system

Abstract

Provide a system. A means for collecting communication data; means for analyzing the communication data using natural language processing to identify problems and related keywords; A means for searching for relevant personnel from a database based on the analyzed keywords; A means for generating an answer using generative artificial intelligence when the person in charge cannot be found; The system includes a means for notifying the person or the generated answer.

Description

[Technical Field]

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

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

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

[0004] When a problem occurs in a company's project, it is necessary to quickly identify the person most suited to the problem and solve it efficiently. It is also necessary to generate appropriate solutions based on past cases and, if necessary, redirect the advice to the person in charge. With traditional methods, identifying the person in charge and generating advice takes time and effort, reducing work efficiency, so it is necessary to solve these problems. [Means for solving the problem]

[0005] The present invention provides a system including: means for collecting communication data; means for analyzing the communication data for problems and related keywords using natural language processing; means for searching a database for relevant personnel based on the analyzed keywords; means for generating an answer using generative artificial intelligence if the relevant personnel cannot be found; and means for notifying the relevant personnel or the generated answer. This makes it possible to quickly and efficiently identify the appropriate personnel and lead them to a solution when a problem occurs in a company's project. Furthermore, the generative artificial intelligence can provide advice and recommand the personnel as needed.

[0006] "Communication data" refers to data such as emails, chat history, and video conference transcripts sent and received through a company's internal communication tools.

[0007] "Natural language processing" is a technology that uses computers to understand, analyze, and generate human language.

[0008] A "problem" is a specific issue or obstacle that needs to be resolved and is described in the communication data.

[0009] "Keywords" are important words or phrases extracted from communication data to identify problems.

[0010] A "database" is a collection of information that stores past response records and information on personnel in a searchable manner.

[0011] A "person in charge" is an employee or official within a company who is qualified to handle a particular issue.

[0012] "Generative AI" is an AI technology that automatically generates new answers and advice based on past cases and data.

[0013] "Notification" is the act of communicating problems and answers to the person in charge or the user in real time. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0022] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0035] The present invention is a system for automatically identifying problems that arise in a company's projects and quickly finding the most suitable person to handle the problem. How this system is implemented will be specifically explained below.

[0036] System configuration

[0037] This system has a means to collect communication data from various communication tools (email, chat, video conferencing) in one place. Specifically, it consists of the following servers and software components:

[0038] The server collects communication data in real time.

[0039] The server analyzes the communication data using natural language processing technology.

[0040] Based on the analysis results, the server searches the database for the appropriate person in charge.

[0041] If no suitable person can be found, the server uses generative artificial intelligence to generate a solution.

[0042] The server notifies the user of the analysis results, the person in charge, and the generated answer.

[0043] Program processing

[0044] Data collection

[0045] The server collects communication data through email APIs, chat tool APIs, and video conferencing APIs. For example, it collects email data using a mail server API, obtains chat history using a chat tool API, and collects video conferencing transcripts using a Zoom API.

[0046] Data analysis

[0047] The server analyzes the collected communication data using natural language processing (NLP) technology. This analysis extracts problems from the text content of the communication data and identifies related keywords. For example, an NLP model can be used to extract the keywords "Project X," "progress delay," and "code bug" from an email that says, "Project X is not progressing."

[0048] Identifying the person in charge

[0049] Based on the analysis results, the server compares past correspondence records and staff information from the database to identify the most suitable staff member, searching for relevant keywords and evaluating the staff member's past performance and expertise.

[0050] Use of generative artificial intelligence

[0051] If no suitable person can be found, the server will automatically generate a solution using generative artificial intelligence, which references past cases and data to generate solutions to similar problems.

[0052] notification

[0053] Finally, the server notifies the person in charge or the user of the analysis results and countermeasures. Notifications are given via email, chat notifications, dashboard alerts, etc. This allows the user to quickly recognize the problem and take appropriate action.

[0054] Specific examples

[0055] Example 1: Email about a code bug

[0056] If a user sends an email saying "Project X isn't progressing. There might be a bug in the code," the server does the following:

[0057] 1. The server collects the email and retrieves the text content.

[0058] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[0059] 3. The server searches the database to identify the person who previously handled bugs for "Project X."

[0060] 4. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[0061] Example 2: Marketing Campaign Issues

[0062] If a user says in a Zoom meeting, "My marketing campaign is not producing the results I expected," the server performs the following process:

[0063] 1. The server collects the Zoom meeting transcript.

[0064] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[0065] 3. The server searches its database and, if it cannot find a specialist who has dealt with a similar campaign issue, it uses generative artificial intelligence to generate advice.

[0066] 4. The server notifies the user with the generated advice "Try a new strategy."

[0067] In this way, the system analyzes multiple communication data, identifies the appropriate person in charge, and notifies them quickly, thereby helping to resolve issues within the company.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] The server collects communication data within the company (emails, chat history, video conference transcripts). The data is obtained through the API of each communication tool and saved in internal storage in real time. At this stage, it is important to keep the latest information on communication data.

[0071] Step 2:

[0072] To analyze the collected communication data, the server first extracts text data, such as email bodies from mailboxes, message texts from chat histories, and video conference transcripts into text format.

[0073] Step 3:

[0074] The server applies natural language processing (NLP) techniques to the extracted text data, including identifying the problem and extracting relevant keywords. Specifically, it uses an NLP model to analyze key phrases and words in the text to understand the nature of the problem.

[0075] Step 4:

[0076] The server uses the keywords and issues identified by NLP to search a database that includes past case records and each agent's expertise to identify the most relevant agent.

[0077] Step 5:

[0078] The server then sends a notification to the identified personnel, which includes a summary of the problem, relevant keywords, and immediate actionable actions. The notification is delivered to the personnel via email, chat notification, or dashboard alert.

[0079] Step 6:

[0080] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[0081] Step 7:

[0082] The server notifies the user of the generated answer via email, chat notification, or dashboard alert, allowing the user to receive actionable advice and next steps.

[0083] Step 8:

[0084] The server stores all processing logs for future analysis and system improvement, including the processing time for each step, the resources used, and the notifications generated.

[0085] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting communication data to analyzing it, identifying the person in charge, notifying them, and using generative artificial intelligence.

[0086] Example 1

[0087] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0088] When a problem occurs in a company's project, it is difficult to quickly and accurately identify the problem and find the most appropriate person to handle it. Furthermore, if the right person cannot be found or the problem is complex, it becomes even more difficult to find a solution efficiently. To solve these issues, a system is needed that effectively utilizes communication data to automatically identify problems and find the right person to handle them.

[0089] 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.

[0090] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person in charge based on the analyzed keywords, means for generating an answer using generative AI if the person in charge is not found, means for notifying the person in charge or the generated answer, and means for executing each process of collecting, analyzing, searching for a person in charge, using generative AI, and notifying the person in charge using each API. This enables automatic collection and analysis of communication data, identification and notification of an appropriate person in charge, and generation of a solution using a generative AI model.

[0091] "Communications data" refers to data such as emails, chat history, and video conference transcripts obtained from an enterprise and related communication tools.

[0092] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, including the processes of tokenizing text, extracting keywords, and identifying issues.

[0093] "Keywords" refer to important words or phrases related to the problem that are extracted through analysis of communication data.

[0094] "Generative artificial intelligence" refers to artificial intelligence models that automatically generate new information and solutions based on past data and examples. Examples include generative AI models.

[0095] A "database" refers to a system that stores data such as past response records and staff information, and keeps it in a searchable format.

[0096] "API" stands for Application Programming Interface, and refers to an interface that enables data exchange and function utilization between different software.

[0097] "Notification" refers to the means by which users and other interested parties are informed of the analysis results, the most appropriate person, or the generated solution.

[0098] "Server" refers to a computer system that performs the processes of collecting communication data, analyzing it, searching for personnel, using generated AI, and sending notifications.

[0099] This invention is a system for automatically identifying problems that arise in corporate projects and quickly finding the most appropriate person to handle them. This system includes the processes of collecting and analyzing communication data, identifying the person in charge, generating solutions using generative artificial intelligence, and notifying the person in charge.

[0100] System configuration

[0101] Hardware and Software

[0102] The server is a central system for collecting communication data, analyzing it using natural language processing, identifying responsible parties, generating solutions using generative AI models, and sending notifications.

[0103] APIs (Application Programming Interfaces) are used to collect data from email, chat tools, and video conferencing servers. Specifically, APIs for email servers (e.g., Gmail API), APIs for chat tools (e.g., Slack API), and APIs for video conferencing (e.g., Zoom API) are used.

[0104] Use natural language processing libraries (e.g., spaCy, BERT) to analyze communication data and extract important keywords.

[0105] The database is a system that stores records of past problem responses and information on personnel in charge, allowing the server to search for them.

[0106] Generative AI models (e.g., GPT-4®) are used to automatically generate countermeasures when no suitable personnel can be found.

[0107] A notification system (e.g., SMTP server, chat tool notification API, WebSocket or Push API) is used to notify users and personnel of analysis results and solutions.

[0108] Examples of data collection

[0109] The server collects users' emails, chat history, and video conference transcripts. For example, it retrieves incoming emails via the Gmail API, retrieves chat history for specific channels using the Slack API, and retrieves meeting transcripts using the Zoom API.

[0110] Specific examples of data analysis

[0111] The server analyzes the collected communication data using natural language processing technology. For example, it uses the NLP library spaCy or the BERT model to tokenize the text and extract keywords related to the problem. For example, from an email that says "Project X is not progressing," it extracts the keywords "Project X," "Progress delay," and "Code bug."

[0112] Specific examples of personnel

[0113] The server searches the database for relevant personnel based on the keywords from the analysis results. For example, it retrieves past response records related to "Project X" or "code bugs" from the database and selects the most suitable person.

[0114] Examples of the use of generative artificial intelligence

[0115] If no suitable person is found, the server generates a solution using a generative AI model (e.g., GPT-4). For example, enter a prompt such as "Please propose a solution to the progress delay in project X" and obtain the generated solution.

[0116] Specific examples of notifications

[0117] The server notifies the user or person in charge of the analysis results and generated solutions. For example, it can send notifications by email using an SMTP server, send chat notifications using the Slack API, or display alerts on a dashboard using WebSocket. This allows users to quickly recognize problems and take appropriate action.

[0118] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0119] Step 1: Data collection

[0120] The server collects communication data from email APIs, chat tool APIs, and video conferencing APIs. Specifically, it uses the Gmail API to obtain received emails, the Slack API to obtain chat history, and the Zoom API to obtain video conferencing transcripts. It sends authentication information and data acquisition requests from each API as input, and obtains the acquired communication data in a structured data format (e.g., JSON) as output.

[0121] Step 2: Data analysis

[0122] The server analyzes the collected communication data using natural language processing technology. Specifically, it uses a natural language processing library (e.g., spaCy, BERT) to tokenize the acquired data and extract keywords. It takes the collected communication data (text data) as input and generates structured data containing issues and related keywords as output.

[0123] Step 3: Identify the person in charge

[0124] The server searches the database for relevant personnel based on the keywords from the analysis results. It uses the analyzed keywords as input and executes a database query. Specifically, it searches past problem response records and personnel information, and obtains information on the most suitable personnel as output. For example, it selects the appropriate personnel based on keywords such as "Project X" and "code bug."

[0125] Step 4: Use generative AI

[0126] If no suitable person can be found, the server uses a generative AI model (e.g., GPT-4) to generate a solution. As input, it provides a prompt (e.g., "Please propose a solution to the delay in project X") generated based on the problem analysis results, and as output, it obtains the solution generated by the generative AI model. This output is filtered and corrected as necessary to create the final answer.

[0127] Step 5: Notification

[0128] The server notifies the user or person in charge of the analysis results and generated solutions. Specifically, it sends email notifications via an SMTP server, sends chat notifications using the Slack API, and displays alerts in real time on a dashboard using WebSocket or Push API. The notification content (analysis results, person in charge information, generated solutions) is given as input, and a confirmation message that the notification has been sent is received as output.

[0129] This series of steps creates a system that automatically and consistently collects and analyzes communication data, identifies responsible parties, proposes solutions using generative artificial intelligence, and finally notifies users.

[0130] (Application example 1)

[0131] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0132] When a problem occurs in a company's project or factory, it is difficult to find the most suitable person to deal with it quickly and accurately. Furthermore, when a suitable person cannot be found, it is necessary to automatically generate a solution. Especially on the production line, where an immediate response is required when an abnormality occurs, a system that can efficiently achieve this is needed.

[0133] 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.

[0134] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating an answer using generative AI if no person is found, means for notifying the person in charge or the generated answer, means for monitoring abnormalities on the production line in real time, identifying the problem when it occurs, and promptly notifying the appropriate engineer, and means for proposing an optimal solution via a generative AI model using automatically generated prompt sentences. This enables prompt and effective response when problems occur within a company or on the production line, and for identifying and notifying the appropriate person in charge.

[0135] "Communications data" refers to records of all digital communications within and outside a company, such as emails, chat histories, video conference transcripts, and production line monitoring data.

[0136] "Natural language processing" refers to the technology that allows computers to analyze, understand, and generate human language, and is used to extract issues and related keywords.

[0137] "Analyzed keywords" refer to issues and related important words and phrases extracted from communication data using natural language processing technology.

[0138] A "database" refers to a system that stores data such as information about the person in charge and past problem-solving history.

[0139] "Generative artificial intelligence" refers to technology that automatically generates optimal solutions to problems by referring to past cases and data.

[0140] "Notification" refers to the act of communicating the analysis results or generated answers to the person in charge or the user, and is done by means of email, chat notification, etc.

[0141] A "production line" refers to a series of devices and machines in production facilities installed within a factory, including their layout for efficiently producing products.

[0142] "Abnormality monitoring" refers to the function of detecting abnormal behavior or problems on the production line and reporting them in real time.

[0143] A "prompt sentence" refers to the input text that a generative artificial intelligence uses to receive the information and requests necessary to solve a problem.

[0144] A "generative AI model" refers to an artificial intelligence model used to suggest optimal solutions based on past data and specific problems.

[0145] This invention is a system for quickly and effectively solving problems in projects and production lines within a company or factory. The system is implemented as follows, centered around a server.

[0146] Data collection

[0147] The server collects various communication data. Specifically, it obtains emails, chat history, and video conference transcripts through email, chat tool, and video conference APIs. It also collects real-time monitoring data from the production line. This aggregates a record of all digital communications within and outside the company.

[0148] Data analysis

[0149] The collected communication data is analyzed on the server using natural language processing (NLP) technology. This analysis analyzes the text content of the communication data and extracts keywords related to the problem. The NLPParser module is specifically used for NLP technology. For example, from an email that says, "Project X isn't progressing. There may be a bug in the code," keywords such as "Project X," "bug," and "code" are extracted.

[0150] Identifying the person in charge

[0151] Based on the analyzed keywords, the server checks the database for past response records and staff information to identify the most suitable staff member. The database stores staff information and past problem-solving history. If an appropriate staff member cannot be found, a generative artificial intelligence (AIGenerator module) is used to automatically generate a response. For example, for the data "The machine has stopped. The cause is unknown," the AI ​​model generates the solution "Please check the power supply."

[0152] notification

[0153] The server notifies the user of the generated analysis results, the person in charge, or the generated answer. Notification methods include email, chat notifications, and dashboard alerts. By receiving this notification, the user can quickly recognize the problem and take appropriate action. For notifications, the Notifier module is used.

[0154] Specific examples

[0155] In a production line, if a worker sends a message saying "The machine on production line A has stopped. The cause is unknown":

[0156] 1. The server collects chat data.

[0157] 2. Use NLP technology to extract the keywords "Production Line A," "Machine Stopped," and "Cause Unknown."

[0158] 3. Search the database to identify engineers who have previously handled machine stoppages on "Production Line A."

[0159] 4. Notify the engineer you found that "The machine on production line A has stopped. The cause is unknown."

[0160] Prompt Sentence Examples

[0161] Prompt to be given to the generative AI model:

[0162] A machine stoppage problem has occurred in Project X. Please suggest a solution based on past data and case studies.

[0163] This prompt allows the generative AI model to refer to past cases and suggest specific countermeasures such as "Please check the power supply."

[0164] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0165] Step 1:

[0166] The server collects communication data through email APIs, chat tool APIs, video conference APIs, and production line monitoring data. This data includes email text, chat logs, video conference minutes, production line operation data, etc. The input is various communication data, and the output is aggregated communication data.

[0167] Step 2:

[0168] The server analyzes the collected communication data using the NLPParser module. The collected data is converted into text data and natural language processing technology is applied to extract issues and related keywords. This analysis extracts meaningful keywords such as "Project X," "bug," and "machine down." The input is the aggregated communication data, and the output is the extracted keywords.

