In this invention, the server includes a means for automatically classifying inquiries and reports related to workplace harassment using generative AI and filtering them according to importance and urgency, a means for combining generative AI with an emotion engine to identify trends and patterns of harassment, and a means for visualizing data and generating reports, thereby enabling real-time monitoring of harassment risks and rapid response.

[1516] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[1517] An "emotion engine" is a technology that analyzes emotions from data such as text and voice, and identifies the emotional state.

[1518] "Harassment" is the act of causing mental or physical pain to another person through inappropriate verbal or physical actions in a workplace, school, or other environment.

[1519] A "trend" is a quality or pattern that a particular phenomenon or behavior moves in a certain direction.

[1520] A "pattern" is a regularity or form in which a particular phenomenon or behavior occurs repeatedly.

[1521] "Data visualization" is a technique for representing data in a visual format, such as in graphs or charts, to make it easier to understand.

[1522] "Report generation" is the process of automatically generating reports based on analysis results and data.

[1523] A "countermeasure" is a specific means or method taken to address a specific problem or risk.

[1524] A "preventive measure" is a means or method for preventing a problem or risk before it occurs.

[1525] A "smartphone" is a multi-function mobile device that, in addition to the functions of a mobile phone, can also connect to the Internet and use applications.

[1526] "Real-time" means that data and information are processed immediately and provided without delay.

[1527] "Filtering" is the process of sorting data based on specific conditions and extracting only the necessary information.

[1528] "Text data" is digital data that includes character information.

[1529] "Sentiment analysis" is a technology that analyzes emotional states from data such as text and voice, and identifies those emotions.

[1530] The system for implementing this invention combines generative AI and an emotion engine to identify trends and patterns of harassment, visualize the data, and generate reports. A specific embodiment of this system is described below.

[1531] System Configuration

[1532] The system consists of the following main components:

[1533] 1. Generative AI model: Artificial intelligence technology that generates new information and patterns based on data.

[1534] 2. Emotion engine: Technology that analyzes emotions from data such as text and voice and identifies the emotional state.

[1535] 3. Smartphone application: An interface for users to monitor harassment risk in real time and enter data.

[1536] 4. Data Visualization Tools: Use software such as Matplotlib or Pandas to create visual representations of your data.

[1537] 5. Report generation function: A function that automatically creates reports based on analysis results.

[1538] Program Processing

[1539] The server uses a generative AI model to identify trends and patterns of harassment from the input text. Specifically, it uses OpenAI's API to analyze the text data entered by the user and evaluate the risk of harassment. The emotion engine performs sentiment analysis on the text data and determines whether a specific emotional state is closely related to the occurrence of harassment.

[1540] Data Visualization and Reporting

[1541] The server uses Matplotlib and Pandas to visualize the emotion data analyzed by the emotion engine, allowing users to visually understand harassment trends and patterns. In addition, a report is automatically generated based on the analysis results of the generative AI model and the emotion engine. This report includes harassment trends and patterns, emotional states, and suggestions for countermeasures and prevention measures.

[1542] Examples

[1543] For example, if the input data were a log of a conversation at work, the user might enter the following text:

[1544] "In yesterday's meeting, the boss used very harsh words towards his subordinate. The subordinate was clearly uncomfortable."

[1545] Based on this text data, the generative AI model identifies harassment trends and patterns using the following prompts:

[1546] Identify trends or patterns of harassment in the following text:

[1547] "In yesterday's meeting, the boss used very harsh words towards his subordinate. The subordinate was clearly uncomfortable."

[1548] The emotion engine analyzes the emotional state of the text data and identifies strong emotions such as anger or sadness. Based on this data, the server visualizes the data and generates a report.

[1549] In this way, users can monitor harassment risks in real time and respond quickly.

[1550] The flow of the identification process in the application example 2 will be described with reference to FIG.

[1551] Step 1:

[1552] A user inputs text data such as conversation logs from work or school through a smartphone application.

[1553] Input: Text data such as conversation logs

[1554] Output: The text data entered

[1555] Step 2:

[1556] The server sends the input text data to a generative AI model and performs analysis to identify trends and patterns of harassment. Specifically, it uses OpenAI's API to analyze the text data.

[1557] Input: The text data entered.

[1558] Output: Analysis of harassment trends and patterns

[1559] Step 3:

[1560] The server uses an emotion engine to perform emotion analysis of the text data based on the analysis results. The emotion engine identifies emotional states such as "anger" or "sadness" from the text data.

[1561] Input: Input text data, analysis results of generative AI model

[1562] Output: Data about emotional state

[1563] Step 4:

[1564] The server uses Matplotlib and Pandas to visualize the emotion data analyzed by the emotion engine, allowing users to visually understand trends and patterns of harassment.

[1565] Input: Data about emotional state

[1566] Output: Visualized data (graphs and charts)

[1567] Step 5:

[1568] The server automatically generates reports based on the results of the generative AI model and emotion engine analysis, including harassment trends and patterns, emotional states, and suggested countermeasures and prevention measures.

[1569] Input: Analysis results of generative AI model, data on emotional state

[1570] Output: Auto-generated report

[1571] Step 6:

[1572] Through a smartphone application, users can review the generated reports, monitor harassment risks in real time, and respond quickly.

[1573] Input: Auto-generated report

[1574] Output: Reports reviewed by the user

[1575] In this way, users can monitor harassment risks in real time and respond quickly.

[1576] Example 3

[1577] Next, a third embodiment of the third embodiment will be described. 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".

[1578] Conventional anti-harassment systems found it difficult to effectively propose specific measures and preventive measures to prevent harassment from occurring. In addition, there was a lack of measures that took into account the emotional state of employees, making it difficult to identify the root causes of harassment. Furthermore, the collection and analysis of data on harassment was often done manually, which meant insufficient risk hedging in situations where a rapid response was required.

[1579] The identification process by the identification processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using a generative AI and filtering them according to importance and urgency, a means for identifying trends and patterns of harassment using a generative AI model, a means for collecting employee emotional information using an emotion engine and analyzing the relationship between the emotional state and the occurrence of harassment, a means for proposing measures and preventive measures against harassment based on the analysis results of the generative AI model and the recognition results of the emotion engine, a means for visualizing data and generating reports, and a means for enabling a rapid response and leading to risk hedging. This makes it possible to prevent the occurrence of harassment and propose effective measures and preventive measures that take into account the emotional state of employees.