[0169] Step 3:

[0170] The server uses the UserDatabase module to search the database based on the analyzed keywords. It searches for agent information that matches the keywords and obtains the agent's past correspondence records and skill information. The input is the extracted keywords, and the output is the most suitable agent information.

[0171] Step 4:

[0172] If the server cannot find a suitable agent, it uses the AI ​​Generator module to automatically generate a solution. This module generates a prompt sentence and inputs it into a generative AI model to suggest the optimal solution based on past data and examples. For example, a specific solution such as "Please check the power supply" is generated. The input is the extracted keywords, and the output is the generated solution.

[0173] Step 5:

[0174] The server uses the Notifier module as a notification method to notify the user of the identified agent or the generated solution. Notifications include email and chat notifications. The user receives the notification and quickly recognizes the problem and takes action. The input is the information of the best agent or the generated solution, and the output is the notification message.

[0175] Specific operations of each processing step

[0176] Step 1:

[0177] The server makes an API call to collect data from each communication data source, e.g. requests.get('https: / / api.email-provider.com / emails')

[0178] The collected data is aggregated in one place to create a set of data sets.

[0179] Step 2:

[0180] The server calls the NLPParser module to begin parsing the text data. Example: nlp_parser.extract_keywords(data)

[0181] Apply keyword extraction algorithms to extract key terms and phrases.

[0182] Step 3:

[0183] The server uses the UserDatabase module to search the database and find the best match based on the keywords, e.g. user_db.search_user(key_info)

[0184] Compare the past response records and skill information of each agent to identify the most suitable agent.

[0185] Step 4:

[0186] The server uses the AIGenerator module to generate prompt sentences and feed them into the generative AI model. Example: ai_generator.generate_solution(key_info)

[0187] Obtain the optimal solution from the generative AI model and document the solution to the problem.

[0188] Step 5:

[0189] The server uses the Notifier module to notify the user of the identified agent or generated solution, e.g. notifier.send(content, notification_type)

[0190] Generate notification messages and send them as emails or chat messages.

[0191] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0192] This invention is a system that automatically identifies the problem and user emotions when a problem occurs in a company's project, and quickly finds the most appropriate person to solve the problem. It also uses generative artificial intelligence to generate solutions as needed, and provides appropriate notifications to efficiently solve the problem. An important component of this invention is the incorporation of an emotion engine, which analyzes the user's emotions and re-commands the notification content and the person in charge.

[0193] System configuration

[0194] The system consists of the following main components:

[0195] Means of collecting communication data

[0196] A means of analyzing issues and related keywords using natural language processing

[0197] A means of searching for personnel based on analyzed keywords

[0198] A means of generating answers using generative artificial intelligence

[0199] A means of notifying the assignee or generated response

[0200] Emotion Engine

[0201] Program processing

[0202] Data collection

[0203] The server collects data through APIs of various communication tools (email, chat, video conferencing) and stores it in real time in internal storage, allowing you to always track the latest communication content.

[0204] Data analysis

[0205] The server analyzes the collected data using natural language processing (NLP) technology to extract keywords related to the problem. For example, from an email saying "Project X is not progressing," it identifies keywords such as "Project X," "progress delay," and "code bug."

[0206] Emotion analysis

[0207] The emotion engine recognizes the user's emotions from the analyzed text data, and this process can identify the user's emotional state, such as whether they are feeling stressed or urgent.

[0208] Identifying the person in charge

[0209] The server searches the database for the most suitable agent based on the analysis and sentiment analysis results. For example, it identifies agents who have solved similar problems in the past. Based on the sentiment analysis results, it may re-command an agent who can provide a more appropriate response.

[0210] Use of generative artificial intelligence

[0211] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[0212] notification

[0213] The server notifies the person in charge or the user of the analysis results and generated answers. The notification includes a summary of the problem, relevant keywords, and appropriate countermeasures based on the sentiment analysis results. Notification methods include email, chat notifications, dashboard alerts, etc.

[0214] Specific examples

[0215] Example 1: Email about a code bug

[0216] When a user sends an email saying "Project X isn't progressing. I think there might be a bug in the code," the server does the following:

[0217] 1. The server collects the email and retrieves the text content.

[0218] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[0219] 3. The emotion engine recognizes the user's emotions and identifies emotions such as "tension" and "anxiety."

[0220] 4. The server searches the database to identify the person who previously handled bugs for "Project X."

[0221] 5. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[0222] Example 2: Marketing Campaign Issues

[0223] If a user says in a Zoom meeting, "My marketing campaigns aren't performing as expected," the server does the following:

[0224] 1. The server collects the Zoom meeting transcript.

[0225] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[0226] 3. The emotion engine recognizes the user's emotions and detects "disappointment" and "sense of challenge."

[0227] 4. The server searches its database and, if no representative who has dealt with a similar campaign issue is found, uses generative artificial intelligence to generate advice.

[0228] 5. The server notifies the user with the generated advice "Try a new strategy."

[0229] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[0230] The processing flow will be explained below.

[0231] Step 1:

[0232] The server collects communication data from the company's internal communication tools (email, chat, video conferencing). It uses the API of each communication tool to obtain the latest data in real time and saves it in internal storage. For example, the server might obtain email content using a mail server API, collect chat history through a chat tool API, and obtain transcripts using a video conferencing API.

[0233] Step 2:

[0234] The server converts the collected communication data into text format. For example, by extracting email text, chat messages, and meeting transcripts as text data, it makes the data easier to analyze. This ensures that all data is handled in a consistent format.

[0235] Step 3:

[0236] The server analyzes the text data using natural language processing (NLP) technology. This analysis identifies problems from the text content and extracts related keywords. For example, from the text "Project X is not progressing," the server extracts the keywords "Project X," "Delayed progress," and "Code bug."

[0237] Step 4:

[0238] The server uses an emotion engine to recognize the user's emotions from the text data. This identifies emotions such as stress, anxiety, and disappointment felt by the user. For example, the server analyzes emotions such as "anxiety" and "stress" from the text "I'm in trouble because the project has stalled." This emotional information has an important impact on subsequent processing.

[0239] Step 5:

[0240] The server searches the database for relevant agents based on the analyzed keywords and emotion information. The server then references past correspondence records to identify the most appropriate agent. This search utilizes information such as the agent's expertise and past performance. The server also takes emotion information into account to select the agent who can best respond to the user's emotions.

[0241] Step 6:

[0242] The server then sends a notification to the identified agent, which includes a summary of the problem, relevant keywords, and user sentiment. The notification can be delivered to the agent via email, chat notification, or dashboard alert, allowing the agent to respond quickly to the problem.

[0243] Step 7:

[0244] If no suitable person can be found, the server uses generative artificial intelligence to generate an answer. This AI automatically creates a solution by referencing past cases and data. For example, if the problem is related to a code bug, the server generates advice such as "Check the coding rules and add test cases."

[0245] Step 8:

[0246] The server notifies the user of the generated answer. This notification includes specific advice created by the generative AI and tells the user what action to take next. Notification methods include email, chat notification, or dashboard alert. The user receives the notification and can act on the provided advice.

[0247] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[0248] Example 2

[0249] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0250] In conventional corporate project management systems, when a problem occurs in a project, it is difficult to quickly and accurately identify the problem and the user's feelings, and to find the most appropriate person to handle it. Furthermore, if an appropriate person cannot be found, it takes a long time to resolve the problem, which is an issue.

[0251] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for identifying the user's emotions using the analyzed keywords and a sentiment analysis engine, means for searching a database for a relevant person in charge based on the analysis results, means for generating an answer using generative artificial intelligence if no person in charge is found, and means for notifying the person in charge or the generated answer. This enables a quick and efficient response when a problem occurs.

[0252] "Communication data" is a general term for text data generated and collected through communication means, such as emails, chat histories, and video conference transcripts.

[0253] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is a processing technology that includes keyword extraction and problem recognition.

[0254] A "problem" is an unexpected situation or difficulty that arises in a project or task and requires a solution.

[0255] "Related keywords" are important words and phrases related to the problem or business that are extracted from the communication data.

[0256] An "emotion analysis engine" is a technology for identifying a user's emotions (e.g., tension, anxiety, disappointment, etc.) from text data.

[0257] A "personnel" is a person within a company who is responsible for solving problems for a particular task or project.

[0258] "Generative AI" is an AI technology that automatically generates solutions and answers based on past cases and data.

[0259] "Notification" refers to the action or means for informing the user or person in charge of the analysis results or generated answers, and includes email and chat notifications.

[0260] This invention is a system for quickly and efficiently resolving project problems that arise within a company. This system collects communication data, analyzes the problem and related keywords using natural language processing technology, identifies the most appropriate person to handle the problem based on the analysis results, and, in some cases, generates a solution using generative artificial intelligence and notifies the user of the solution.

[0261] Hardware or software used

[0262] The server is the main component of this system, and uses the following hardware and software:

[0263] Hardware: High-performance computing servers (e.g. general-purpose servers)

[0264] software:

[0265] Natural language processing libraries (e.g., natural language processing APIs provided by popular manufacturers)

[0266] Sentiment analysis engine (e.g., general analysis engine API)

[0267] Generative artificial intelligence models (e.g., widely used generative AI models)

[0268] Notification systems (e.g. email API, chat notification API)

[0269] System configuration

[0270] The system consists of the following main components:

[0271] 1. Collection of Communications Data:

[0272] The server collects data using APIs for communication tools such as email, chat, and video conferencing. For example, it uses email APIs and video conferencing APIs to obtain communication data in real time and saves it in internal storage.

[0273] 2. Data Analysis:

[0274] The server analyzes the collected communication data using natural language processing (NLP) technology. Using NLP technology, it extracts problems and related keywords. For example, from an email that says "Project X isn't progressing," it extracts keywords such as "Project X," "progress delay," and "code bug."

[0275] 3. Emotion analysis:

[0276] The emotion engine recognizes the user's emotions from the analyzed text data. The emotion analysis engine identifies emotions such as "tension," "anxiety," and "disappointment" that the user is feeling.

[0277] 4. Identify the person in charge:

[0278] The server searches the database for the most suitable agent based on the analysis and emotion analysis results, and can refer to past cases to identify the agent who can handle the specific problem or emotional state.

[0279] 5. Use of generative artificial intelligence:

[0280] If the server cannot find a suitable person, it uses a generative artificial intelligence model to generate a solution. It references accumulated data and automatically generates a solution based on similar past cases.

[0281] 6. Notice:

[0282] The server notifies the person in charge or the user of the analysis results and generated solutions via email, chat notification, dashboard alerts, etc. The notification includes a summary of the problem, related keywords, sentiment analysis results, and the optimal response.

[0283] Specific examples

[0284] Example 1: Email about a code bug

[0285] If a user sends an email stating "Project X isn't progressing. I think there might be a bug in the code," the system will respond with the following prompt:

[0286] procedure:

[0287] 1. The server collects emails using an email API.

[0288] 2. The server uses a natural language processing API to analyze the content of the email and extract the keywords "Project X," "code," and "bug."

[0289] 3. The emotion engine analyzes the content of the email and identifies emotions such as "tension" and "anxiety."

[0290] 4. The server searches the database to identify the appropriate person who handled the bug for "Project X."

[0291] 5. Once the appropriate person has been identified, the server uses the notification system to send a notification to the person saying, "There is a suspected bug in the code of Project X."

[0292] Example 2: Marketing Campaign Issues

[0293] If a user says in a video conference, "My marketing campaigns aren't performing as expected," the system will respond with the following prompt:

[0294] procedure:

[0295] 1. The server collects the transcript of the meeting using the video conferencing API.

[0296] 2. The server uses a natural language processing API to analyze the transcript and extract the keywords "marketing campaign," "results," and "failed."

[0297] 3. The emotion engine analyzes the content of the meeting and identifies emotions such as "disappointment" and "sense of challenge."

[0298] 4. The server searches the database for a suitable agent, and if not found, uses a generative artificial intelligence model to generate advice such as "Try a new strategy."

[0299] 5. The server uses a notification system to notify the user of the generated advice.

[0300] In this way, the system of the present invention efficiently supports problem-solving within companies by performing a series of processes, including collecting communication data, analyzing it, recognizing emotions, identifying the person in charge, and using generative artificial intelligence and sending notifications.

[0301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0302] Step 1: Data collection

[0303] The server collects communication data such as emails, chat histories, and video conference transcripts. Specifically, it does the following:

[0304] Input: Requests to each communication tool's API (email API, chat API, video conferencing API)

[0305] Data processing: new messages and meeting transcripts retrieved via API requests

[0306] Output: Save the acquired communication data to the internal storage.

[0307] For example, a server calls an email API to retrieve new emails and save them in storage.

[0308] Step 2: Data analysis

[0309] The server analyzes the collected communication data and extracts the problem and related keywords. The specific operations are as follows:

[0310] Input: Text data stored in internal storage

[0311] Data processing: Extracting keywords and issues from text data using natural language processing (NLP) techniques

[0312] Output: Extracted keywords and issues

[0313] For example, the server calls a natural language processing API to extract the keywords "Project X," "Delayed progress," and "Code bug" from the text "Project X is not progressing."

[0314] Step 3: Sentiment Analysis

[0315] The emotion engine recognizes the user's emotion from the analyzed text data. The specific operation is as follows:

[0316] Input: Text data extracted by data analysis

[0317] Data processing: Use a sentiment analysis engine to identify sentiment categories from text data

[0318] Output: Identified emotion (e.g., "tension," "anxiety," "disappointment")

[0319] For example, an emotion engine can analyze the text "Project X isn't progressing" and identify the emotions "tension" and "anxiety."

[0320] Step 4: Identify the person in charge

[0321] The server searches the database for the most suitable agent based on the analysis results and the sentiment analysis results. The specific operations are as follows:

[0322] Input: Extracted keywords and identified sentiments

[0323] Data manipulation: Performing database queries to find the right person

[0324] Output: Optimal Rep

[0325] For example, the server might search the database for keywords like "Project X," "progress delay," and "code bug" to identify people who have solved similar problems in the past.

[0326] Step 5: Use generative AI

[0327] If the server cannot find a suitable person, it uses generative artificial intelligence to generate a solution. The specific operation is as follows:

[0328] Input: Keywords and sentiment analysis results

[0329] Data processing: Invoking generative AI to generate solutions

[0330] Output: The generated solution

[0331] For example, a generative artificial intelligence model generates a solution to the problem of "delays in the progress of Project X."

[0332] Step 6: Notification

[0333] The server notifies the person in charge or the user of the analysis results and generated solutions. The specific operations are as follows:

[0334] Input: Assignee or generated solution

[0335] Data processing: Creating notification messages

[0336] Output: Email, chat notification, dashboard alert

[0337] For example, the server might use a notification system to send a message to a responsible party saying, "There is a suspected bug in the code for project X."

[0338] In this way, the system efficiently supports problem-solving within companies through the steps of data collection, data analysis, sentiment analysis, identifying responsible parties, utilizing generative artificial intelligence, and notification.

[0339] (Application example 2)

[0340] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0341] In factories, various problems occur daily with the operation of robots and various equipment. Quickly identifying these problems and finding the appropriate person or solution is essential for improving productivity and streamlining troubleshooting. However, with conventional systems, the process from problem detection to resolution was complicated and took a lot of time and effort. In addition, emotion analysis was not incorporated, making it difficult to respond efficiently while taking into account the urgency of the problem and the emotional state of the personnel.

[0342] 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.

[0343] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating a response using generative artificial intelligence if the person is not found, means for notifying the person or the generated response, means including an emotion engine for recognizing the emotional state of the analyzed communication, means for coordinating an appropriate response based on the recognized emotional state, and means for including communication data provided by robots in the factory. This makes it possible to quickly and efficiently identify and analyze problems occurring in the factory and propose appropriate people or solutions.

[0344] "Communications data" refers to information collected within a factory or other environment in the form of emails, chat histories, video conference transcripts, sensor data from robots, etc.

[0345] "Natural language processing" is a technology for understanding text information from communication data and analyzing problems and related keywords.

[0346] "Keywords" are important words or phrases extracted through natural language processing to identify issues and related information.

[0347] A "database" is a collection of information that searches for relevant personnel based on analyzed keywords.

[0348] "Generative AI" refers to artificial intelligence technology that automatically generates answers and suggestions to solve problems.

[0349] An "emotion engine" is a device or program that recognizes the user's emotional state from analyzed communication data and adjusts appropriate responses based on that information.

[0350] A "personnel" is a person with specialized knowledge and skills for solving a problem.

[0351] A "robot" is a machine or device used to automate work in a factory.

[0352] "Means of notification" refers to the means for notifying the relevant personnel or systems of the analysis results and generated solutions.

[0353] The present invention is a system for quickly and efficiently identifying problems occurring within a factory and recommending appropriate personnel or solutions. The system is composed of the following main components:

[0354] Hardware and Software Configuration

[0355] server

[0356] The server has the following functions:

[0357] 1. Communication data collection: Collect various communication data provided by robots and operators in the factory. Through API access, obtain emails, chat history, video conference transcripts, and sensor data from robots in real time.

[0358] 2. Data analysis: The collected data is analyzed using natural language processing (NLP) technology to extract keywords related to the problem. Examples of NLP technology used include TextBlob.

[0359] 3. Use of emotion engine: Recognize the user's emotional state from the analyzed text data. The emotion engine identifies the urgency and stress the user (operator or robot) is feeling.

[0360] 4. Agent Search: Based on the results of the analysis and sentiment analysis, the database is searched for the most suitable agent. Agents are identified based on their past experience and skill sets stored in the database.

[0361] 5. Use of generative AI: If no suitable person can be found, a solution can be automatically generated using generative AI, which learns from past cases and provides solutions to similar problems.

[0362] 6. Notification: Notify personnel or users of the analysis results and generated solutions. Notification methods include email, chat notifications, and dashboard alerts.

[0363] Terminal

[0364] User devices that can be used to access the system include PCs, smartphones, and tablets.

[0365] Specific examples

[0366] Example 1: Case of a sensor abnormality in a factory robot

[0367] The server collects communication data from the robot indicating that the sensor is malfunctioning.

[0368] The data is analyzed using natural language processing technology to extract keywords such as "sensor malfunction" and "robot."

[0369] An emotion engine is used to analyze user emotions and identify "anxiety" and "urgency."

[0370] The system searches the database for staff who have dealt with similar problems in the past, and if no such staff is found, it uses generative artificial intelligence to generate a solution.

[0371] Notify generated solutions and assignees.

[0372] Prompt Sentence Examples

[0373] "Please suggest a solution if the robot's battery is rapidly depleting."

[0374] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0375] Step 1:

[0376] The server collects communication data provided by robots and operators in the factory. Specifically, emails, chat history, video conference transcripts, and sensor data from the robots are obtained in real time through API access and stored in internal storage. The input is a variety of communication data, and the output is data ready for analysis.

[0377] Step 2:

[0378] The server analyzes the collected communication data using natural language processing (NLP). The specific operations performed here are text extraction and keyword analysis. For example, TextBlob is used to extract keywords such as "sensor malfunction" and "robot." The input is the collected communication data, and the output is the extracted keywords.

[0379] Step 3:

[0380] The server recognizes the user's emotional state from the text data analyzed using the emotion engine. In this step, the emotion the user is feeling, such as "anxiety" or "urgency," is identified. The emotion engine performs emotion analysis on the input text data, and the identified emotional state is output.

[0381] Step 4:

[0382] The server searches the database for relevant staff members based on the analysis and sentiment analysis results. Specifically, it searches for staff members who have solved similar problems in the past and identifies the most suitable staff member. The input is keywords and sentiment analysis results, and the output is information about the identified staff member.

[0383] Step 5:

[0384] If the server cannot find a suitable person, it uses generative AI to automatically generate a solution. Here, it references past cases and generates solutions to similar problems. The input is the extracted keywords, and the output is the solution generated by the AI.

[0385] Step 6:

[0386] The server notifies the person in charge or the user of the analysis results and the generated solution. In this step, notifications are made via email, chat notifications, or dashboard alerts. The input is the generated solution and the person in charge information, and the output is the notification result sent to the user.

[0387] Example operation

[0388] As an example, consider the case where a factory robot reports a "sensor malfunction."

[0389] Step 1: Collect communication data from the robot regarding "sensor malfunctions."

[0390] Step 2: Analyze the collected data for keywords such as "sensor malfunction" and "robot."

[0391] Step 3: Use the emotion engine to recognize the emotion "anxiety" from the data.

[0392] Step 4: Search the database to identify the person who responded to the "sensor malfunction."

[0393] Step 5: If no suitable person can be found, use generative artificial intelligence to generate a solution.

[0394] Step 6: Notify the person or user of the generated solution.

[0395] Example prompt sentence:

[0396] "Please suggest a solution if the robot's battery is rapidly depleting."

[0397] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0398] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0399] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0400] [Second embodiment]

[0401] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0402] 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.

[0403] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0404] 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.

[0405] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0406] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0407] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0408] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0409] 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.

[0410] 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.

[0411] 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.

[0412] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0413] The present invention is a system for automatically identifying problems that arise in a company's projects and quickly finding the most suitable person to handle the problem. How this system is implemented will be specifically explained below.

[0414] System configuration

[0415] This system has a means to collect communication data from various communication tools (email, chat, video conferencing) in one place. Specifically, it consists of the following servers and software components:

[0416] The server collects communication data in real time.

[0417] The server analyzes the communication data using natural language processing technology.

[0418] Based on the analysis results, the server searches the database for the appropriate person in charge.

[0419] If no suitable person can be found, the server uses generative artificial intelligence to generate a solution.

[0420] The server notifies the user of the analysis results, the person in charge, and the generated answer.

[0421] Program processing

[0422] Data collection

[0423] The server collects communication data through email APIs, chat tool APIs, and video conferencing APIs. For example, it collects email data using a mail server API, obtains chat history using a chat tool API, and collects video conferencing transcripts using a Zoom API.

[0424] Data analysis

[0425] The server analyzes the collected communication data using natural language processing (NLP) technology. This analysis extracts problems from the text content of the communication data and identifies related keywords. For example, an NLP model can be used to extract the keywords "Project X," "progress delay," and "code bug" from an email that says, "Project X is not progressing."

[0426] Identifying the person in charge

[0427] Based on the analysis results, the server compares past correspondence records and staff information from the database to identify the most suitable staff member, searching for relevant keywords and evaluating the staff member's past performance and expertise.

[0428] Use of generative artificial intelligence

[0429] If no suitable person can be found, the server will automatically generate a solution using generative artificial intelligence, which references past cases and data to generate solutions to similar problems.

[0430] notification

[0431] Finally, the server notifies the person in charge or the user of the analysis results and countermeasures. Notifications are given via email, chat notifications, dashboard alerts, etc. This allows the user to quickly recognize the problem and take appropriate action.

[0432] Specific examples

[0433] Example 1: Email about a code bug

[0434] If a user sends an email saying "Project X isn't progressing. There might be a bug in the code," the server does the following:

[0435] 1. The server collects the email and retrieves the text content.

[0436] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[0437] 3. The server searches the database to identify the person who previously handled bugs for "Project X."

[0438] 4. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[0439] Example 2: Marketing Campaign Issues

[0440] If a user says in a Zoom meeting, "My marketing campaign is not producing the results I expected," the server performs the following process:

[0441] 1. The server collects the Zoom meeting transcript.

[0442] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[0443] 3. The server searches its database and, if it cannot find a specialist who has dealt with a similar campaign issue, it uses generative artificial intelligence to generate advice.

[0444] 4. The server notifies the user with the generated advice "Try a new strategy."

[0445] In this way, the system analyzes multiple communication data, identifies the appropriate person in charge, and notifies them quickly, thereby helping to resolve issues within the company.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The server collects communication data within the company (emails, chat history, video conference transcripts). The data is obtained through the API of each communication tool and saved in internal storage in real time. At this stage, it is important to keep the latest information on communication data.

[0449] Step 2:

[0450] To analyze the collected communication data, the server first extracts text data, such as email bodies from mailboxes, message texts from chat histories, and video conference transcripts into text format.

[0451] Step 3:

[0452] The server applies natural language processing (NLP) techniques to the extracted text data, including identifying the problem and extracting relevant keywords. Specifically, it uses an NLP model to analyze key phrases and words in the text to understand the nature of the problem.

[0453] Step 4:

[0454] The server uses the keywords and issues identified by NLP to search a database that includes past case records and each agent's expertise to identify the most relevant agent.

[0455] Step 5:

[0456] The server then sends a notification to the identified personnel, which includes a summary of the problem, relevant keywords, and immediate actionable actions. The notification is delivered to the personnel via email, chat notification, or dashboard alert.

[0457] Step 6:

[0458] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[0459] Step 7:

[0460] The server notifies the user of the generated answer via email, chat notification, or dashboard alert, allowing the user to receive actionable advice and next steps.

[0461] Step 8:

[0462] The server stores all processing logs for future analysis and system improvement, including the processing time for each step, the resources used, and the notifications generated.

[0463] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting communication data to analyzing it, identifying the person in charge, notifying them, and using generative artificial intelligence.

[0464] Example 1

[0465] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0466] When a problem occurs in a company's project, it is difficult to quickly and accurately identify the problem and find the most appropriate person to handle it. Furthermore, if the right person cannot be found or the problem is complex, it becomes even more difficult to find a solution efficiently. To solve these issues, a system is needed that effectively utilizes communication data to automatically identify problems and find the right person to handle them.

[0467] 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.

[0468] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person in charge based on the analyzed keywords, means for generating an answer using generative AI if the person in charge is not found, means for notifying the person in charge or the generated answer, and means for executing each process of collecting, analyzing, searching for a person in charge, using generative AI, and notifying the person in charge using each API. This enables automatic collection and analysis of communication data, identification and notification of an appropriate person in charge, and generation of a solution using a generative AI model.

[0469] "Communications data" refers to data such as emails, chat history, and video conference transcripts obtained from an enterprise and related communication tools.

[0470] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, including the processes of tokenizing text, extracting keywords, and identifying issues.

[0471] "Keywords" refer to important words or phrases related to the problem that are extracted through analysis of communication data.

[0472] "Generative artificial intelligence" refers to artificial intelligence models that automatically generate new information and solutions based on past data and examples. Examples include generative AI models.

[0473] A "database" refers to a system that stores data such as past response records and staff information, and keeps it in a searchable format.

[0474] "API" stands for Application Programming Interface, and refers to an interface that enables data exchange and function utilization between different software.

[0475] "Notification" refers to the means by which users and other interested parties are informed of the analysis results, the most appropriate person, or the generated solution.

[0476] "Server" refers to a computer system that performs the processes of collecting communication data, analyzing it, searching for personnel, using generated AI, and sending notifications.

[0477] This invention is a system for automatically identifying problems that arise in corporate projects and quickly finding the most appropriate person to handle them. This system includes the processes of collecting and analyzing communication data, identifying the person in charge, generating solutions using generative artificial intelligence, and notifying the person in charge.

[0478] System configuration

[0479] Hardware and Software

[0480] The server is a central system for collecting communication data, analyzing it using natural language processing, identifying responsible parties, generating solutions using generative AI models, and sending notifications.

[0481] APIs (Application Programming Interfaces) are used to collect data from email, chat tools, and video conferencing servers. Specifically, APIs for email servers (e.g., Gmail API), APIs for chat tools (e.g., Slack API), and APIs for video conferencing (e.g., Zoom API) are used.

[0482] Use natural language processing libraries (e.g., spaCy, BERT) to analyze communication data and extract important keywords.

[0483] The database is a system that stores records of past problem responses and information on personnel in charge, allowing the server to search for them.

[0484] Generative AI models (e.g., GPT-4) are used to automatically generate responses when no suitable personnel can be found.

[0485] A notification system (e.g., SMTP server, chat tool notification API, WebSocket or Push API) is used to notify users and personnel of analysis results and solutions.

[0486] Examples of data collection

[0487] The server collects users' emails, chat history, and video conference transcripts. For example, it retrieves incoming emails via the Gmail API, retrieves chat history for specific channels using the Slack API, and retrieves meeting transcripts using the Zoom API.

[0488] Specific examples of data analysis

[0489] The server analyzes the collected communication data using natural language processing technology. For example, it uses the NLP library spaCy or the BERT model to tokenize the text and extract keywords related to the problem. For example, from an email that says "Project X is not progressing," it extracts the keywords "Project X," "Progress delay," and "Code bug."

[0490] Specific examples of personnel

[0491] The server searches the database for relevant personnel based on the keywords from the analysis results. For example, it retrieves past response records related to "Project X" or "code bugs" from the database and selects the most suitable person.

[0492] Examples of the use of generative artificial intelligence

[0493] If no suitable person is found, the server generates a solution using a generative AI model (e.g., GPT-4). For example, enter a prompt such as "Please propose a solution to the progress delay in project X" and obtain the generated solution.

[0494] Specific examples of notifications

[0495] The server notifies the user or person in charge of the analysis results and generated solutions. For example, it can send notifications by email using an SMTP server, send chat notifications using the Slack API, or display alerts on a dashboard using WebSocket. This allows users to quickly recognize problems and take appropriate action.

[0496] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0497] Step 1: Data collection

[0498] The server collects communication data from email APIs, chat tool APIs, and video conferencing APIs. Specifically, it uses the Gmail API to obtain received emails, the Slack API to obtain chat history, and the Zoom API to obtain video conferencing transcripts. It sends authentication information and data acquisition requests from each API as input, and obtains the acquired communication data in a structured data format (e.g., JSON) as output.

[0499] Step 2: Data analysis

[0500] The server analyzes the collected communication data using natural language processing technology. Specifically, it uses a natural language processing library (e.g., spaCy, BERT) to tokenize the acquired data and extract keywords. It takes the collected communication data (text data) as input and generates structured data containing issues and related keywords as output.

[0501] Step 3: Identify the person in charge

[0502] The server searches the database for relevant personnel based on the keywords from the analysis results. It uses the analyzed keywords as input and executes a database query. Specifically, it searches past problem response records and personnel information, and obtains information on the most suitable personnel as output. For example, it selects the appropriate personnel based on keywords such as "Project X" and "code bug."

[0503] Step 4: Use generative AI

[0504] If no suitable person can be found, the server uses a generative AI model (e.g., GPT-4) to generate a solution. As input, it provides a prompt (e.g., "Please propose a solution to the delay in project X") generated based on the problem analysis results, and as output, it obtains the solution generated by the generative AI model. This output is filtered and corrected as necessary to create the final answer.

[0505] Step 5: Notification

[0506] The server notifies the user or person in charge of the analysis results and generated solutions. Specifically, it sends email notifications via an SMTP server, sends chat notifications using the Slack API, and displays alerts in real time on a dashboard using WebSocket or Push API. The notification content (analysis results, person in charge information, generated solutions) is given as input, and a confirmation message that the notification has been sent is received as output.

[0507] This series of steps creates a system that automatically and consistently collects and analyzes communication data, identifies responsible parties, proposes solutions using generative artificial intelligence, and finally notifies users.

[0508] (Application example 1)

[0509] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0510] When a problem occurs in a company's project or factory, it is difficult to find the most suitable person to deal with it quickly and accurately. Furthermore, when a suitable person cannot be found, it is necessary to automatically generate a solution. Especially on the production line, where an immediate response is required when an abnormality occurs, a system that can efficiently achieve this is needed.

[0511] 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.

[0512] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating an answer using generative AI if no person is found, means for notifying the person in charge or the generated answer, means for monitoring abnormalities on the production line in real time, identifying the problem when it occurs, and promptly notifying the appropriate engineer, and means for proposing an optimal solution via a generative AI model using automatically generated prompt sentences. This enables prompt and effective response when problems occur within a company or on the production line, and for identifying and notifying the appropriate person in charge.

[0513] "Communications data" refers to records of all digital communications within and outside a company, such as emails, chat histories, video conference transcripts, and production line monitoring data.

[0514] "Natural language processing" refers to the technology that allows computers to analyze, understand, and generate human language, and is used to extract issues and related keywords.

[0515] "Analyzed keywords" refer to issues and related important words and phrases extracted from communication data using natural language processing technology.

[0516] A "database" refers to a system that stores data such as information about the person in charge and past problem-solving history.

[0517] "Generative artificial intelligence" refers to technology that automatically generates optimal solutions to problems by referring to past cases and data.

[0518] "Notification" refers to the act of communicating the analysis results or generated answers to the person in charge or the user, and is done by means of email, chat notification, etc.

[0519] A "production line" refers to a series of devices and machines in production facilities installed within a factory, including their layout for efficiently producing products.

[0520] "Abnormality monitoring" refers to the function of detecting abnormal behavior or problems on the production line and reporting them in real time.

[0521] A "prompt sentence" refers to the input text that a generative artificial intelligence uses to receive the information and requests necessary to solve a problem.

[0522] A "generative AI model" refers to an artificial intelligence model used to suggest optimal solutions based on past data and specific problems.