[1580] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[1581] "Harassment" refers to acts of harassment or unfair treatment in the workplace or organization.

[1582] "Inquiry" means a question or request for specific information or assistance.

[1583] "Reporting" is the act of providing information about a particular event or situation.

[1584] "Classification" is the process of grouping data or information based on specific criteria.

[1585] "Filtering" is the process of selecting data or information based on specific conditions.

[1586] "Generative AI model" refers to the specific implementation and algorithms of generative AI.

[1587] A "trend" is a movement in data that shows a particular direction or pattern.

[1588] A "pattern" is a recurring structure or regularity in data or events.

[1589] An "emotion engine" is a technology for analyzing and recognizing the emotional state of employees.

[1590] "Emotional information" is data regarding an employee's emotional state.

[1591] A "measure" is a specific action or measure to address a particular problem or issue.

[1592] A "prevention measure" is a specific action or step taken to head off a problem or issue before it occurs.

[1593] "Visualization" is the process of representing data or information visually.

[1594] A "report" is a document that compiles specific information or analytical results.

[1595] "Quick response" refers to the action of quickly dealing with problems or issues.

[1596] "Risk hedging" refers to measures or means for reducing potential risks.

[1597] This invention is a system that proposes measures and preventive measures against harassment by utilizing generative AI and an emotion engine. This system operates mainly with a server, a terminal, and a user.

[1598] Hardware and Software Used

[1599] Hardware: Servers, terminals

[1600] Software: Generative AI models (e.g. GPT-4), emotion engines (e.g. Affectiva)

[1601] Specific operation of the system

[1602] Data collection

[1603] The server collects data on harassment from each department within the company. Specifically, the server accesses the management systems of each department and obtains data such as the frequency, time periods, and types of harassment. For example, the server automatically collects monthly reports and the results of internal investigations.

[1604] Data analysis

[1605] The server inputs the collected data into a generative AI model to analyze harassment trends. Specifically, the server preprocesses the collected data and inputs it into a generative AI model (e.g., GPT-4) using a prompt sentence. For example, the prompt sentence could be, "If harassment is frequent in a specific department, please identify that department."

[1606] Collecting emotional information

[1607] The device collects employees' emotional information using an emotion engine. Specifically, the device analyzes the employee's facial expressions and voice in real time, and the emotion engine (e.g., Affectiva) recognizes the emotional state. For example, the device captures the facial expressions of employees during a meeting with a camera, and the emotion engine analyzes emotions from the facial expressions.

[1608] Emotional information analysis

[1609] The server inputs the emotion information obtained from the emotion engine into the generative AI model and analyzes the correlation between the emotional state and the occurrence of harassment. Specifically, the server inputs the data obtained from the emotion engine into the generative AI model and uses a prompt sentence such as "If a specific emotional state is closely related to the occurrence of harassment, please identify that information." For example, the server identifies departments where emotional states such as "anger" and "anxiety" are frequently observed.

[1610] Suggested measures and prevention measures

[1611] The server proposes specific measures and prevention measures against harassment based on the analysis results of the generative AI model and the recognition results of the emotion engine. Specifically, the server inputs a prompt to the generative AI model, such as "If harassment is occurring frequently in a specific department, what measures should be proposed for that department?" and plans countermeasures based on the results obtained. For example, the server proposes regular harassment prevention training and counseling for stress management for a specific department.

[1612] Examples

[1613] Example 1: At the beginning of each month, a server accesses each department's management system and automatically downloads the previous month's harassment report.

[1614] Example 2: The report downloaded by the server is input into a generative AI model and analyzed using the prompt, "In which department is harassment most prevalent?"

[1615] Example 3: The device uses a camera to capture the facial expressions of employees during a meeting, and the emotion engine analyzes the facial expressions in real time to determine emotions such as "anger" or "anxiety."

[1616] Example 4: The server inputs the emotion data obtained from the emotion engine into a generative AI model and analyzes it using the prompt, "If a specific emotional state is closely related to the occurrence of harassment, please identify that information."

[1617] Example 5: Based on the analysis results of the generative AI model, the server suggests "harassment prevention training" or "stress management counseling" for a specific department.

[1618] The above is an embodiment of the present invention. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1619] Step 1: Data collection

[1620] The server collects data on harassment from each department in the company. Specifically, the server accesses each department's management system and obtains data such as the frequency, time of day, and type of harassment. The input is data from each department's management system, and the output is the collected harassment-related data. For example, the server automatically downloads monthly reports and the results of internal investigations.

[1621] Step 2: Data Preprocessing

[1622] The server preprocesses the collected data. Specifically, it performs tasks such as filling in missing values, detecting and correcting outliers, and normalizing the data. The input is the collected harassment-related data, and the output is the preprocessed data. For example, the server fills in missing values ​​with the average value and detects and corrects outliers.

[1623] Step 3: Data analysis

[1624] The server inputs the preprocessed data into a generative AI model to analyze harassment trends. Specifically, the server inputs the generative AI model (e.g., GPT-4) using a prompt sentence. The inputs are the preprocessed data and the prompt sentence, and the output is the analysis results regarding harassment trends and patterns. For example, the prompt sentence could be, "If harassment occurs frequently in a specific department, please identify that department."

[1625] Step 4: Collecting emotional information

[1626] The device collects employees' emotional information using an emotion engine. Specifically, the device analyzes the employee's facial expressions and voice in real time, and the emotion engine (e.g., Affectiva) recognizes the employee's emotional state. The input is the employee's facial expressions and voice data, and the output is the recognized emotional information. For example, the device uses a camera to capture the facial expressions of employees during a meeting, and the emotion engine analyzes emotions from the facial expressions.

[1627] Step 5: Analyze sentiment information

[1628] The server inputs the emotion information obtained from the emotion engine into the generative AI model and analyzes the correlation between the emotional state and the occurrence of harassment. Specifically, the server inputs the data obtained from the emotion engine into the generative AI model and uses a prompt sentence such as "If a specific emotional state is closely related to the occurrence of harassment, please identify that information." The inputs are the emotion information and the prompt sentence, and the output is the analysis results regarding the correlation between the emotional state and harassment. For example, the server identifies departments where emotional states such as "anger" and "anxiety" are frequently observed.