[0523] This invention is a system for quickly and effectively solving problems in projects and production lines within a company or factory. The system is implemented as follows, centered around a server.

[0524] Data collection

[0525] The server collects various communication data. Specifically, it obtains emails, chat history, and video conference transcripts through email, chat tool, and video conference APIs. It also collects real-time monitoring data from the production line. This aggregates a record of all digital communications within and outside the company.

[0526] Data analysis

[0527] The collected communication data is analyzed on the server using natural language processing (NLP) technology. This analysis analyzes the text content of the communication data and extracts keywords related to the problem. The NLPParser module is specifically used for NLP technology. For example, from an email that says, "Project X isn't progressing. There may be a bug in the code," keywords such as "Project X," "bug," and "code" are extracted.

[0528] Identifying the person in charge

[0529] Based on the analyzed keywords, the server checks the database for past response records and staff information to identify the most suitable staff member. The database stores staff information and past problem-solving history. If an appropriate staff member cannot be found, a generative artificial intelligence (AIGenerator module) is used to automatically generate a response. For example, for the data "The machine has stopped. The cause is unknown," the AI ​​model generates the solution "Please check the power supply."

[0530] notification

[0531] The server notifies the user of the generated analysis results, the person in charge, or the generated answer. Notification methods include email, chat notifications, and dashboard alerts. By receiving this notification, the user can quickly recognize the problem and take appropriate action. For notifications, the Notifier module is used.

[0532] Specific examples

[0533] In a production line, if a worker sends a message saying "The machine on production line A has stopped. The cause is unknown":

[0534] 1. The server collects chat data.

[0535] 2. Use NLP technology to extract the keywords "Production Line A," "Machine Stopped," and "Cause Unknown."

[0536] 3. Search the database to identify engineers who have previously handled machine stoppages on "Production Line A."

[0537] 4. Notify the engineer you found that "The machine on production line A has stopped. The cause is unknown."

[0538] Prompt Sentence Examples

[0539] Prompt to be given to the generative AI model:

[0540] A machine stoppage problem has occurred in Project X. Please suggest a solution based on past data and case studies.

[0541] This prompt allows the generative AI model to refer to past cases and suggest specific countermeasures such as "Please check the power supply."

[0542] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0543] Step 1:

[0544] The server collects communication data through email APIs, chat tool APIs, video conference APIs, and production line monitoring data. This data includes email text, chat logs, video conference minutes, production line operation data, etc. The input is various communication data, and the output is aggregated communication data.

[0545] Step 2:

[0546] The server analyzes the collected communication data using the NLPParser module. The collected data is converted into text data and natural language processing technology is applied to extract issues and related keywords. This analysis extracts meaningful keywords such as "Project X," "bug," and "machine down." The input is the aggregated communication data, and the output is the extracted keywords.

[0547] Step 3:

[0548] The server uses the UserDatabase module to search the database based on the analyzed keywords. It searches for agent information that matches the keywords and obtains the agent's past correspondence records and skill information. The input is the extracted keywords, and the output is the most suitable agent information.

[0549] Step 4:

[0550] If the server cannot find a suitable agent, it uses the AI ​​Generator module to automatically generate a solution. This module generates a prompt sentence and inputs it into a generative AI model to suggest the optimal solution based on past data and examples. For example, a specific solution such as "Please check the power supply" is generated. The input is the extracted keywords, and the output is the generated solution.

[0551] Step 5:

[0552] The server uses the Notifier module as a notification method to notify the user of the identified agent or the generated solution. Notifications include email and chat notifications. The user receives the notification and quickly recognizes the problem and takes action. The input is the information of the best agent or the generated solution, and the output is the notification message.

[0553] Specific operations of each processing step

[0554] Step 1:

[0555] The server makes an API call to collect data from each communication data source, e.g. requests.get('https: / / api.email-provider.com / emails')

[0556] The collected data is aggregated in one place to create a set of data sets.

[0557] Step 2:

[0558] The server calls the NLPParser module to begin parsing the text data. Example: nlp_parser.extract_keywords(data)

[0559] Apply keyword extraction algorithms to extract key terms and phrases.

[0560] Step 3:

[0561] The server uses the UserDatabase module to search the database and find the best match based on the keywords, e.g. user_db.search_user(key_info)

[0562] Compare the past response records and skill information of each agent to identify the most suitable agent.

[0563] Step 4:

[0564] The server uses the AIGenerator module to generate prompt sentences and feed them into the generative AI model. Example: ai_generator.generate_solution(key_info)

[0565] Obtain the optimal solution from the generative AI model and document the solution to the problem.

[0566] Step 5:

[0567] The server uses the Notifier module to notify the user of the identified agent or generated solution, e.g. notifier.send(content, notification_type)

[0568] Generate notification messages and send them as emails or chat messages.

[0569] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0570] This invention is a system that automatically identifies the problem and user emotions when a problem occurs in a company's project, and quickly finds the most appropriate person to solve the problem. It also uses generative artificial intelligence to generate solutions as needed, and provides appropriate notifications to efficiently solve the problem. An important component of this invention is the incorporation of an emotion engine, which analyzes the user's emotions and re-commands the notification content and the person in charge.

[0571] System configuration

[0572] The system consists of the following main components:

[0573] Means of collecting communication data

[0574] A means of analyzing issues and related keywords using natural language processing

[0575] A means of searching for personnel based on analyzed keywords

[0576] A means of generating answers using generative artificial intelligence

[0577] A means of notifying the assignee or generated response

[0578] Emotion Engine

[0579] Program processing

[0580] Data collection

[0581] The server collects data through APIs of various communication tools (email, chat, video conferencing) and stores it in real time in internal storage, allowing you to always track the latest communication content.

[0582] Data analysis

[0583] The server analyzes the collected data using natural language processing (NLP) technology to extract keywords related to the problem. For example, from an email saying "Project X is not progressing," it identifies keywords such as "Project X," "progress delay," and "code bug."

[0584] Emotion analysis

[0585] The emotion engine recognizes the user's emotions from the analyzed text data, and this process can identify the user's emotional state, such as whether they are feeling stressed or urgent.

[0586] Identifying the person in charge

[0587] The server searches the database for the most suitable agent based on the analysis and sentiment analysis results. For example, it identifies agents who have solved similar problems in the past. Based on the sentiment analysis results, it may re-command an agent who can provide a more appropriate response.

[0588] Use of generative artificial intelligence

[0589] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[0590] notification

[0591] The server notifies the person in charge or the user of the analysis results and generated answers. The notification includes a summary of the problem, relevant keywords, and appropriate countermeasures based on the sentiment analysis results. Notification methods include email, chat notifications, dashboard alerts, etc.

[0592] Specific examples

[0593] Example 1: Email about a code bug

[0594] When a user sends an email saying "Project X isn't progressing. I think there might be a bug in the code," the server does the following:

[0595] 1. The server collects the email and retrieves the text content.

[0596] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[0597] 3. The emotion engine recognizes the user's emotions and identifies emotions such as "tension" and "anxiety."

[0598] 4. The server searches the database to identify the person who previously handled bugs for "Project X."

[0599] 5. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[0600] Example 2: Marketing Campaign Issues

[0601] If a user says in a Zoom meeting, "My marketing campaigns aren't performing as expected," the server does the following:

[0602] 1. The server collects the Zoom meeting transcript.

[0603] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[0604] 3. The emotion engine recognizes the user's emotions and detects "disappointment" and "sense of challenge."

[0605] 4. The server searches its database and, if no representative who has dealt with a similar campaign issue is found, uses generative artificial intelligence to generate advice.

[0606] 5. The server notifies the user with the generated advice "Try a new strategy."

[0607] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[0608] The processing flow will be explained below.

[0609] Step 1:

[0610] The server collects communication data from the company's internal communication tools (email, chat, video conferencing). It uses the API of each communication tool to obtain the latest data in real time and saves it in internal storage. For example, the server might obtain email content using a mail server API, collect chat history through a chat tool API, and obtain transcripts using a video conferencing API.

[0611] Step 2:

[0612] The server converts the collected communication data into text format. For example, by extracting email text, chat messages, and meeting transcripts as text data, it makes the data easier to analyze. This ensures that all data is handled in a consistent format.

[0613] Step 3:

[0614] The server analyzes the text data using natural language processing (NLP) technology. This analysis identifies problems from the text content and extracts related keywords. For example, from the text "Project X is not progressing," the server extracts the keywords "Project X," "Delayed progress," and "Code bug."

[0615] Step 4:

[0616] The server uses an emotion engine to recognize the user's emotions from the text data. This identifies emotions such as stress, anxiety, and disappointment felt by the user. For example, the server analyzes emotions such as "anxiety" and "stress" from the text "I'm in trouble because the project has stalled." This emotional information has an important impact on subsequent processing.

[0617] Step 5:

[0618] The server searches the database for relevant agents based on the analyzed keywords and emotion information. The server then references past correspondence records to identify the most appropriate agent. This search utilizes information such as the agent's expertise and past performance. The server also takes emotion information into account to select the agent who can best respond to the user's emotions.

[0619] Step 6:

[0620] The server then sends a notification to the identified agent, which includes a summary of the problem, relevant keywords, and user sentiment. The notification can be delivered to the agent via email, chat notification, or dashboard alert, allowing the agent to respond quickly to the problem.

[0621] Step 7:

[0622] If no suitable person can be found, the server uses generative artificial intelligence to generate an answer. This AI automatically creates a solution by referencing past cases and data. For example, if the problem is related to a code bug, the server generates advice such as "Check the coding rules and add test cases."

[0623] Step 8:

[0624] The server notifies the user of the generated answer. This notification includes specific advice created by the generative AI and tells the user what action to take next. Notification methods include email, chat notification, or dashboard alert. The user receives the notification and can act on the provided advice.

[0625] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[0626] Example 2

[0627] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0628] In conventional corporate project management systems, when a problem occurs in a project, it is difficult to quickly and accurately identify the problem and the user's feelings, and to find the most appropriate person to handle it. Furthermore, if an appropriate person cannot be found, it takes a long time to resolve the problem, which is an issue.

[0629] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for identifying the user's emotions using the analyzed keywords and a sentiment analysis engine, means for searching a database for a relevant person in charge based on the analysis results, means for generating an answer using generative artificial intelligence if no person in charge is found, and means for notifying the person in charge or the generated answer. This enables a quick and efficient response when a problem occurs.

[0630] "Communication data" is a general term for text data generated and collected through communication means, such as emails, chat histories, and video conference transcripts.

[0631] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is a processing technology that includes keyword extraction and problem recognition.

[0632] A "problem" is an unexpected situation or difficulty that arises in a project or task and requires a solution.

[0633] "Related keywords" are important words and phrases related to the problem or business that are extracted from the communication data.

[0634] An "emotion analysis engine" is a technology for identifying a user's emotions (e.g., tension, anxiety, disappointment, etc.) from text data.

[0635] A "personnel" is a person within a company who is responsible for solving problems for a particular task or project.

[0636] "Generative AI" is an AI technology that automatically generates solutions and answers based on past cases and data.

[0637] "Notification" refers to the action or means for informing the user or person in charge of the analysis results or generated answers, and includes email and chat notifications.

[0638] This invention is a system for quickly and efficiently resolving project problems that arise within a company. This system collects communication data, analyzes the problem and related keywords using natural language processing technology, identifies the most appropriate person to handle the problem based on the analysis results, and, in some cases, generates a solution using generative artificial intelligence and notifies the user of the solution.

[0639] Hardware or software used

[0640] The server is the main component of this system, and uses the following hardware and software:

[0641] Hardware: High-performance computing servers (e.g. general-purpose servers)

[0642] software:

[0643] Natural language processing libraries (e.g., natural language processing APIs provided by popular manufacturers)

[0644] Sentiment analysis engine (e.g., general analysis engine API)

[0645] Generative artificial intelligence models (e.g., widely used generative AI models)

[0646] Notification systems (e.g. email API, chat notification API)

[0647] System configuration

[0648] The system consists of the following main components:

[0649] 1. Collection of Communications Data:

[0650] The server collects data using APIs for communication tools such as email, chat, and video conferencing. For example, it uses email APIs and video conferencing APIs to obtain communication data in real time and saves it in internal storage.

[0651] 2. Data Analysis:

[0652] The server analyzes the collected communication data using natural language processing (NLP) technology. Using NLP technology, it extracts problems and related keywords. For example, from an email that says "Project X isn't progressing," it extracts keywords such as "Project X," "progress delay," and "code bug."

[0653] 3. Emotion analysis:

[0654] The emotion engine recognizes the user's emotions from the analyzed text data. The emotion analysis engine identifies emotions such as "tension," "anxiety," and "disappointment" that the user is feeling.

[0655] 4. Identify the person in charge:

[0656] The server searches the database for the most suitable agent based on the analysis and emotion analysis results, and can refer to past cases to identify the agent who can handle the specific problem or emotional state.

[0657] 5. Use of generative artificial intelligence:

[0658] If the server cannot find a suitable person, it uses a generative artificial intelligence model to generate a solution. It references accumulated data and automatically generates a solution based on similar past cases.

[0659] 6. Notice:

[0660] The server notifies the person in charge or the user of the analysis results and generated solutions via email, chat notification, dashboard alerts, etc. The notification includes a summary of the problem, related keywords, sentiment analysis results, and the optimal response.

[0661] Specific examples

[0662] Example 1: Email about a code bug

[0663] If a user sends an email stating "Project X isn't progressing. I think there might be a bug in the code," the system will respond with the following prompt:

[0664] procedure:

[0665] 1. The server collects emails using an email API.

[0666] 2. The server uses a natural language processing API to analyze the content of the email and extract the keywords "Project X," "code," and "bug."

[0667] 3. The emotion engine analyzes the content of the email and identifies emotions such as "tension" and "anxiety."

[0668] 4. The server searches the database to identify the appropriate person who handled the bug for "Project X."

[0669] 5. Once the appropriate person has been identified, the server uses the notification system to send a notification to the person saying, "There is a suspected bug in the code of Project X."

[0670] Example 2: Marketing Campaign Issues

[0671] If a user says in a video conference, "My marketing campaigns aren't performing as expected," the system will respond with the following prompt:

[0672] procedure:

[0673] 1. The server collects the transcript of the meeting using the video conferencing API.

[0674] 2. The server uses a natural language processing API to analyze the transcript and extract the keywords "marketing campaign," "results," and "failed."

[0675] 3. The emotion engine analyzes the content of the meeting and identifies emotions such as "disappointment" and "sense of challenge."

[0676] 4. The server searches the database for a suitable agent, and if not found, uses a generative artificial intelligence model to generate advice such as "Try a new strategy."

[0677] 5. The server uses a notification system to notify the user of the generated advice.

[0678] In this way, the system of the present invention efficiently supports problem-solving within companies by performing a series of processes, including collecting communication data, analyzing it, recognizing emotions, identifying the person in charge, and using generative artificial intelligence and sending notifications.

[0679] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0680] Step 1: Data collection

[0681] The server collects communication data such as emails, chat histories, and video conference transcripts. Specifically, it does the following:

[0682] Input: Requests to each communication tool's API (email API, chat API, video conferencing API)

[0683] Data processing: new messages and meeting transcripts retrieved via API requests

[0684] Output: Save the acquired communication data to the internal storage.

[0685] For example, a server calls an email API to retrieve new emails and save them in storage.

[0686] Step 2: Data analysis

[0687] The server analyzes the collected communication data and extracts the problem and related keywords. The specific operations are as follows:

[0688] Input: Text data stored in internal storage

[0689] Data processing: Extracting keywords and issues from text data using natural language processing (NLP) techniques

[0690] Output: Extracted keywords and issues

[0691] For example, the server calls a natural language processing API to extract the keywords "Project X," "Delayed progress," and "Code bug" from the text "Project X is not progressing."

[0692] Step 3: Sentiment Analysis

[0693] The emotion engine recognizes the user's emotion from the analyzed text data. The specific operation is as follows:

[0694] Input: Text data extracted by data analysis

[0695] Data processing: Use a sentiment analysis engine to identify sentiment categories from text data

[0696] Output: Identified emotion (e.g., "tension," "anxiety," "disappointment")

[0697] For example, an emotion engine can analyze the text "Project X isn't progressing" and identify the emotions "tension" and "anxiety."

[0698] Step 4: Identify the person in charge

[0699] The server searches the database for the most suitable agent based on the analysis results and the sentiment analysis results. The specific operations are as follows:

[0700] Input: Extracted keywords and identified sentiments

[0701] Data manipulation: Performing database queries to find the right person

[0702] Output: Optimal Rep

[0703] For example, the server might search the database for keywords like "Project X," "progress delay," and "code bug" to identify people who have solved similar problems in the past.