[1629] Step 6: Proposing countermeasures and preventative measures

[1630] The server proposes specific countermeasures and preventive measures against harassment based on the analysis results of the generative AI model and the recognition results of the emotion engine. Specifically, the server inputs a prompt to the generative AI model, such as "If harassment occurs frequently in a specific department, what countermeasures should be proposed for that department?" and plans countermeasures based on the results obtained. The inputs are the analysis results and the prompt, and the output is the proposed countermeasures and preventive measures. For example, the server might propose regular harassment prevention training or counseling for stress management for a specific department.

[1631] (Application example 3)

[1632] Next, a description will be given of Application Example 3 of Form Example 3. 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".

[1633] Conventional harassment prevention systems have difficulty efficiently classifying and quickly responding to inquiries and reports related to harassment within the company. They also have difficulty identifying trends and patterns of harassment and proposing specific countermeasures and preventative measures. In particular, there is a need for early detection and countermeasures of harassment using voice data in communication between employees within factories.

[1634] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1635] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the workplace using generative AI and filtering them according to importance and urgency, a means for enabling a rapid response and leading to risk hedging, a means for converting conversation into text using voice recognition, a means for recognizing the emotional state of the conversation using an emotion engine, a means for analyzing the content of the conversation using generative AI and detecting signs of harassment, and a means for proposing specific countermeasures and preventive measures for the detected signs of harassment. This enables early detection and countermeasures of harassment in communication between employees in a factory.

[1636] "Generative AI" is an artificial intelligence technology that generates new information and content based on data.

[1637] "Speech recognition" is a technology that converts voice data into text data.

[1638] An "emotion engine" is a technology that recognizes emotional states from text and voice.

[1639] "Filtering" is the process of sorting data based on specific criteria.

[1640] "Risk hedging" refers to taking measures to reduce potential risks.

[1641] A "indicator of harassment" is a pattern of behavior or conduct that indicates that harassment may be occurring.

[1642] "Countermeasures and preventive measures" are specific actions or means to prevent the occurrence of harassment.

[1643] "Conversation content analysis" is the process of analyzing text data of a conversation to understand its meaning and intent.

[1644] The system for carrying out the present invention is configured as an application installed on a robot working in a factory. A specific embodiment of the system will be described below.

[1645] System Configuration

[1646] 1. Voice Recognition

[1647] The server uses voice recognition technology to convert conversations in the factory into text data in real time. Specifically, it uses the speech_recognition library.

[1648] 2. Generative AI Models

[1649] The server uses a generative AI model to analyze the text data and detect signs of harassment. To do this, it uses the GPT-3 model from the transformers library.

[1650] 3. Emotion Engine

[1651] The server uses an emotion engine to recognize emotional states from text data. Specifically, it uses the emotion_recognition library.

[1652] 4. Filtering and risk hedging

[1653] The server uses generative AI to automatically categorize harassment-related inquiries and reports, filtering them according to importance and urgency, enabling a rapid response and hedging risks.

[1654] 5. Proposals for countermeasures and preventive measures

[1655] The server uses a generative AI model to suggest specific countermeasures and preventive measures for detected signs of harassment.

[1656] Processing flow

[1657] 1. Acquiring audio data

[1658] The terminal (robot) picks up conversations within the factory through a microphone.

[1659] 2. Converting voice data to text

[1660] The server converts the acquired voice data into text data using the speech_recognition library.

[1661] 3. Recognizing Emotional States

[1662] The server recognizes the emotional state of the text data using the emotion_recognition library.

[1663] 4. Detecting signs of harassment

[1664] The server uses a generative AI model (GPT-3) to analyze text data and detect signs of harassment.

[1665] 5. Proposals for countermeasures and preventive measures

[1666] The server uses a generative AI model to suggest specific countermeasures and preventive measures for detected signs of harassment.

[1667] Examples

[1668] For example, the following conversation might take place in a factory:

[1669] Employee A: "You've been working slow lately. You need to work harder."

[1670] Employee B: "Sorry, I'm not feeling well..."

[1671] This conversation is captured as audio data and input to the program. The server inputs the following prompt sentence into the generative AI model:

[1672] Analyze the following conversation for harassment: "Recently, your work has been slow. You need to work harder." "I'm sorry, I'm not feeling well."

[1673] Based on this prompt, the server analyzes signs of harassment and suggests appropriate countermeasures and preventive measures.

[1674] The flow of the specific process in the application example 3 will be described with reference to FIG.

[1675] Step 1:

[1676] The terminal (robot) picks up conversations in the factory through a microphone. The input is voice data, and the output is the same voice data. This voice data is processed in the next step.

[1677] Step 2:

[1678] The server converts the acquired voice data into text data using the speech_recognition library. The input is voice data, and the output is text data. This conversion allows the voice information to be treated as text information.

[1679] Step 3:

[1680] The server recognizes the emotional state of the text data using the emotion_recognition library. The input is text data, and the output is the emotional state (e.g. anger, sadness, joy, etc.). This processing allows the emotional nuances of the conversation to be understood.

[1681] Step 4:

[1682] The server uses a generative AI model (GPT-3) to analyze text data and detect signs of harassment. The input is text data and emotional state, and the output is the analysis results on signs of harassment. This analysis determines whether the conversation corresponds to harassment.

[1683] Step 5:

[1684] The server uses a generative AI model to propose specific countermeasures and preventive measures for the detected signs of harassment. The input is the analysis results on the signs of harassment, and the output is specific countermeasures and preventive measures. This proposal provides appropriate countermeasures.

[1685] Examples

[1686] For example, the following conversation might take place in a factory:

[1687] Employee A: "You've been working slow lately. You need to work harder."

[1688] Employee B: "Sorry, I'm not feeling well..."

[1689] This conversation is captured as audio data and input to the program. The server inputs the following prompt sentence into the generative AI model:

[1690] Analyze the following conversation for harassment: "Recently, your work has been slow. You need to work harder." "I'm sorry, I'm not feeling well."