[0704] Step 5: Use generative AI

[0705] If the server cannot find a suitable person, it uses generative artificial intelligence to generate a solution. The specific operation is as follows:

[0706] Input: Keywords and sentiment analysis results

[0707] Data processing: Invoking generative AI to generate solutions

[0708] Output: The generated solution

[0709] For example, a generative artificial intelligence model generates a solution to the problem of "delays in the progress of Project X."

[0710] Step 6: Notification

[0711] The server notifies the person in charge or the user of the analysis results and generated solutions. The specific operations are as follows:

[0712] Input: Assignee or generated solution

[0713] Data processing: Creating notification messages

[0714] Output: Email, chat notification, dashboard alert

[0715] For example, the server might use a notification system to send a message to a responsible party saying, "There is a suspected bug in the code for project X."

[0716] In this way, the system efficiently supports problem-solving within companies through the steps of data collection, data analysis, sentiment analysis, identifying responsible parties, utilizing generative artificial intelligence, and notification.

[0717] (Application example 2)

[0718] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0719] In factories, various problems occur daily with the operation of robots and various equipment. Quickly identifying these problems and finding the appropriate person or solution is essential for improving productivity and streamlining troubleshooting. However, with conventional systems, the process from problem detection to resolution was complicated and took a lot of time and effort. In addition, emotion analysis was not incorporated, making it difficult to respond efficiently while taking into account the urgency of the problem and the emotional state of the personnel.

[0720] 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.

[0721] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating a response using generative artificial intelligence if the person is not found, means for notifying the person or the generated response, means including an emotion engine for recognizing the emotional state of the analyzed communication, means for coordinating an appropriate response based on the recognized emotional state, and means for including communication data provided by robots in the factory. This makes it possible to quickly and efficiently identify and analyze problems occurring in the factory and propose appropriate people or solutions.

[0722] "Communications data" refers to information collected within a factory or other environment in the form of emails, chat histories, video conference transcripts, sensor data from robots, etc.

[0723] "Natural language processing" is a technology for understanding text information from communication data and analyzing problems and related keywords.

[0724] "Keywords" are important words or phrases extracted through natural language processing to identify issues and related information.

[0725] A "database" is a collection of information that searches for relevant personnel based on analyzed keywords.

[0726] "Generative AI" refers to artificial intelligence technology that automatically generates answers and suggestions to solve problems.

[0727] An "emotion engine" is a device or program that recognizes the user's emotional state from analyzed communication data and adjusts appropriate responses based on that information.

[0728] A "personnel" is a person with specialized knowledge and skills for solving a problem.

[0729] A "robot" is a machine or device used to automate work in a factory.

[0730] "Means of notification" refers to the means for notifying the relevant personnel or systems of the analysis results and generated solutions.

[0731] The present invention is a system for quickly and efficiently identifying problems occurring within a factory and recommending appropriate personnel or solutions. The system is composed of the following main components:

[0732] Hardware and Software Configuration

[0733] server

[0734] The server has the following functions:

[0735] 1. Communication data collection: Collect various communication data provided by robots and operators in the factory. Through API access, obtain emails, chat history, video conference transcripts, and sensor data from robots in real time.

[0736] 2. Data analysis: The collected data is analyzed using natural language processing (NLP) technology to extract keywords related to the problem. Examples of NLP technology used include TextBlob.

[0737] 3. Use of emotion engine: Recognize the user's emotional state from the analyzed text data. The emotion engine identifies the urgency and stress the user (operator or robot) is feeling.

[0738] 4. Agent Search: Based on the results of the analysis and sentiment analysis, the database is searched for the most suitable agent. Agents are identified based on their past experience and skill sets stored in the database.

[0739] 5. Use of generative AI: If no suitable person can be found, a solution can be automatically generated using generative AI, which learns from past cases and provides solutions to similar problems.

[0740] 6. Notification: Notify personnel or users of the analysis results and generated solutions. Notification methods include email, chat notifications, and dashboard alerts.

[0741] Terminal

[0742] User devices that can be used to access the system include PCs, smartphones, and tablets.

[0743] Specific examples

[0744] Example 1: Case of a sensor abnormality in a factory robot

[0745] The server collects communication data from the robot indicating that the sensor is malfunctioning.

[0746] The data is analyzed using natural language processing technology to extract keywords such as "sensor malfunction" and "robot."

[0747] An emotion engine is used to analyze user emotions and identify "anxiety" and "urgency."

[0748] The system searches the database for staff who have dealt with similar problems in the past, and if no such staff is found, it uses generative artificial intelligence to generate a solution.

[0749] Notify generated solutions and assignees.

[0750] Prompt Sentence Examples

[0751] "Please suggest a solution if the robot's battery is rapidly depleting."

[0752] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0753] Step 1:

[0754] The server collects communication data provided by robots and operators in the factory. Specifically, emails, chat history, video conference transcripts, and sensor data from the robots are obtained in real time through API access and stored in internal storage. The input is a variety of communication data, and the output is data ready for analysis.

[0755] Step 2:

[0756] The server analyzes the collected communication data using natural language processing (NLP). The specific operations performed here are text extraction and keyword analysis. For example, TextBlob is used to extract keywords such as "sensor malfunction" and "robot." The input is the collected communication data, and the output is the extracted keywords.

[0757] Step 3:

[0758] The server recognizes the user's emotional state from the text data analyzed using the emotion engine. In this step, the emotion the user is feeling, such as "anxiety" or "urgency," is identified. The emotion engine performs emotion analysis on the input text data, and the identified emotional state is output.

[0759] Step 4:

[0760] The server searches the database for relevant staff members based on the analysis and sentiment analysis results. Specifically, it searches for staff members who have solved similar problems in the past and identifies the most suitable staff member. The input is keywords and sentiment analysis results, and the output is information about the identified staff member.

[0761] Step 5:

[0762] If the server cannot find a suitable person, it uses generative AI to automatically generate a solution. Here, it references past cases and generates solutions to similar problems. The input is the extracted keywords, and the output is the solution generated by the AI.

[0763] Step 6:

[0764] The server notifies the person in charge or the user of the analysis results and the generated solution. In this step, notifications are made via email, chat notifications, or dashboard alerts. The input is the generated solution and the person in charge information, and the output is the notification result sent to the user.

[0765] Example operation

[0766] As an example, consider the case where a factory robot reports a "sensor malfunction."

[0767] Step 1: Collect communication data from the robot regarding "sensor malfunctions."

[0768] Step 2: Analyze the collected data for keywords such as "sensor malfunction" and "robot."

[0769] Step 3: Use the emotion engine to recognize the emotion "anxiety" from the data.

[0770] Step 4: Search the database to identify the person who responded to the "sensor malfunction."

[0771] Step 5: If no suitable person can be found, use generative artificial intelligence to generate a solution.

[0772] Step 6: Notify the person or user of the generated solution.

[0773] Example prompt sentence:

[0774] "Please suggest a solution if the robot's battery is rapidly depleting."

[0775] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0776] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0777] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0778] [Third embodiment]

[0779] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0780] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0781] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0782] 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.

[0783] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0784] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0785] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0786] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0787] 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.

[0788] 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.

[0789] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0790] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0791] The present invention is a system for automatically identifying problems that arise in a company's projects and quickly finding the most suitable person to handle the problem. How this system is implemented will be specifically explained below.

[0792] System configuration

[0793] This system has a means to collect communication data from various communication tools (email, chat, video conferencing) in one place. Specifically, it consists of the following servers and software components:

[0794] The server collects communication data in real time.

[0795] The server analyzes the communication data using natural language processing technology.

[0796] Based on the analysis results, the server searches the database for the appropriate person in charge.

[0797] If no suitable person can be found, the server uses generative artificial intelligence to generate a solution.

[0798] The server notifies the user of the analysis results, the person in charge, and the generated answer.

[0799] Program processing

[0800] Data collection

[0801] The server collects communication data through email APIs, chat tool APIs, and video conferencing APIs. For example, it collects email data using a mail server API, obtains chat history using a chat tool API, and collects video conferencing transcripts using a Zoom API.

[0802] Data analysis

[0803] The server analyzes the collected communication data using natural language processing (NLP) technology. This analysis extracts problems from the text content of the communication data and identifies related keywords. For example, an NLP model can be used to extract the keywords "Project X," "progress delay," and "code bug" from an email that says, "Project X is not progressing."

[0804] Identifying the person in charge

[0805] Based on the analysis results, the server compares past correspondence records and staff information from the database to identify the most suitable staff member, searching for relevant keywords and evaluating the staff member's past performance and expertise.

[0806] Use of generative artificial intelligence

[0807] If no suitable person can be found, the server will automatically generate a solution using generative artificial intelligence, which references past cases and data to generate solutions to similar problems.

[0808] notification

[0809] Finally, the server notifies the person in charge or the user of the analysis results and countermeasures. Notifications are given via email, chat notifications, dashboard alerts, etc. This allows the user to quickly recognize the problem and take appropriate action.

[0810] Specific examples

[0811] Example 1: Email about a code bug

[0812] If a user sends an email saying "Project X isn't progressing. There might be a bug in the code," the server does the following:

[0813] 1. The server collects the email and retrieves the text content.

[0814] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[0815] 3. The server searches the database to identify the person who previously handled bugs for "Project X."

[0816] 4. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[0817] Example 2: Marketing Campaign Issues

[0818] If a user says in a Zoom meeting, "My marketing campaign is not producing the results I expected," the server performs the following process:

[0819] 1. The server collects the Zoom meeting transcript.

[0820] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[0821] 3. The server searches its database and, if it cannot find a specialist who has dealt with a similar campaign issue, it uses generative artificial intelligence to generate advice.

[0822] 4. The server notifies the user with the generated advice "Try a new strategy."

[0823] In this way, the system analyzes multiple communication data, identifies the appropriate person in charge, and notifies them quickly, thereby helping to resolve issues within the company.

[0824] The processing flow will be explained below.

[0825] Step 1:

[0826] The server collects communication data within the company (emails, chat history, video conference transcripts). The data is obtained through the API of each communication tool and saved in internal storage in real time. At this stage, it is important to keep the latest information on communication data.

[0827] Step 2:

[0828] To analyze the collected communication data, the server first extracts text data, such as email bodies from mailboxes, message texts from chat histories, and video conference transcripts into text format.

[0829] Step 3:

[0830] The server applies natural language processing (NLP) techniques to the extracted text data, including identifying the problem and extracting relevant keywords. Specifically, it uses an NLP model to analyze key phrases and words in the text to understand the nature of the problem.

[0831] Step 4:

[0832] The server uses the keywords and issues identified by NLP to search a database that includes past case records and each agent's expertise to identify the most relevant agent.

[0833] Step 5:

[0834] The server then sends a notification to the identified personnel, which includes a summary of the problem, relevant keywords, and immediate actionable actions. The notification is delivered to the personnel via email, chat notification, or dashboard alert.

[0835] Step 6:

[0836] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[0837] Step 7:

[0838] The server notifies the user of the generated answer via email, chat notification, or dashboard alert, allowing the user to receive actionable advice and next steps.

[0839] Step 8:

[0840] The server stores all processing logs for future analysis and system improvement, including the processing time for each step, the resources used, and the notifications generated.

[0841] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting communication data to analyzing it, identifying the person in charge, notifying them, and using generative artificial intelligence.

[0842] Example 1

[0843] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0844] When a problem occurs in a company's project, it is difficult to quickly and accurately identify the problem and find the most appropriate person to handle it. Furthermore, if the right person cannot be found or the problem is complex, it becomes even more difficult to find a solution efficiently. To solve these issues, a system is needed that effectively utilizes communication data to automatically identify problems and find the right person to handle them.

[0845] 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.

[0846] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person in charge based on the analyzed keywords, means for generating an answer using generative AI if the person in charge is not found, means for notifying the person in charge or the generated answer, and means for executing each process of collecting, analyzing, searching for a person in charge, using generative AI, and notifying the person in charge using each API. This enables automatic collection and analysis of communication data, identification and notification of an appropriate person in charge, and generation of a solution using a generative AI model.

[0847] "Communications data" refers to data such as emails, chat history, and video conference transcripts obtained from an enterprise and related communication tools.

[0848] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, including the processes of tokenizing text, extracting keywords, and identifying issues.

[0849] "Keywords" refer to important words or phrases related to the problem that are extracted through analysis of communication data.

[0850] "Generative artificial intelligence" refers to artificial intelligence models that automatically generate new information and solutions based on past data and examples. Examples include generative AI models.

[0851] A "database" refers to a system that stores data such as past response records and staff information, and keeps it in a searchable format.

[0852] "API" stands for Application Programming Interface, and refers to an interface that enables data exchange and function utilization between different software.

[0853] "Notification" refers to the means by which users and other interested parties are informed of the analysis results, the most appropriate person, or the generated solution.

[0854] "Server" refers to a computer system that performs the processes of collecting communication data, analyzing it, searching for personnel, using generated AI, and sending notifications.

[0855] This invention is a system for automatically identifying problems that arise in corporate projects and quickly finding the most appropriate person to handle them. This system includes the processes of collecting and analyzing communication data, identifying the person in charge, generating solutions using generative artificial intelligence, and notifying the person in charge.

[0856] System configuration

[0857] Hardware and Software

[0858] The server is a central system for collecting communication data, analyzing it using natural language processing, identifying responsible parties, generating solutions using generative AI models, and sending notifications.

[0859] APIs (Application Programming Interfaces) are used to collect data from email, chat tools, and video conferencing servers. Specifically, APIs for email servers (e.g., Gmail API), APIs for chat tools (e.g., Slack API), and APIs for video conferencing (e.g., Zoom API) are used.

[0860] Use natural language processing libraries (e.g., spaCy, BERT) to analyze communication data and extract important keywords.

[0861] The database is a system that stores records of past problem responses and information on personnel in charge, allowing the server to search for them.

[0862] Generative AI models (e.g., GPT-4) are used to automatically generate responses when no suitable personnel can be found.

[0863] A notification system (e.g., SMTP server, chat tool notification API, WebSocket or Push API) is used to notify users and personnel of analysis results and solutions.

[0864] Examples of data collection

[0865] The server collects users' emails, chat history, and video conference transcripts. For example, it retrieves incoming emails via the Gmail API, retrieves chat history for specific channels using the Slack API, and retrieves meeting transcripts using the Zoom API.

[0866] Specific examples of data analysis

[0867] The server analyzes the collected communication data using natural language processing technology. For example, it uses the NLP library spaCy or the BERT model to tokenize the text and extract keywords related to the problem. For example, from an email that says "Project X is not progressing," it extracts the keywords "Project X," "Progress delay," and "Code bug."

[0868] Specific examples of personnel

[0869] The server searches the database for relevant personnel based on the keywords from the analysis results. For example, it retrieves past response records related to "Project X" or "code bugs" from the database and selects the most suitable person.

[0870] Examples of the use of generative artificial intelligence

[0871] If no suitable person is found, the server generates a solution using a generative AI model (e.g., GPT-4). For example, enter a prompt such as "Please propose a solution to the progress delay in project X" and obtain the generated solution.

[0872] Specific examples of notifications

[0873] The server notifies the user or person in charge of the analysis results and generated solutions. For example, it can send notifications by email using an SMTP server, send chat notifications using the Slack API, or display alerts on a dashboard using WebSocket. This allows users to quickly recognize problems and take appropriate action.

[0874] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0875] Step 1: Data collection

[0876] The server collects communication data from email APIs, chat tool APIs, and video conferencing APIs. Specifically, it uses the Gmail API to obtain received emails, the Slack API to obtain chat history, and the Zoom API to obtain video conferencing transcripts. It sends authentication information and data acquisition requests from each API as input, and obtains the acquired communication data in a structured data format (e.g., JSON) as output.

[0877] Step 2: Data analysis

[0878] The server analyzes the collected communication data using natural language processing technology. Specifically, it uses a natural language processing library (e.g., spaCy, BERT) to tokenize the acquired data and extract keywords. It takes the collected communication data (text data) as input and generates structured data containing issues and related keywords as output.

[0879] Step 3: Identify the person in charge

[0880] The server searches the database for relevant personnel based on the keywords from the analysis results. It uses the analyzed keywords as input and executes a database query. Specifically, it searches past problem response records and personnel information, and obtains information on the most suitable personnel as output. For example, it selects the appropriate personnel based on keywords such as "Project X" and "code bug."

[0881] Step 4: Use generative AI

[0882] If no suitable person can be found, the server uses a generative AI model (e.g., GPT-4) to generate a solution. As input, it provides a prompt (e.g., "Please propose a solution to the delay in project X") generated based on the problem analysis results, and as output, it obtains the solution generated by the generative AI model. This output is filtered and corrected as necessary to create the final answer.

[0883] Step 5: Notification

[0884] The server notifies the user or person in charge of the analysis results and generated solutions. Specifically, it sends email notifications via an SMTP server, sends chat notifications using the Slack API, and displays alerts in real time on a dashboard using WebSocket or Push API. The notification content (analysis results, person in charge information, generated solutions) is given as input, and a confirmation message that the notification has been sent is received as output.

[0885] This series of steps creates a system that automatically and consistently collects and analyzes communication data, identifies responsible parties, proposes solutions using generative artificial intelligence, and finally notifies users.

[0886] (Application example 1)

[0887] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0888] When a problem occurs in a company's project or factory, it is difficult to find the most suitable person to deal with it quickly and accurately. Furthermore, when a suitable person cannot be found, it is necessary to automatically generate a solution. Especially on the production line, where an immediate response is required when an abnormality occurs, a system that can efficiently achieve this is needed.

[0889] 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.

[0890] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating an answer using generative AI if no person is found, means for notifying the person in charge or the generated answer, means for monitoring abnormalities on the production line in real time, identifying the problem when it occurs, and promptly notifying the appropriate engineer, and means for proposing an optimal solution via a generative AI model using automatically generated prompt sentences. This enables prompt and effective response when problems occur within a company or on the production line, and for identifying and notifying the appropriate person in charge.

[0891] "Communications data" refers to records of all digital communications within and outside a company, such as emails, chat histories, video conference transcripts, and production line monitoring data.

[0892] "Natural language processing" refers to the technology that allows computers to analyze, understand, and generate human language, and is used to extract issues and related keywords.

[0893] "Analyzed keywords" refer to issues and related important words and phrases extracted from communication data using natural language processing technology.

[0894] A "database" refers to a system that stores data such as information about the person in charge and past problem-solving history.

[0895] "Generative artificial intelligence" refers to technology that automatically generates optimal solutions to problems by referring to past cases and data.

[0896] "Notification" refers to the act of communicating the analysis results or generated answers to the person in charge or the user, and is done by means of email, chat notification, etc.

[0897] A "production line" refers to a series of devices and machines in production facilities installed within a factory, including their layout for efficiently producing products.

[0898] "Abnormality monitoring" refers to the function of detecting abnormal behavior or problems on the production line and reporting them in real time.

[0899] A "prompt sentence" refers to the input text that a generative artificial intelligence uses to receive the information and requests necessary to solve a problem.

[0900] A "generative AI model" refers to an artificial intelligence model used to suggest optimal solutions based on past data and specific problems.

[0901] This invention is a system for quickly and effectively solving problems in projects and production lines within a company or factory. The system is implemented as follows, centered around a server.

[0902] Data collection

[0903] The server collects various communication data. Specifically, it obtains emails, chat history, and video conference transcripts through email, chat tool, and video conference APIs. It also collects real-time monitoring data from the production line. This aggregates a record of all digital communications within and outside the company.

[0904] Data analysis

[0905] The collected communication data is analyzed on the server using natural language processing (NLP) technology. This analysis analyzes the text content of the communication data and extracts keywords related to the problem. The NLPParser module is specifically used for NLP technology. For example, from an email that says, "Project X isn't progressing. There may be a bug in the code," keywords such as "Project X," "bug," and "code" are extracted.

[0906] Identifying the person in charge

[0907] Based on the analyzed keywords, the server checks the database for past response records and staff information to identify the most suitable staff member. The database stores staff information and past problem-solving history. If an appropriate staff member cannot be found, a generative artificial intelligence (AIGenerator module) is used to automatically generate a response. For example, for the data "The machine has stopped. The cause is unknown," the AI ​​model generates the solution "Please check the power supply."

[0908] notification

[0909] The server notifies the user of the generated analysis results, the person in charge, or the generated answer. Notification methods include email, chat notifications, and dashboard alerts. By receiving this notification, the user can quickly recognize the problem and take appropriate action. For notifications, the Notifier module is used.

[0910] Specific examples

[0911] In a production line, if a worker sends a message saying "The machine on production line A has stopped. The cause is unknown":

[0912] 1. The server collects chat data.

[0913] 2. Use NLP technology to extract the keywords "Production Line A," "Machine Stopped," and "Cause Unknown."

[0914] 3. Search the database to identify engineers who have previously handled machine stoppages on "Production Line A."

[0915] 4. Notify the engineer you found that "The machine on production line A has stopped. The cause is unknown."

[0916] Prompt Sentence Examples

[0917] Prompt to be given to the generative AI model:

[0918] A machine stoppage problem has occurred in Project X. Please suggest a solution based on past data and case studies.

[0919] This prompt allows the generative AI model to refer to past cases and suggest specific countermeasures such as "Please check the power supply."

[0920] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0921] Step 1:

[0922] The server collects communication data through email APIs, chat tool APIs, video conference APIs, and production line monitoring data. This data includes email text, chat logs, video conference minutes, production line operation data, etc. The input is various communication data, and the output is aggregated communication data.

[0923] Step 2:

[0924] The server analyzes the collected communication data using the NLPParser module. The collected data is converted into text data and natural language processing technology is applied to extract issues and related keywords. This analysis extracts meaningful keywords such as "Project X," "bug," and "machine down." The input is the aggregated communication data, and the output is the extracted keywords.

[0925] Step 3:

[0926] The server uses the UserDatabase module to search the database based on the analyzed keywords. It searches for agent information that matches the keywords and obtains the agent's past correspondence records and skill information. The input is the extracted keywords, and the output is the most suitable agent information.

[0927] Step 4:

[0928] If the server cannot find a suitable agent, it uses the AI ​​Generator module to automatically generate a solution. This module generates a prompt sentence and inputs it into a generative AI model to suggest the optimal solution based on past data and examples. For example, a specific solution such as "Please check the power supply" is generated. The input is the extracted keywords, and the output is the generated solution.

[0929] Step 5:

[0930] The server uses the Notifier module as a notification method to notify the user of the identified agent or the generated solution. Notifications include email and chat notifications. The user receives the notification and quickly recognizes the problem and takes action. The input is the information of the best agent or the generated solution, and the output is the notification message.

[0931] Specific operations of each processing step

[0932] Step 1:

[0933] The server makes an API call to collect data from each communication data source, e.g. requests.get('https: / / api.email-provider.com / emails')

[0934] The collected data is aggregated in one place to create a set of data sets.

[0935] Step 2:

[0936] The server calls the NLPParser module to begin parsing the text data. Example: nlp_parser.extract_keywords(data)

[0937] Apply keyword extraction algorithms to extract key terms and phrases.

[0938] Step 3:

[0939] The server uses the UserDatabase module to search the database and find the best match based on the keywords, e.g. user_db.search_user(key_info)

[0940] Compare the past response records and skill information of each agent to identify the most suitable agent.

[0941] Step 4:

[0942] The server uses the AIGenerator module to generate prompt sentences and feed them into the generative AI model. Example: ai_generator.generate_solution(key_info)

[0943] Obtain the optimal solution from the generative AI model and document the solution to the problem.

[0944] Step 5:

[0945] The server uses the Notifier module to notify the user of the identified agent or generated solution, e.g. notifier.send(content, notification_type)

[0946] Generate notification messages and send them as emails or chat messages.

[0947] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0948] This invention is a system that automatically identifies the problem and user emotions when a problem occurs in a company's project, and quickly finds the most appropriate person to solve the problem. It also uses generative artificial intelligence to generate solutions as needed, and provides appropriate notifications to efficiently solve the problem. An important component of this invention is the incorporation of an emotion engine, which analyzes the user's emotions and re-commands the notification content and the person in charge.

[0949] System configuration

[0950] The system consists of the following main components:

[0951] Means of collecting communication data

[0952] A means of analyzing issues and related keywords using natural language processing

[0953] A means of searching for personnel based on analyzed keywords

[0954] A means of generating answers using generative artificial intelligence

[0955] A means of notifying the assignee or generated response

[0956] Emotion Engine

[0957] Program processing

[0958] Data collection

[0959] The server collects data through APIs of various communication tools (email, chat, video conferencing) and stores it in real time in internal storage, allowing you to always track the latest communication content.

[0960] Data analysis

[0961] The server analyzes the collected data using natural language processing (NLP) technology to extract keywords related to the problem. For example, from an email saying "Project X is not progressing," it identifies keywords such as "Project X," "progress delay," and "code bug."

[0962] Emotion analysis

[0963] The emotion engine recognizes the user's emotions from the analyzed text data, and this process can identify the user's emotional state, such as whether they are feeling stressed or urgent.

[0964] Identifying the person in charge

[0965] The server searches the database for the most suitable agent based on the analysis and sentiment analysis results. For example, it identifies agents who have solved similar problems in the past. Based on the sentiment analysis results, it may re-command an agent who can provide a more appropriate response.

[0966] Use of generative artificial intelligence

[0967] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[0968] notification

[0969] The server notifies the person in charge or the user of the analysis results and generated answers. The notification includes a summary of the problem, relevant keywords, and appropriate countermeasures based on the sentiment analysis results. Notification methods include email, chat notifications, dashboard alerts, etc.

[0970] Specific examples

[0971] Example 1: Email about a code bug

[0972] When a user sends an email saying "Project X isn't progressing. I think there might be a bug in the code," the server does the following:

[0973] 1. The server collects the email and retrieves the text content.

[0974] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[0975] 3. The emotion engine recognizes the user's emotions and identifies emotions such as "tension" and "anxiety."

[0976] 4. The server searches the database to identify the person who previously handled bugs for "Project X."

[0977] 5. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[0978] Example 2: Marketing Campaign Issues

[0979] If a user says in a Zoom meeting, "My marketing campaigns aren't performing as expected," the server does the following:

[0980] 1. The server collects the Zoom meeting transcript.

[0981] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[0982] 3. The emotion engine recognizes the user's emotions and detects "disappointment" and "sense of challenge."

[0983] 4. The server searches its database and, if no representative who has dealt with a similar campaign issue is found, uses generative artificial intelligence to generate advice.

[0984] 5. The server notifies the user with the generated advice "Try a new strategy."

[0985] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[0986] The processing flow will be explained below.

[0987] Step 1:

[0988] The server collects communication data from the company's internal communication tools (email, chat, video conferencing). It uses the API of each communication tool to obtain the latest data in real time and saves it in internal storage. For example, the server might obtain email content using a mail server API, collect chat history through a chat tool API, and obtain transcripts using a video conferencing API.

[0989] Step 2:

[0990] The server converts the collected communication data into text format. For example, by extracting email text, chat messages, and meeting transcripts as text data, it makes the data easier to analyze. This ensures that all data is handled in a consistent format.

[0991] Step 3:

[0992] The server analyzes the text data using natural language processing (NLP) technology. This analysis identifies problems from the text content and extracts related keywords. For example, from the text "Project X is not progressing," the server extracts the keywords "Project X," "Delayed progress," and "Code bug."

[0993] Step 4:

[0994] The server uses an emotion engine to recognize the user's emotions from the text data. This identifies emotions such as stress, anxiety, and disappointment felt by the user. For example, the server analyzes emotions such as "anxiety" and "stress" from the text "I'm in trouble because the project has stalled." This emotional information has an important impact on subsequent processing.

[0995] Step 5:

[0996] The server searches the database for relevant agents based on the analyzed keywords and emotion information. The server then references past correspondence records to identify the most appropriate agent. This search utilizes information such as the agent's expertise and past performance. The server also takes emotion information into account to select the agent who can best respond to the user's emotions.

[0997] Step 6:

[0998] The server then sends a notification to the identified agent, which includes a summary of the problem, relevant keywords, and user sentiment. The notification can be delivered to the agent via email, chat notification, or dashboard alert, allowing the agent to respond quickly to the problem.

[0999] Step 7:

[1000] If no suitable person can be found, the server uses generative artificial intelligence to generate an answer. This AI automatically creates a solution by referencing past cases and data. For example, if the problem is related to a code bug, the server generates advice such as "Check the coding rules and add test cases."

[1001] Step 8:

[1002] The server notifies the user of the generated answer. This notification includes specific advice created by the generative AI and tells the user what action to take next. Notification methods include email, chat notification, or dashboard alert. The user receives the notification and can act on the provided advice.

[1003] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[1004] Example 2

[1005] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1006] In conventional corporate project management systems, when a problem occurs in a project, it is difficult to quickly and accurately identify the problem and the user's feelings, and to find the most appropriate person to handle it. Furthermore, if an appropriate person cannot be found, it takes a long time to resolve the problem, which is an issue.

[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 means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for identifying the user's emotions using the analyzed keywords and a sentiment analysis engine, means for searching a database for a relevant person in charge based on the analysis results, means for generating an answer using generative artificial intelligence if no person in charge is found, and means for notifying the person in charge or the generated answer. This enables a quick and efficient response when a problem occurs.

[1008] "Communication data" is a general term for text data generated and collected through communication means, such as emails, chat histories, and video conference transcripts.

[1009] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is a processing technology that includes keyword extraction and problem recognition.

[1010] A "problem" is an unexpected situation or difficulty that arises in a project or task and requires a solution.

[1011] "Related keywords" are important words and phrases related to the problem or business that are extracted from the communication data.

[1012] An "emotion analysis engine" is a technology for identifying a user's emotions (e.g., tension, anxiety, disappointment, etc.) from text data.

[1013] A "personnel" is a person within a company who is responsible for solving problems for a particular task or project.

[1014] "Generative AI" is an AI technology that automatically generates solutions and answers based on past cases and data.

[1015] "Notification" refers to the action or means for informing the user or person in charge of the analysis results or generated answers, and includes email and chat notifications.

[1016] This invention is a system for quickly and efficiently resolving project problems that arise within a company. This system collects communication data, analyzes the problem and related keywords using natural language processing technology, identifies the most appropriate person to handle the problem based on the analysis results, and, in some cases, generates a solution using generative artificial intelligence and notifies the user of the solution.

[1017] Hardware or software used

[1018] The server is the main component of this system, and uses the following hardware and software:

[1019] Hardware: High-performance computing servers (e.g. general-purpose servers)

[1020] software:

[1021] Natural language processing libraries (e.g., natural language processing APIs provided by popular manufacturers)

[1022] Sentiment analysis engine (e.g., general analysis engine API)

[1023] Generative artificial intelligence models (e.g., widely used generative AI models)

[1024] Notification systems (e.g. email API, chat notification API)

[1025] System configuration

[1026] The system consists of the following main components:

[1027] 1. Collection of Communications Data:

[1028] The server collects data using APIs for communication tools such as email, chat, and video conferencing. For example, it uses email APIs and video conferencing APIs to obtain communication data in real time and saves it in internal storage.

[1029] 2. Data Analysis:

[1030] The server analyzes the collected communication data using natural language processing (NLP) technology. Using NLP technology, it extracts problems and related keywords. For example, from an email that says "Project X isn't progressing," it extracts keywords such as "Project X," "progress delay," and "code bug."

[1031] 3. Emotion analysis:

[1032] The emotion engine recognizes the user's emotions from the analyzed text data. The emotion analysis engine identifies emotions such as "tension," "anxiety," and "disappointment" that the user is feeling.

[1033] 4. Identify the person in charge:

[1034] The server searches the database for the most suitable agent based on the analysis and emotion analysis results, and can refer to past cases to identify the agent who can handle the specific problem or emotional state.

[1035] 5. Use of generative artificial intelligence:

[1036] If the server cannot find a suitable person, it uses a generative artificial intelligence model to generate a solution. It references accumulated data and automatically generates a solution based on similar past cases.

[1037] 6. Notice:

[1038] The server notifies the person in charge or the user of the analysis results and generated solutions via email, chat notification, dashboard alerts, etc. The notification includes a summary of the problem, related keywords, sentiment analysis results, and the optimal response.

[1039] Specific examples

[1040] Example 1: Email about a code bug

[1041] If a user sends an email stating "Project X isn't progressing. I think there might be a bug in the code," the system will respond with the following prompt:

[1042] procedure:

[1043] 1. The server collects emails using an email API.

[1044] 2. The server uses a natural language processing API to analyze the content of the email and extract the keywords "Project X," "code," and "bug."

[1045] 3. The emotion engine analyzes the content of the email and identifies emotions such as "tension" and "anxiety."

[1046] 4. The server searches the database to identify the appropriate person who handled the bug for "Project X."

[1047] 5. Once the appropriate person has been identified, the server uses the notification system to send a notification to the person saying, "There is a suspected bug in the code of Project X."