[1691] Based on this prompt, the server analyzes signs of harassment and suggests appropriate countermeasures and preventive measures.

[1692] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the 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.

[1693] 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> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1694] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1695] 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 smart glasses 214.

[1696] [Third embodiment]

[1697] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1698] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1699] 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 wide area network (WAN) and / or a local area network (LAN).

[1700] 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.

[1701] 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 the voice according to instructions from the processor 46.

[1702] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1703] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1704] Fig. 6 shows an example of 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.

[1705] 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.

[1706] 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.

[1707] In the headset type terminal 314, 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.

[1708] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1709] "Example 1"

[1710] One embodiment of the present invention is a system that uses generative AI to automatically classify inquiries and reports related to harassment in the workplace. Specifically, generative AI analyzes text data collected through anonymous reporting channels using chatbots, and automatically classifies content related to harassment. Furthermore, the results can be filtered according to importance and urgency, allowing for rapid response.

[1711] "Example 2"

[1712] Another embodiment of the present invention is a system that uses generative AI to identify trends and patterns of harassment, visualize the data, and generate reports. Specifically, based on the results of the generative AI analysis, the system extracts trends and patterns of harassment and visualizes them. Based on the results, the system automatically generates reports and suggests measures and preventative measures against harassment.

[1713] "Example 3"

[1714] As a further embodiment of the present invention, there is a system that utilizes generative AI to propose measures and preventive measures against harassment. Specifically, the system proposes measures and preventive measures against harassment based on the results of analysis by generative AI. For example, it identifies departments, time periods, and types of harassment where harassment occurs frequently, and proposes specific measures and preventive measures against them.

[1715] The process flow of each embodiment will be described below.

[1716] "Example 1"

[1717] Step 1: Collect text data from an anonymous reporting channel using a chatbot.

[1718] Step 2: Input the collected text data into a generative AI system to automatically classify harassment-related content.

[1719] Step 3: Filter the results of the generative AI's classification according to importance and urgency, and take necessary action quickly.

[1720] "Example 2"

[1721] Step 1: Based on the results of the generative AI analysis, extract trends and patterns of harassment.

[1722] Step 2: Visualize the extracted trends and patterns.

[1723] Step 3: Automatically generate a report based on the visualized results and suggest measures to combat and prevent harassment.

[1724] "Example 3"

[1725] Step 1: Based on the results of the generative AI's analysis, propose countermeasures and preventive measures against harassment.

[1726] Step 2: Identify the departments, times of day, and types of harassment where harassment is most frequent.

[1727] Step 3: Propose specific countermeasures and preventive measures for the identified information.

[1728] Example 1

[1729] Next, a description will be given of Example 1 of the embodiment 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".

[1730] There is a need to efficiently classify inquiries and reports related to harassment within the company and respond quickly according to their importance and urgency. However, traditional manual responses run the risk of delaying the processing of reports or overlooking important reports. It is also difficult to identify trends and patterns of harassment and propose countermeasures and preventive measures. To solve these issues, automatic classification and filtering of reports, rapid response, data visualization and report generation, and proposal of countermeasures and preventive measures are required.

[1731] 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.

[1732] In this invention, the server includes a means for collecting anonymous reports using a chatbot, a means for transmitting collected text data to the server, a means for analyzing the text data using a generative AI model and automatically classifying content related to harassment, a means for filtering the classification results according to importance and urgency, a means for notifying the person in charge of the filtered results, a means for enabling a rapid response and leading to risk hedging, a means for identifying trends and patterns of harassment using generative AI, a means for visualizing data and generating reports, and a means for proposing measures and preventative measures against harassment. This makes it possible to efficiently classify inquiries and reports related to harassment within the company and to respond quickly according to importance and urgency.

[1733] A "chatbot" is software that automates dialogue with users and has the ability to collect and respond to information through text and voice.

[1734] An "anonymous report" is a report made without revealing the reporter's identity, providing a means of providing information while protecting privacy.

[1735] "Text data" is information expressed as a character string, and includes the contents of reports and inquiries.

[1736] A "server" is a computer system that processes and stores data on a network, and provides services in response to requests from clients.

[1737] A "generative AI model" is an algorithm or system that uses artificial intelligence techniques to analyze data and automatically perform specific tasks.

[1738] "Analysis" is the process of examining data in detail to understand its structure and meaning.

[1739] Classification is the process of separating data into specific categories or groups, grouping data that share common characteristics.

[1740] "Filtering" is the process of sorting through data based on specific criteria to extract only the information you need.

[1741] A "notification" is a means of informing relevant parties of specific information, and is done via email, dashboard, etc.

[1742] "Rapid response" refers to dealing with a problem quickly when it occurs, and is an action taken to minimize risk.

[1743] "Risk hedging" is the process of predicting potential risks and taking measures to reduce the impact of those risks.

[1744] A "trend" refers to a general movement or pattern of data or events moving in a particular direction.

[1745] A "pattern" refers to a repeating structure or arrangement in data or events.

[1746] "Visualization" is the process of making information easier to understand intuitively by representing data visually.

[1747] A "report" is a document that compiles information on a particular topic and includes analytical findings and recommendations.

[1748] A "measure" refers to a specific action or plan to address a particular problem.

[1749] "Preventive measures" refer to measures or actions taken to prevent problems before they occur.

[1750] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[1751] This invention is a system that uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is described below.

[1752] Hardware and Software Used

[1753] The system uses the following hardware and software:

[1754] Server: A computer system that processes and stores data, and also serves as the execution environment for generative AI models.

[1755] Device: The device used by the user (PC, smartphone, tablet, etc.).

[1756] Chatbot: Software that automates conversations with users. It runs on communication tools such as Slack and Microsoft Teams.

[1757] Generative AI model: An algorithm that analyzes text data and performs specific tasks automatically, such as OpenAI's GPT-4.

[1758] Data processing and calculation

[1759] This system performs the following data processing and calculations.

[1760] 1. Collect reports: Users anonymously report harassment through the chatbot. For example, a user may report, “My boss yells at me every day.”

[1761] 2. Data transmission: The terminal transmits the text data collected through the chatbot to the server, which temporarily stores the received text data.

[1762] 3. Text Analysis and Classification: The server inputs the stored text data into the generative AI model, which analyzes the text data using the following prompt sentence:

[1763] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[1764] The generative AI model analyzes text data and classifies it as "power harassment."

[1765] 4. Filtering of classification results: The server evaluates the importance and urgency of reports based on the classification results obtained from the generative AI model. For example, reports classified as "power harassment" are deemed to be of high importance. The server filters reports taking into account their content, frequency, and the strength of the words used.

[1766] 5. Notify the person in charge: The server notifies the person in charge based on the filtered results. The notification is done, for example, via email or a dedicated management dashboard. The person in charge can receive the notification and take the necessary action promptly.

[1767] Examples

[1768] As a concrete example, consider the following scenario.

[1769] scenario:

[1770] A user anonymously reports to a chatbot on Slack, "My boss yells at me every day." This report is sent to a server and analyzed by a generative AI model.

[1771] Example prompt:

[1772] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[1773] The generative AI model receives this prompt and classifies the report as "power harassment." The server then determines the importance of the report as "high" based on this classification and notifies the person in charge by email.

[1774] The above is a specific embodiment for carrying out the present invention.

[1775] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1776] Step 1:

[1777] A user anonymously reports harassment through the chatbot. For example, a user reports, "My boss yells at me every day." This report becomes input data. The chatbot receives this text data and saves the report.

[1778] Step 2:

[1779] The terminal transmits the text data collected through the chatbot to the server. The input data is the text data reported by the user. The server temporarily stores the received text data. Specifically, it stores it in a database.

[1780] Step 3:

[1781] The server inputs the stored text data into the generative AI model. The input data is the stored text data. The generative AI model parses the text data using the following prompt sentence:

[1782] I received a report that said, "My boss yells at me every day." Please analyze this report and classify it into the appropriate category.

[1783] The generative AI model analyzes the text data and classifies it as "power harassment." The output data is the classification result.

[1784] Step 4:

[1785] The server evaluates the importance and urgency of reports based on the classification results obtained from the generative AI model. The input data is the classification results from the generative AI model. The server filters the reports taking into account their content, frequency, and the strength of the words used. The output data is the filtered results.

[1786] Step 5:

[1787] The server notifies the person in charge based on the filtered results. The input data is the filtered results. The notification is sent, for example, via email or a dedicated management dashboard. The output data is the notification content. The person in charge can receive the notification and take the necessary action promptly.

[1788] The above is the specific flow of the program processing of this system.

[1789] (Application example 1)

[1790] Next, a description will be given of Application Example 1 of Form 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".

[1791] In conventional harassment reporting systems, classification of reports and judgment of their importance were often done manually, making it difficult to respond quickly. In addition, there was a lack of a mechanism to properly filter important reports and notify the person in charge immediately while ensuring anonymity. This created a risk of delaying the early detection and countermeasures of harassment.

[1792] 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.

[1793] In this invention, the server includes a means for automatically classifying inquiries and reports related to workplace harassment using generative AI and filtering them according to importance and urgency, a means for analyzing text data collected through anonymous reporting channels, and a means for immediately notifying the person in charge when an important report is received. This enables a quick response and leads to risk hedging.

[1794] "Generative AI" is an artificial intelligence technology that generates new data and information based on input information such as text data and image data.

[1795] "Workplace harassment" refers to inappropriate behavior such as harassment, bullying, and discrimination that occurs in the workplace.

[1796] An "inquiry or report" refers to an employee communicating an issue or question about harassment to the company.

[1797] "Automatic classification" refers to the process in which generative AI analyzes input data and automatically classifies it based on specific categories or importance.

[1798] "Filtering based on importance and urgency" refers to the process of selecting data classified by generative AI based on its importance and urgency.

[1799] "Anonymous reporting channel" means a means of communication through which a report of harassment may be made without revealing the reporter's identity.

[1800] "Text data" refers to data expressed as character information.

[1801] "Analyze" refers to the process in which generative AI examines the input data in detail to understand and classify its contents.

[1802] "Immediate notification to responsible parties" refers to the process of immediately notifying designated responsible parties when important reports are received.

[1803] "Prompt response" refers to taking appropriate measures without delay when a problem occurs.

[1804] "Risk hedging" refers to minimizing risks by detecting potential risks in advance and taking measures to address them.

[1805] The system for implementing this invention uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to their importance and urgency. A specific embodiment of this system is described below.

[1806] System Configuration

[1807] The system consists of the following main components:

[1808] 1. Server: Runs the generative AI model to analyze and classify text data.

[1809] 2. Device: The device (e.g., smartphone) through which a user reports harassment via the anonymous reporting channel.

[1810] 3. Notification system: Immediately notify the responsible person when there is an important report.

[1811] Hardware and software used

[1812] Hardware: Smartphones, servers

[1813] Software: Python, OpenAI API

[1814] Data processing and calculation

[1815] 1. Text data collection

[1816] Users can use their smartphones to access the anonymous reporting channel and report on harassment. The report content is sent to the server as text data.

[1817] 2. Generative AI analysis

[1818] The server analyzes the collected text data using the OpenAI API, and inputs the text data into the generative AI model using the following prompt:

[1819] Example prompt:

[1820] Analyze the text below and classify the content as harassment related.

[1821] Text: My boss keeps harassing me. Please help.

[1822] Classification results:

[1823] The generative AI model analyzes the text data based on this prompt and classifies the content as harassment-related.

[1824] 3. Filtering and Notifications

[1825] The server determines the importance and urgency of the report based on the analysis results obtained from the generative AI model. If an important report is received, the person in charge is notified immediately via the notification system.

[1826] Examples

[1827] For example, if a user reports, "My boss continues to harass me. Please help me," the server inputs this text data into a generative AI model, and obtains the classification result as "This report is important. My boss continues to harass me, so urgent action is required." Based on this result, the server immediately notifies the person in charge, enabling a prompt response.

[1828] In this way, a harassment reporting system using generative AI can enable quick and appropriate responses, helping to hedge risks.

[1829] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1830] Step 1:

[1831] A user accesses the anonymous reporting channel using a smartphone to report harassment. The input is text data entered by the user. The output is text data sent to the server.