[1048] Example 2: Marketing Campaign Issues

[1049] If a user says in a video conference, "My marketing campaigns aren't performing as expected," the system will respond with the following prompt:

[1050] procedure:

[1051] 1. The server collects the transcript of the meeting using the video conferencing API.

[1052] 2. The server uses a natural language processing API to analyze the transcript and extract the keywords "marketing campaign," "results," and "failed."

[1053] 3. The emotion engine analyzes the content of the meeting and identifies emotions such as "disappointment" and "sense of challenge."

[1054] 4. The server searches the database for a suitable agent, and if not found, uses a generative artificial intelligence model to generate advice such as "Try a new strategy."

[1055] 5. The server uses a notification system to notify the user of the generated advice.

[1056] In this way, the system of the present invention efficiently supports problem-solving within companies by performing a series of processes, including collecting communication data, analyzing it, recognizing emotions, identifying the person in charge, and using generative artificial intelligence and sending notifications.

[1057] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1058] Step 1: Data collection

[1059] The server collects communication data such as emails, chat histories, and video conference transcripts. Specifically, it does the following:

[1060] Input: Requests to each communication tool's API (email API, chat API, video conferencing API)

[1061] Data processing: new messages and meeting transcripts retrieved via API requests

[1062] Output: Save the acquired communication data to the internal storage.

[1063] For example, a server calls an email API to retrieve new emails and save them in storage.

[1064] Step 2: Data analysis

[1065] The server analyzes the collected communication data and extracts the problem and related keywords. The specific operations are as follows:

[1066] Input: Text data stored in internal storage

[1067] Data processing: Extracting keywords and issues from text data using natural language processing (NLP) techniques

[1068] Output: Extracted keywords and issues

[1069] For example, the server calls a natural language processing API to extract the keywords "Project X," "Delayed progress," and "Code bug" from the text "Project X is not progressing."

[1070] Step 3: Sentiment Analysis

[1071] The emotion engine recognizes the user's emotion from the analyzed text data. The specific operation is as follows:

[1072] Input: Text data extracted by data analysis

[1073] Data processing: Use a sentiment analysis engine to identify sentiment categories from text data

[1074] Output: Identified emotion (e.g., "tension," "anxiety," "disappointment")

[1075] For example, an emotion engine can analyze the text "Project X isn't progressing" and identify the emotions "tension" and "anxiety."

[1076] Step 4: Identify the person in charge

[1077] The server searches the database for the most suitable agent based on the analysis results and the sentiment analysis results. The specific operations are as follows:

[1078] Input: Extracted keywords and identified sentiments

[1079] Data manipulation: Performing database queries to find the right person

[1080] Output: Optimal Rep

[1081] For example, the server might search the database for keywords like "Project X," "progress delay," and "code bug" to identify people who have solved similar problems in the past.

[1082] Step 5: Use generative AI

[1083] If the server cannot find a suitable person, it uses generative artificial intelligence to generate a solution. The specific operation is as follows:

[1084] Input: Keywords and sentiment analysis results

[1085] Data processing: Invoking generative AI to generate solutions

[1086] Output: The generated solution

[1087] For example, a generative artificial intelligence model generates a solution to the problem of "delays in the progress of Project X."

[1088] Step 6: Notification

[1089] The server notifies the person in charge or the user of the analysis results and generated solutions. The specific operations are as follows:

[1090] Input: Assignee or generated solution

[1091] Data processing: Creating notification messages

[1092] Output: Email, chat notification, dashboard alert

[1093] For example, the server might use a notification system to send a message to a responsible party saying, "There is a suspected bug in the code for project X."

[1094] In this way, the system efficiently supports problem-solving within companies through the steps of data collection, data analysis, sentiment analysis, identifying responsible parties, utilizing generative artificial intelligence, and notification.

[1095] (Application example 2)

[1096] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1097] In factories, various problems occur daily with the operation of robots and various equipment. Quickly identifying these problems and finding the appropriate person or solution is essential for improving productivity and streamlining troubleshooting. However, with conventional systems, the process from problem detection to resolution was complicated and took a lot of time and effort. In addition, emotion analysis was not incorporated, making it difficult to respond efficiently while taking into account the urgency of the problem and the emotional state of the personnel.

[1098] 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.

[1099] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating a response using generative artificial intelligence if the person is not found, means for notifying the person or the generated response, means including an emotion engine for recognizing the emotional state of the analyzed communication, means for coordinating an appropriate response based on the recognized emotional state, and means for including communication data provided by robots in the factory. This makes it possible to quickly and efficiently identify and analyze problems occurring in the factory and propose appropriate people or solutions.

[1100] "Communications data" refers to information collected within a factory or other environment in the form of emails, chat histories, video conference transcripts, sensor data from robots, etc.

[1101] "Natural language processing" is a technology for understanding text information from communication data and analyzing problems and related keywords.

[1102] "Keywords" are important words or phrases extracted through natural language processing to identify issues and related information.

[1103] A "database" is a collection of information that searches for relevant personnel based on analyzed keywords.

[1104] "Generative AI" refers to artificial intelligence technology that automatically generates answers and suggestions to solve problems.

[1105] An "emotion engine" is a device or program that recognizes the user's emotional state from analyzed communication data and adjusts appropriate responses based on that information.

[1106] A "personnel" is a person with specialized knowledge and skills for solving a problem.

[1107] A "robot" is a machine or device used to automate work in a factory.

[1108] "Means of notification" refers to the means for notifying the relevant personnel or systems of the analysis results and generated solutions.

[1109] The present invention is a system for quickly and efficiently identifying problems occurring within a factory and recommending appropriate personnel or solutions. The system is composed of the following main components:

[1110] Hardware and Software Configuration

[1111] server

[1112] The server has the following functions:

[1113] 1. Communication data collection: Collect various communication data provided by robots and operators in the factory. Through API access, obtain emails, chat history, video conference transcripts, and sensor data from robots in real time.

[1114] 2. Data analysis: The collected data is analyzed using natural language processing (NLP) technology to extract keywords related to the problem. Examples of NLP technology used include TextBlob.

[1115] 3. Use of emotion engine: Recognize the user's emotional state from the analyzed text data. The emotion engine identifies the urgency and stress the user (operator or robot) is feeling.

[1116] 4. Agent Search: Based on the results of the analysis and sentiment analysis, the database is searched for the most suitable agent. Agents are identified based on their past experience and skill sets stored in the database.

[1117] 5. Use of generative AI: If no suitable person can be found, a solution can be automatically generated using generative AI, which learns from past cases and provides solutions to similar problems.

[1118] 6. Notification: Notify personnel or users of the analysis results and generated solutions. Notification methods include email, chat notifications, and dashboard alerts.

[1119] Terminal

[1120] User devices that can be used to access the system include PCs, smartphones, and tablets.

[1121] Specific examples

[1122] Example 1: Case of a sensor abnormality in a factory robot

[1123] The server collects communication data from the robot indicating that the sensor is malfunctioning.

[1124] The data is analyzed using natural language processing technology to extract keywords such as "sensor malfunction" and "robot."

[1125] An emotion engine is used to analyze user emotions and identify "anxiety" and "urgency."

[1126] The system searches the database for staff who have dealt with similar problems in the past, and if no such staff is found, it uses generative artificial intelligence to generate a solution.

[1127] Notify generated solutions and assignees.

[1128] Prompt Sentence Examples

[1129] "Please suggest a solution if the robot's battery is rapidly depleting."

[1130] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1131] Step 1:

[1132] The server collects communication data provided by robots and operators in the factory. Specifically, emails, chat history, video conference transcripts, and sensor data from the robots are obtained in real time through API access and stored in internal storage. The input is a variety of communication data, and the output is data ready for analysis.

[1133] Step 2:

[1134] The server analyzes the collected communication data using natural language processing (NLP). The specific operations performed here are text extraction and keyword analysis. For example, TextBlob is used to extract keywords such as "sensor malfunction" and "robot." The input is the collected communication data, and the output is the extracted keywords.

[1135] Step 3:

[1136] The server recognizes the user's emotional state from the text data analyzed using the emotion engine. In this step, the emotion the user is feeling, such as "anxiety" or "urgency," is identified. The emotion engine performs emotion analysis on the input text data, and the identified emotional state is output.

[1137] Step 4:

[1138] The server searches the database for relevant staff members based on the analysis and sentiment analysis results. Specifically, it searches for staff members who have solved similar problems in the past and identifies the most suitable staff member. The input is keywords and sentiment analysis results, and the output is information about the identified staff member.

[1139] Step 5:

[1140] If the server cannot find a suitable person, it uses generative AI to automatically generate a solution. Here, it references past cases and generates solutions to similar problems. The input is the extracted keywords, and the output is the solution generated by the AI.

[1141] Step 6:

[1142] The server notifies the person in charge or the user of the analysis results and the generated solution. In this step, notifications are made via email, chat notifications, or dashboard alerts. The input is the generated solution and the person in charge information, and the output is the notification result sent to the user.

[1143] Example operation

[1144] As an example, consider the case where a factory robot reports a "sensor malfunction."

[1145] Step 1: Collect communication data from the robot regarding "sensor malfunctions."

[1146] Step 2: Analyze the collected data for keywords such as "sensor malfunction" and "robot."

[1147] Step 3: Use the emotion engine to recognize the emotion "anxiety" from the data.

[1148] Step 4: Search the database to identify the person who responded to the "sensor malfunction."

[1149] Step 5: If no suitable person can be found, use generative artificial intelligence to generate a solution.

[1150] Step 6: Notify the person or user of the generated solution.

[1151] Example prompt sentence:

[1152] "Please suggest a solution if the robot's battery is rapidly depleting."

[1153] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1154] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1155] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1156] [Fourth embodiment]

[1157] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1158] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1159] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1160] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1161] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1162] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1163] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1164] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1165] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1166] 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.

[1167] 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.

[1168] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1169] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1170] The present invention is a system for automatically identifying problems that arise in a company's projects and quickly finding the most suitable person to handle the problem. How this system is implemented will be specifically explained below.

[1171] System configuration

[1172] This system has a means to collect communication data from various communication tools (email, chat, video conferencing) in one place. Specifically, it consists of the following servers and software components:

[1173] The server collects communication data in real time.

[1174] The server analyzes the communication data using natural language processing technology.

[1175] Based on the analysis results, the server searches the database for the appropriate person in charge.

[1176] If no suitable person can be found, the server uses generative artificial intelligence to generate a solution.

[1177] The server notifies the user of the analysis results, the person in charge, and the generated answer.

[1178] Program processing

[1179] Data collection

[1180] The server collects communication data through email APIs, chat tool APIs, and video conferencing APIs. For example, it collects email data using a mail server API, obtains chat history using a chat tool API, and collects video conferencing transcripts using a Zoom API.

[1181] Data analysis

[1182] The server analyzes the collected communication data using natural language processing (NLP) technology. This analysis extracts problems from the text content of the communication data and identifies related keywords. For example, an NLP model can be used to extract the keywords "Project X," "progress delay," and "code bug" from an email that says, "Project X is not progressing."

[1183] Identifying the person in charge

[1184] Based on the analysis results, the server compares past correspondence records and staff information from the database to identify the most suitable staff member, searching for relevant keywords and evaluating the staff member's past performance and expertise.

[1185] Use of generative artificial intelligence

[1186] If no suitable person can be found, the server will automatically generate a solution using generative artificial intelligence, which references past cases and data to generate solutions to similar problems.

[1187] notification

[1188] Finally, the server notifies the person in charge or the user of the analysis results and countermeasures. Notifications are given via email, chat notifications, dashboard alerts, etc. This allows the user to quickly recognize the problem and take appropriate action.

[1189] Specific examples

[1190] Example 1: Email about a code bug

[1191] If a user sends an email saying "Project X isn't progressing. There might be a bug in the code," the server does the following:

[1192] 1. The server collects the email and retrieves the text content.

[1193] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[1194] 3. The server searches the database to identify the person who previously handled bugs for "Project X."

[1195] 4. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[1196] Example 2: Marketing Campaign Issues

[1197] If a user says in a Zoom meeting, "My marketing campaign is not producing the results I expected," the server performs the following process:

[1198] 1. The server collects the Zoom meeting transcript.

[1199] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[1200] 3. The server searches its database and, if it cannot find a specialist who has dealt with a similar campaign issue, it uses generative artificial intelligence to generate advice.

[1201] 4. The server notifies the user with the generated advice "Try a new strategy."

[1202] In this way, the system analyzes multiple communication data, identifies the appropriate person in charge, and notifies them quickly, thereby helping to resolve issues within the company.

[1203] The processing flow will be explained below.

[1204] Step 1:

[1205] The server collects communication data within the company (emails, chat history, video conference transcripts). The data is obtained through the API of each communication tool and saved in internal storage in real time. At this stage, it is important to keep the latest information on communication data.

[1206] Step 2:

[1207] To analyze the collected communication data, the server first extracts text data, such as email bodies from mailboxes, message texts from chat histories, and video conference transcripts into text format.

[1208] Step 3:

[1209] The server applies natural language processing (NLP) techniques to the extracted text data, including identifying the problem and extracting relevant keywords. Specifically, it uses an NLP model to analyze key phrases and words in the text to understand the nature of the problem.

[1210] Step 4:

[1211] The server uses the keywords and issues identified by NLP to search a database that includes past case records and each agent's expertise to identify the most relevant agent.

[1212] Step 5:

[1213] The server then sends a notification to the identified personnel, which includes a summary of the problem, relevant keywords, and immediate actionable actions. The notification is delivered to the personnel via email, chat notification, or dashboard alert.

[1214] Step 6:

[1215] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[1216] Step 7:

[1217] The server notifies the user of the generated answer via email, chat notification, or dashboard alert, allowing the user to receive actionable advice and next steps.

[1218] Step 8:

[1219] The server stores all processing logs for future analysis and system improvement, including the processing time for each step, the resources used, and the notifications generated.

[1220] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting communication data to analyzing it, identifying the person in charge, notifying them, and using generative artificial intelligence.

[1221] Example 1

[1222] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1223] When a problem occurs in a company's project, it is difficult to quickly and accurately identify the problem and find the most appropriate person to handle it. Furthermore, if the right person cannot be found or the problem is complex, it becomes even more difficult to find a solution efficiently. To solve these issues, a system is needed that effectively utilizes communication data to automatically identify problems and find the right person to handle them.

[1224] 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.

[1225] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person in charge based on the analyzed keywords, means for generating an answer using generative AI if the person in charge is not found, means for notifying the person in charge or the generated answer, and means for executing each process of collecting, analyzing, searching for a person in charge, using generative AI, and notifying the person in charge using each API. This enables automatic collection and analysis of communication data, identification and notification of an appropriate person in charge, and generation of a solution using a generative AI model.

[1226] "Communications data" refers to data such as emails, chat history, and video conference transcripts obtained from an enterprise and related communication tools.

[1227] "Natural language processing" refers to the technology that enables computers to understand and analyze human language, including the processes of tokenizing text, extracting keywords, and identifying issues.

[1228] "Keywords" refer to important words or phrases related to the problem that are extracted through analysis of communication data.

[1229] "Generative artificial intelligence" refers to artificial intelligence models that automatically generate new information and solutions based on past data and examples. Examples include generative AI models.

[1230] A "database" refers to a system that stores data such as past response records and staff information, and keeps it in a searchable format.

[1231] "API" stands for Application Programming Interface, and refers to an interface that enables data exchange and function utilization between different software.

[1232] "Notification" refers to the means by which users and other interested parties are informed of the analysis results, the most appropriate person, or the generated solution.

[1233] "Server" refers to a computer system that performs the processes of collecting communication data, analyzing it, searching for personnel, using generated AI, and sending notifications.

[1234] This invention is a system for automatically identifying problems that arise in corporate projects and quickly finding the most appropriate person to handle them. This system includes the processes of collecting and analyzing communication data, identifying the person in charge, generating solutions using generative artificial intelligence, and notifying the person in charge.

[1235] System configuration

[1236] Hardware and Software

[1237] The server is a central system for collecting communication data, analyzing it using natural language processing, identifying responsible parties, generating solutions using generative AI models, and sending notifications.

[1238] APIs (Application Programming Interfaces) are used to collect data from email, chat tools, and video conferencing servers. Specifically, APIs for email servers (e.g., Gmail API), APIs for chat tools (e.g., Slack API), and APIs for video conferencing (e.g., Zoom API) are used.

[1239] Use natural language processing libraries (e.g., spaCy, BERT) to analyze communication data and extract important keywords.

[1240] The database is a system that stores records of past problem responses and information on personnel in charge, allowing the server to search for them.

[1241] Generative AI models (e.g., GPT-4) are used to automatically generate responses when no suitable personnel can be found.