[1832] Step 2:

[1833] The server inputs the received text data into the generative AI model. Specifically, it analyzes the text data using the following prompt sentence. The input is the text data sent by the user. The output is the analysis result by the generative AI model.

[1834] Example prompt:

[1835] Analyze the text below and classify the content as harassment related.

[1836] Text: My boss keeps harassing me. Please help.

[1837] Classification results:

[1838] Step 3:

[1839] The server judges the importance and urgency of the report content based on the analysis results obtained from the generative AI model. The input is the analysis results of the generative AI model. The output is the filtering results according to the importance and urgency.

[1840] Step 4:

[1841] The server immediately notifies the person in charge through the notification system when there is an important report based on the filtering result. The input is the filtering result. The output is the notification to the person in charge.

[1842] Step 5:

[1843] The person in charge receives the notification and takes prompt action. The input is the notification from the server. The output is the implementation of the action.

[1844] In this way, a harassment reporting system using generative AI can enable quick and appropriate responses, helping to hedge risks.

[1845] Example 2

[1846] Next, a second embodiment of the second form will be described. 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".

[1847] With conventional harassment prevention systems, it was difficult to efficiently classify inquiries and reports related to harassment within the company and quickly respond to them according to their importance and urgency. It was also difficult to identify trends and patterns of harassment and propose countermeasures and preventative measures based on them. This led to problems such as the inability to properly manage the risk of harassment and delays in improving the working environment within the company.

[1848] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for collecting data from a database, a means for preprocessing the collected data, a means for analyzing data using a generative AI model and identifying trends and patterns of harassment, a means for visualizing the analysis results, and a means for automatically generating a report based on the visualized data. This makes it possible to efficiently identify trends and patterns of harassment, and to propose rapid responses and appropriate countermeasures and preventive measures.

[1849] "Generative AI" is a system that uses artificial intelligence technology to generate, analyze, and classify data.

[1850] A "database" is a system for efficiently storing, managing, and searching data.

[1851] "Preprocessing" refers to the initial process of preparing data for analysis, and specifically includes data cleaning and tokenization.

[1852] A "generative AI model" is a part of generative AI, an algorithm that analyzes data and generates results based on specific prompts.

[1853] A "prompt sentence" is an input sentence that gives specific instructions or questions to a generative AI model.

[1854] "Visualization" refers to the display of data analysis results in a visual format such as a graph or chart.

[1855] A "report" is a written summary of data analysis results and recommendations.

[1856] "Harassment" refers to inappropriate behavior or remarks towards others in the workplace or any other environment.

[1857] "Inquiry" means a question or request made for specific information or assistance.

[1858] A "report" is a written or oral communication providing information about a particular event or situation.

[1859] "Classification" means grouping data based on specific criteria.

[1860] "Filtering" means selecting data based on specific conditions.

[1861] A "trend" refers to a recurring pattern or trend in data.

[1862] A "pattern" is a collection of elements in data that have a certain regularity or commonality.

[1863] A "measure" is a specific action or plan to address a particular problem.

[1864] A "prevention" is a specific action or plan to prevent a problem before it occurs.

[1865] This invention is a system that uses generative AI to automatically classify inquiries and reports related to workplace harassment and filter them according to importance and urgency. It also collects data from a database, pre-processes it, and uses a generative AI model to analyze the data and identify trends and patterns of harassment. It visualizes the analysis results and automatically generates reports to suggest countermeasures and preventive measures against harassment.

[1866] Hardware and Software Used

[1867] Hardware:

[1868] Server: Database server (e.g. MySQL)

[1869] Terminal: A computer used to view data and review reports.

[1870] software:

[1871] Database Management System: MySQL

[1872] Natural Language Processing Libraries: NLTK, spaCy

[1873] Generative AI model: GPT-4

[1874] Data visualization tools: Tableau, Matplotlib

[1875] Report generation tools: LaTeX, Microsoft Word

[1876] Explanation of program processing

[1877] Data collection:

[1878] The server collects data such as chat logs, emails, and survey results within the company. Specifically, it connects to the database server and retrieves the required data with a query. For example, execute the query "SELECT FROM chat_logs WHERE date BETWEEN '2023-01-01' AND '2023-01-31'" to retrieve chat logs for January.

[1879] Data preprocessing:

[1880] The server preprocesses the collected data. Specifically, it cleans the text data (removes unnecessary characters and spaces) and tokenizes it (splits it into words and phrases). The preprocessed data is temporarily stored on the terminal. For example, the cleaned text data is saved as a CSV file.

[1881] Analysis by generative AI models:

[1882] The server inputs the preprocessed data into a generative AI model (GPT-4) to analyze harassment trends and patterns. The prompt text to be input into the generative AI model is created by the user. For example, the prompt text "Please identify the harassment trends from the following chat logs" is used.

[1883] Data Visualization:

[1884] The server visualizes harassment trends and patterns based on the results of the generative AI model's analysis. Specifically, it uses Matplotlib to create graphs and display bar graphs showing the time periods when certain keywords frequently appear. The visualized data is then displayed on the terminal.

[1885] Generate report:

[1886] The server automatically generates a "January Harassment Trend Report" using LaTeX based on the visualized data and saves it in PDF format. Users can check the generated report and make corrections or additional comments as necessary.

[1887] Examples of concrete examples and prompts

[1888] Examples:

[1889] Identify the times and departments in which specific keywords (e.g. "harassment" or "ignoring") appear frequently from company chat logs.

[1890] From the survey results, the names of departments and superiors with the most reports of harassment will be extracted.

[1891] Example prompt:

[1892] Please identify harassment trends from the chat logs below. In particular, please extract frequently occurring keywords and the time periods in which they occurred.

[1893] "Based on the results of this survey, please identify departments with a high number of harassment reports and analyze the causes."

[1894] The above is an embodiment of the present invention.

[1895] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1896] Step 1: Data collection

[1897] The server collects data such as chat logs, emails, and survey results within the company. Specifically, it connects to a database server and retrieves the required data with a query. For example, execute the query "SELECT FROM chat_logs WHERE date BETWEEN '2023-01-01' AND '2023-01-31'" to retrieve chat logs for January. The input is the database query, and the output is the collected raw data.

[1898] Step 2: Data Preprocessing

[1899] The server preprocesses the collected data. Specifically, it cleans the text data (removes unnecessary characters and spaces) and tokenizes it (splits it into words and phrases). The preprocessed data is temporarily stored on the terminal. For example, the cleaned text data is saved as a CSV file. The input is the collected raw data, and the output is the preprocessed clean data.

[1900] Step 3: Analysis by generative AI model

[1901] The server inputs the preprocessed data into a generative AI model (GPT-4) to analyze harassment trends and patterns. The user creates a prompt to input to the generative AI model. For example, the prompt could be, "Please identify the harassment trends from the chat logs below." The input is the preprocessed data and the prompt, and the output is the analysis results by the generative AI model.

[1902] Step 4: Visualize the data

[1903] The server visualizes harassment trends and patterns based on the results of the generative AI model's analysis. Specifically, it uses Matplotlib to create graphs, and displays time periods when specific keywords frequently appear as bar graphs. The visualized data is displayed on the terminal. The input is the analysis results from the generative AI model, and the output is the visualized graph or chart.

[1904] Step 5: Generate reports

[1905] The server automatically generates a "January Harassment Trend Report" using LaTeX based on the visualized data and saves it in PDF format. The user checks the generated report and makes corrections or additional comments as necessary. The input is the visualized data, and the output is the automatically generated report.

[1906] (Application example 2)

[1907] Next, a description will be given of Application Example 2 of Form 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".

[1908] Conventional harassment prevention systems make it difficult to efficiently classify inquiries and reports related to harassment within the company and respond quickly according to their importance and urgency. It is also time-consuming to identify trends and patterns of harassment, visualize them, and generate reports. Furthermore, there is a lack of functionality to suggest specific countermeasures and preventive measures, which makes it difficult to take effective measures against harassment.

[1909] The identification process by the identification processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means. In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment in the company using generative AI and filtering them according to importance and urgency, a means for identifying trends and patterns of harassment using generative AI, a means for visualizing data and generating reports, a means for proposing measures and preventive measures against harassment, a means for collecting text data such as reports, chat logs, and emails from users through an application installed on a smartphone, a means for identifying trends and patterns of harassment from the collected data using a generative AI model, a means for visualizing the analysis results in graphs and charts, and a means for automatically generating a report based on the analysis results and proposing specific measures and preventive measures. This makes it possible to efficiently classify inquiries and reports related to harassment and to quickly respond to them, and to identify and visualize trends and patterns of harassment and propose specific measures and preventive measures.

[1910] "Generative AI" is an artificial intelligence technology that generates new information and patterns based on data.

[1911] "Harassment" refers to inappropriate language or behavior toward others in the workplace or any other environment.

[1912] "Inquiry" means a question or request for specific information or assistance.

[1913] "Reporting" refers to the act of providing information about a particular event or situation.

[1914] "Classification" refers to the grouping of data or information based on specific criteria.

[1915] "Filtering" refers to selecting data or information based on specific conditions.

[1916] A "trend" refers to a movement or flow toward a particular direction or pattern.

[1917] A "pattern" refers to a particular repeated form or arrangement.

[1918] "Visualization" refers to the visual representation of data or information.

[1919] "Report" means a document that compiles specific information or analytical results.

[1920] A "measure" refers to a specific action or measure to address a particular problem or issue.

[1921] "Preventive measures" refer to specific actions or steps taken to head off problems or issues before they occur.

[1922] A "smartphone" refers to a type of mobile phone that can connect to the Internet and use applications.

[1923] "Application" refers to a software program designed to provide a specific function or service.

[1924] "Chat log" refers to a record of conversations held in chat format.

[1925] "Email" refers to messages sent and received electronically.

[1926] "Data collection" refers to the act of gathering data for a specific purpose.

[1927] A "graph" refers to a diagram for visually representing data.

[1928] A "chart" refers to a table or diagram that visually represents data.

[1929] The system for implementing this invention uses generative AI to automatically classify inquiries and reports related to harassment in the workplace and filter them according to importance and urgency. It also uses generative AI to identify trends and patterns of harassment, visualize the data, and generate reports. It also has the ability to suggest countermeasures and preventative measures against harassment.

[1930] Hardware and Software Used

[1931] Hardware: Smartphones, servers

[1932] Software: Python, OpenAI API, Matplotlib, Pandas

[1933] Data processing and calculation

[1934] Data collection

[1935] Users input text data such as reports of harassment, chat logs, and emails through an application installed on their smartphones. This data is sent to a server and stored in a database.

[1936] AI analysis

[1937] The server inputs the collected data into a generative AI model (e.g., GPT-3) to identify trends and patterns of harassment, using prompts such as the following:

[1938] Examples of prompt statements

[1939] Identify trends and patterns of harassment in the text data below.

[1940] Text: My boss is nasty to me every day

[1941] Text: Colleagues ignoring me

[1942] Data Visualization

[1943] Based on the analysis results obtained from the generative AI model, the server uses Pandas and Matplotlib to visualize the data in graphs and charts, allowing users to visually confirm trends and patterns of harassment.

[1944] Report Generation

[1945] The server automatically generates a report based on the analysis results, which includes trends and patterns of harassment, as well as specific countermeasures and preventative measures, and outputs the report as a text file that users can download.

[1946] Examples

[1947] For example, if a user reports that "my boss is nasty every day," the generative AI model will identify the pattern of "nasty." Based on this information, the server will generate a graph showing that there are many reports of nasty behavior and suggest measures such as "regular counseling" in the report.

[1948] In this way, the invention is able to efficiently categorize and rapidly respond to harassment-related inquiries and reports, identify and visualize harassment trends and patterns, and suggest specific countermeasures and preventative measures.

[1949] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1950] Step 1:

[1951] Users input text data such as reports of harassment, chat logs, and emails through an application installed on their smartphones. The input data is then sent to a server by the application. The input data includes the specific details of the harassment, as well as the date and time.

[1952] Step 2:

[1953] The server saves the received text data in a database. At this time, it checks the format and content of the data and converts it into an appropriate format. For example, it converts the text data into JSON format and saves it.

[1954] Step 3:

[1955] The server inputs the stored text data into a generative AI model. The generative AI model (e.g., GPT-3) analyzes the data based on the prompt text and identifies harassment trends and patterns. Examples of prompt text are as follows:

[1956] Examples of prompt statements

[1957] Identify trends and patterns of harassment in the text data below.

[1958] Text: My boss is nasty to me every day

[1959] Text: Colleagues ignoring me

[1960] Step 4:

[1961] The server receives the analysis results from the generative AI model and stores them in a database, including any identified harassment trends or patterns.

[1962] Step 5:

[1963] The server visualizes the data based on the analysis results. It uses Pandas and Matplotlib to represent the analysis results in graphs and charts. For example, it generates a bar graph showing the high number of reports of sarcasm.

[1964] Step 6:

[1965] The server automatically generates reports based on the visualized data. The reports include trends and patterns of harassment, as well as specific countermeasures and preventative measures. The generated reports are output as text files.

[1966] Step 7:

[1967] Users can download and view the generated report through a smartphone application, which includes specific measures such as "regular counseling."

[1968] In this way, the system will be able to efficiently categorize and quickly respond to harassment-related inquiries and reports, identify and visualize harassment trends and patterns, and suggest specific countermeasures and preventive measures.

[1969] Example 3

[1970] Next, a third embodiment of the third embodiment will be described. 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".

[1971] In conventional harassment prevention systems, classification of harassment reports and inquiries, filtering of importance and urgency, and proposal of specific countermeasures and preventive measures are often done manually, making it difficult to respond quickly.In addition, there was a lack of means to identify trends and patterns of harassment and visualize the data, making it difficult to take effective measures.

[1972] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1973] In this invention, the server includes a means for automatically classifying inquiries and reports related to harassment within the company using generative AI and filtering them according to importance and urgency, a means for collecting data on harassment from each department within the company, a means for preprocessing the collected data and completing missing values ​​and correcting abnormal values, a means for inputting the preprocessed data into a generative AI model and identifying departments, time periods, and types of harassment with high frequency, a means for proposing specific countermeasures and preventive measures based on the analysis results of the generative AI model, and a means for notifying the user of the proposed contents. This enables rapid classification and filtering of harassment reports and inquiries, and allows for the proposal of effective countermeasures and preventive measures.

[1974] "Generative AI" is an artificial intelligence technology that generates new information and suggestions based on data.

[1975] "Harassment" refers to inappropriate verbal or physical actions taken against others in the workplace or in society, and is an act that causes mental or physical pain.

[1976] "Inquiry" means a question or inquiry made to request specific information or advice.

[1977] "Report" means a formal notification or recording made to convey information about a particular event or situation.

[1978] "Classification" refers to the grouping of collected data or information based on specific criteria.

[1979] "Filtering" refers to sorting data or information based on specific criteria and extracting only what is needed.

[1980] "Data collection" refers to the act of gathering information or data needed for a specific purpose.

[1981] "Preprocessing" refers to the process of preparing data for analysis by performing operations such as filling in missing values ​​and correcting outliers before conducting data analysis.

[1982] A "generative AI model" is a specific implementation of generative AI, and refers to algorithms and programs for generating new information and suggestions based on data.

[1983] "Analysis" refers to the act of analyzing collected data to find specific patterns or trends.

[1984] "Countermeasures" refers to specific actions or measures taken in response to a particular problem or issue.

[1985] "Preventive measures" refer to specific actions or steps taken to prevent a particular problem or issue before it occurs.

[1986] "Notice" means a formal communication or notification made to convey specific information or proposals to interested parties.

[1987] This invention is a system that uses generative AI to propose measures and preventive measures against harassment. A specific embodiment of this system is shown below.

[1988] The server first collects data on harassment from each department in the company, including the number of reported cases, the time of occurrence, the location of occurrence, the type of harassment, etc. For example, it collects report data from the sales department and survey results.

[1989] The server then preprocesses the collected data by completing missing values, detecting and correcting outliers, and standardizing the data and converting it into a format suitable for generative AI models, such as converting text data into numerical data.

[1990] The server inputs the preprocessed data into a generative AI model (for example, OpenAI's GPT-4) and performs analysis. The generative AI model analyzes the data and identifies departments, time periods, and types of harassment that occur frequently. For example, it identifies that harassment occurs frequently in the sales department between 3:00 and 5:00 p.m.

[1991] The server then uses the results of the generative AI model's analysis to suggest specific countermeasures and preventative measures, such as providing harassment prevention training to the sales department and strengthening monitoring between 3:00 and 5:00 p.m.

[1992] Finally, the server notifies the user of the proposed content. Specifically, it sends the content to the relevant parties via email or the company's internal messaging system. For example, it notifies the sales department manager that harassment prevention training should be conducted.

[1993] As a concrete example, consider the following scenario.

[1994] scenario:

[1995] Data was collected showing that harassment reports were more frequent during a certain time period (3:00 to 5:00 pm) in the sales department of a certain company. Based on this data, a generative AI model analyzes and proposes countermeasures.

[1996] Example prompt:

[1997] "There have been many reports of harassment in the sales department between 3:00 and 5:00 p.m. Please suggest measures and preventative measures for harassment during this time period."

[1998] Example output of a generative AI model:

[1999] "To combat harassment between the hours of 3pm and 5pm, here are some suggestions:

[2000] 1. Strengthen surveillance during this time period.

[2001] 2. Conduct harassment prevention training for all employees in the sales department.

[2002] 3. Improve the harassment reporting system and allow anonymous reporting.

[2003] 4. Make adjustments to reduce work load during this time.”

[2004] In this way, the server utilizes the generative AI model to provide a system that proposes measures and preventive measures against harassment and notifies the user. The flow of the identifi...

Claims

1. A means of collecting data on harassment from each department within the company; A means for pre-processing the collected data and inputting the pre-processed data into a generating AI to analyze harassment trends; A means for analyzing a correlation between the employee's emotional information analyzed using an emotion engine and the occurrence of harassment using the generating AI; A means for proposing measures and preventive measures against harassment based on the analysis results of the generating AI and the analysis results of the emotion engine; A system including:

2. 10. The system of claim 1, further comprising means for visualizing data and generating reports.

3. The system of claim 1 , wherein the preprocessing comprises imputing missing values ​​in the data, detecting and correcting outliers, and normalizing the data.

Images