[1242] A notification system (e.g., SMTP server, chat tool notification API, WebSocket or Push API) is used to notify users and personnel of analysis results and solutions.

[1243] Examples of data collection

[1244] The server collects users' emails, chat history, and video conference transcripts. For example, it retrieves incoming emails via the Gmail API, retrieves chat history for specific channels using the Slack API, and retrieves meeting transcripts using the Zoom API.

[1245] Specific examples of data analysis

[1246] The server analyzes the collected communication data using natural language processing technology. For example, it uses the NLP library spaCy or the BERT model to tokenize the text and extract keywords related to the problem. For example, from an email that says "Project X is not progressing," it extracts the keywords "Project X," "Progress delay," and "Code bug."

[1247] Specific examples of personnel

[1248] The server searches the database for relevant personnel based on the keywords from the analysis results. For example, it retrieves past response records related to "Project X" or "code bugs" from the database and selects the most suitable person.

[1249] Examples of the use of generative artificial intelligence

[1250] If no suitable person is found, the server generates a solution using a generative AI model (e.g., GPT-4). For example, enter a prompt such as "Please propose a solution to the progress delay in project X" and obtain the generated solution.

[1251] Specific examples of notifications

[1252] The server notifies the user or person in charge of the analysis results and generated solutions. For example, it can send notifications by email using an SMTP server, send chat notifications using the Slack API, or display alerts on a dashboard using WebSocket. This allows users to quickly recognize problems and take appropriate action.

[1253] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1254] Step 1: Data collection

[1255] The server collects communication data from email APIs, chat tool APIs, and video conferencing APIs. Specifically, it uses the Gmail API to obtain received emails, the Slack API to obtain chat history, and the Zoom API to obtain video conferencing transcripts. It sends authentication information and data acquisition requests from each API as input, and obtains the acquired communication data in a structured data format (e.g., JSON) as output.

[1256] Step 2: Data analysis

[1257] The server analyzes the collected communication data using natural language processing technology. Specifically, it uses a natural language processing library (e.g., spaCy, BERT) to tokenize the acquired data and extract keywords. It takes the collected communication data (text data) as input and generates structured data containing issues and related keywords as output.

[1258] Step 3: Identify the person in charge

[1259] The server searches the database for relevant personnel based on the keywords from the analysis results. It uses the analyzed keywords as input and executes a database query. Specifically, it searches past problem response records and personnel information, and obtains information on the most suitable personnel as output. For example, it selects the appropriate personnel based on keywords such as "Project X" and "code bug."

[1260] Step 4: Use generative AI

[1261] If no suitable person can be found, the server uses a generative AI model (e.g., GPT-4) to generate a solution. As input, it provides a prompt (e.g., "Please propose a solution to the delay in project X") generated based on the problem analysis results, and as output, it obtains the solution generated by the generative AI model. This output is filtered and corrected as necessary to create the final answer.

[1262] Step 5: Notification

[1263] The server notifies the user or person in charge of the analysis results and generated solutions. Specifically, it sends email notifications via an SMTP server, sends chat notifications using the Slack API, and displays alerts in real time on a dashboard using WebSocket or Push API. The notification content (analysis results, person in charge information, generated solutions) is given as input, and a confirmation message that the notification has been sent is received as output.

[1264] This series of steps creates a system that automatically and consistently collects and analyzes communication data, identifies responsible parties, proposes solutions using generative artificial intelligence, and finally notifies users.

[1265] (Application example 1)

[1266] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1267] When a problem occurs in a company's project or factory, it is difficult to find the most suitable person to deal with it quickly and accurately. Furthermore, when a suitable person cannot be found, it is necessary to automatically generate a solution. Especially on the production line, where an immediate response is required when an abnormality occurs, a system that can efficiently achieve this is needed.

[1268] 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.

[1269] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating an answer using generative AI if no person is found, means for notifying the person in charge or the generated answer, means for monitoring abnormalities on the production line in real time, identifying the problem when it occurs, and promptly notifying the appropriate engineer, and means for proposing an optimal solution via a generative AI model using automatically generated prompt sentences. This enables prompt and effective response when problems occur within a company or on the production line, and for identifying and notifying the appropriate person in charge.

[1270] "Communications data" refers to records of all digital communications within and outside a company, such as emails, chat histories, video conference transcripts, and production line monitoring data.

[1271] "Natural language processing" refers to the technology that allows computers to analyze, understand, and generate human language, and is used to extract issues and related keywords.

[1272] "Analyzed keywords" refer to issues and related important words and phrases extracted from communication data using natural language processing technology.

[1273] A "database" refers to a system that stores data such as information about the person in charge and past problem-solving history.

[1274] "Generative artificial intelligence" refers to technology that automatically generates optimal solutions to problems by referring to past cases and data.

[1275] "Notification" refers to the act of communicating the analysis results or generated answers to the person in charge or the user, and is done by means of email, chat notification, etc.

[1276] A "production line" refers to a series of devices and machines in production facilities installed within a factory, including their layout for efficiently producing products.

[1277] "Abnormality monitoring" refers to the function of detecting abnormal behavior or problems on the production line and reporting them in real time.

[1278] A "prompt sentence" refers to the input text that a generative artificial intelligence uses to receive the information and requests necessary to solve a problem.

[1279] A "generative AI model" refers to an artificial intelligence model used to suggest optimal solutions based on past data and specific problems.

[1280] This invention is a system for quickly and effectively solving problems in projects and production lines within a company or factory. The system is implemented as follows, centered around a server.

[1281] Data collection

[1282] The server collects various communication data. Specifically, it obtains emails, chat history, and video conference transcripts through email, chat tool, and video conference APIs. It also collects real-time monitoring data from the production line. This aggregates a record of all digital communications within and outside the company.

[1283] Data analysis

[1284] The collected communication data is analyzed on the server using natural language processing (NLP) technology. This analysis analyzes the text content of the communication data and extracts keywords related to the problem. The NLPParser module is specifically used for NLP technology. For example, from an email that says, "Project X isn't progressing. There may be a bug in the code," keywords such as "Project X," "bug," and "code" are extracted.

[1285] Identifying the person in charge

[1286] Based on the analyzed keywords, the server checks the database for past response records and staff information to identify the most suitable staff member. The database stores staff information and past problem-solving history. If an appropriate staff member cannot be found, a generative artificial intelligence (AIGenerator module) is used to automatically generate a response. For example, for the data "The machine has stopped. The cause is unknown," the AI ​​model generates the solution "Please check the power supply."

[1287] notification

[1288] The server notifies the user of the generated analysis results, the person in charge, or the generated answer. Notification methods include email, chat notifications, and dashboard alerts. By receiving this notification, the user can quickly recognize the problem and take appropriate action. For notifications, the Notifier module is used.

[1289] Specific examples

[1290] In a production line, if a worker sends a message saying "The machine on production line A has stopped. The cause is unknown":

[1291] 1. The server collects chat data.

[1292] 2. Use NLP technology to extract the keywords "Production Line A," "Machine Stopped," and "Cause Unknown."

[1293] 3. Search the database to identify engineers who have previously handled machine stoppages on "Production Line A."

[1294] 4. Notify the engineer you found that "The machine on production line A has stopped. The cause is unknown."

[1295] Prompt Sentence Examples

[1296] Prompt to be given to the generative AI model:

[1297] A machine stoppage problem has occurred in Project X. Please suggest a solution based on past data and case studies.

[1298] This prompt allows the generative AI model to refer to past cases and suggest specific countermeasures such as "Please check the power supply."

[1299] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1300] Step 1:

[1301] The server collects communication data through email APIs, chat tool APIs, video conference APIs, and production line monitoring data. This data includes email text, chat logs, video conference minutes, production line operation data, etc. The input is various communication data, and the output is aggregated communication data.

[1302] Step 2:

[1303] The server analyzes the collected communication data using the NLPParser module. The collected data is converted into text data and natural language processing technology is applied to extract issues and related keywords. This analysis extracts meaningful keywords such as "Project X," "bug," and "machine down." The input is the aggregated communication data, and the output is the extracted keywords.

[1304] Step 3:

[1305] The server uses the UserDatabase module to search the database based on the analyzed keywords. It searches for agent information that matches the keywords and obtains the agent's past correspondence records and skill information. The input is the extracted keywords, and the output is the most suitable agent information.

[1306] Step 4:

[1307] If the server cannot find a suitable agent, it uses the AI ​​Generator module to automatically generate a solution. This module generates a prompt sentence and inputs it into a generative AI model to suggest the optimal solution based on past data and examples. For example, a specific solution such as "Please check the power supply" is generated. The input is the extracted keywords, and the output is the generated solution.

[1308] Step 5:

[1309] The server uses the Notifier module as a notification method to notify the user of the identified agent or the generated solution. Notifications include email and chat notifications. The user receives the notification and quickly recognizes the problem and takes action. The input is the information of the best agent or the generated solution, and the output is the notification message.

[1310] Specific operations of each processing step

[1311] Step 1:

[1312] The server makes an API call to collect data from each communication data source, e.g. requests.get('https: / / api.email-provider.com / emails')

[1313] The collected data is aggregated in one place to create a set of data sets.

[1314] Step 2:

[1315] The server calls the NLPParser module to begin parsing the text data. Example: nlp_parser.extract_keywords(data)

[1316] Apply keyword extraction algorithms to extract key terms and phrases.

[1317] Step 3:

[1318] The server uses the UserDatabase module to search the database and find the best match based on the keywords, e.g. user_db.search_user(key_info)

[1319] Compare the past response records and skill information of each agent to identify the most suitable agent.

[1320] Step 4:

[1321] The server uses the AIGenerator module to generate prompt sentences and feed them into the generative AI model. Example: ai_generator.generate_solution(key_info)

[1322] Obtain the optimal solution from the generative AI model and document the solution to the problem.

[1323] Step 5:

[1324] The server uses the Notifier module to notify the user of the identified agent or generated solution, e.g. notifier.send(content, notification_type)

[1325] Generate notification messages and send them as emails or chat messages.

[1326] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1327] This invention is a system that automatically identifies the problem and user emotions when a problem occurs in a company's project, and quickly finds the most appropriate person to solve the problem. It also uses generative artificial intelligence to generate solutions as needed, and provides appropriate notifications to efficiently solve the problem. An important component of this invention is the incorporation of an emotion engine, which analyzes the user's emotions and re-commands the notification content and the person in charge.

[1328] System configuration

[1329] The system consists of the following main components:

[1330] Means of collecting communication data

[1331] A means of analyzing issues and related keywords using natural language processing

[1332] A means of searching for personnel based on analyzed keywords

[1333] A means of generating answers using generative artificial intelligence

[1334] A means of notifying the assignee or generated response

[1335] Emotion Engine

[1336] Program processing

[1337] Data collection

[1338] The server collects data through APIs of various communication tools (email, chat, video conferencing) and stores it in real time in internal storage, allowing you to always track the latest communication content.

[1339] Data analysis

[1340] The server analyzes the collected data using natural language processing (NLP) technology to extract keywords related to the problem. For example, from an email saying "Project X is not progressing," it identifies keywords such as "Project X," "progress delay," and "code bug."

[1341] Emotion analysis

[1342] The emotion engine recognizes the user's emotions from the analyzed text data, and this process can identify the user's emotional state, such as whether they are feeling stressed or urgent.

[1343] Identifying the person in charge

[1344] The server searches the database for the most suitable agent based on the analysis and sentiment analysis results. For example, it identifies agents who have solved similar problems in the past. Based on the sentiment analysis results, it may re-command an agent who can provide a more appropriate response.

[1345] Use of generative artificial intelligence

[1346] If no suitable person can be found, the server generates an answer using generative artificial intelligence, which references past cases and automatically generates solutions to similar problems.

[1347] notification

[1348] The server notifies the person in charge or the user of the analysis results and generated answers. The notification includes a summary of the problem, relevant keywords, and appropriate countermeasures based on the sentiment analysis results. Notification methods include email, chat notifications, dashboard alerts, etc.

[1349] Specific examples

[1350] Example 1: Email about a code bug

[1351] When a user sends an email saying "Project X isn't progressing. I think there might be a bug in the code," the server does the following:

[1352] 1. The server collects the email and retrieves the text content.

[1353] 2. The server uses NLP technology to analyze the content of the email and extracts keywords such as "Project X," "bug," and "code."

[1354] 3. The emotion engine recognizes the user's emotions and identifies emotions such as "tension" and "anxiety."

[1355] 4. The server searches the database to identify the person who previously handled bugs for "Project X."

[1356] 5. The server sends a notification to the person in charge, informing them that there is a suspected bug in the code for Project X.

[1357] Example 2: Marketing Campaign Issues

[1358] If a user says in a Zoom meeting, "My marketing campaigns aren't performing as expected," the server does the following:

[1359] 1. The server collects the Zoom meeting transcript.

[1360] 2. The server uses NLP technology to analyze the transcript and extract the keywords "marketing campaign," "results," and "failure."

[1361] 3. The emotion engine recognizes the user's emotions and detects "disappointment" and "sense of challenge."

[1362] 4. The server searches its database and, if no representative who has dealt with a similar campaign issue is found, uses generative artificial intelligence to generate advice.

[1363] 5. The server notifies the user with the generated advice "Try a new strategy."

[1364] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[1365] The processing flow will be explained below.

[1366] Step 1:

[1367] The server collects communication data from the company's internal communication tools (email, chat, video conferencing). It uses the API of each communication tool to obtain the latest data in real time and saves it in internal storage. For example, the server might obtain email content using a mail server API, collect chat history through a chat tool API, and obtain transcripts using a video conferencing API.

[1368] Step 2:

[1369] The server converts the collected communication data into text format. For example, by extracting email text, chat messages, and meeting transcripts as text data, it makes the data easier to analyze. This ensures that all data is handled in a consistent format.

[1370] Step 3:

[1371] The server analyzes the text data using natural language processing (NLP) technology. This analysis identifies problems from the text content and extracts related keywords. For example, from the text "Project X is not progressing," the server extracts the keywords "Project X," "Delayed progress," and "Code bug."

[1372] Step 4:

[1373] The server uses an emotion engine to recognize the user's emotions from the text data. This identifies emotions such as stress, anxiety, and disappointment felt by the user. For example, the server analyzes emotions such as "anxiety" and "stress" from the text "I'm in trouble because the project has stalled." This emotional information has an important impact on subsequent processing.

[1374] Step 5:

[1375] The server searches the database for relevant agents based on the analyzed keywords and emotion information. The server then references past correspondence records to identify the most appropriate agent. This search utilizes information such as the agent's expertise and past performance. The server also takes emotion information into account to select the agent who can best respond to the user's emotions.

[1376] Step 6:

[1377] The server then sends a notification to the identified agent, which includes a summary of the problem, relevant keywords, and user sentiment. The notification can be delivered to the agent via email, chat notification, or dashboard alert, allowing the agent to respond quickly to the problem.

[1378] Step 7:

[1379] If no suitable person can be found, the server uses generative artificial intelligence to generate an answer. This AI automatically creates a solution by referencing past cases and data. For example, if the problem is related to a code bug, the server generates advice such as "Check the coding rules and add test cases."

[1380] Step 8:

[1381] The server notifies the user of the generated answer. This notification includes specific advice created by the generative AI and tells the user what action to take next. Notification methods include email, chat notification, or dashboard alert. The user receives the notification and can act on the provided advice.

[1382] In this way, the system efficiently supports problem-solving within companies through a series of processes, from collecting and analyzing communication data, recognizing emotions, identifying responsible parties, sending notifications, and using generative artificial intelligence.

[1383] Example 2

[1384] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1385] In conventional corporate project management systems, when a problem occurs in a project, it is difficult to quickly and accurately identify the problem and the user's feelings, and to find the most appropriate person to handle it. Furthermore, if an appropriate person cannot be found, it takes a long time to resolve the problem, which is an issue.

[1386] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for identifying the user's emotions using the analyzed keywords and a sentiment analysis engine, means for searching a database for a relevant person in charge based on the analysis results, means for generating an answer using generative artificial intelligence if no person in charge is found, and means for notifying the person in charge or the generated answer. This enables a quick and efficient response when a problem occurs.

[1387] "Communication data" is a general term for text data generated and collected through communication means, such as emails, chat histories, and video conference transcripts.

[1388] "Natural language processing" is a technology that enables computers to understand, analyze, and generate human language, and is a processing technology that includes keyword extraction and problem recognition.

[1389] A "problem" is an unexpected situation or difficulty that arises in a project or task and requires a solution.

[1390] "Related keywords" are important words and phrases related to the problem or business that are extracted from the communication data.

[1391] An "emotion analysis engine" is a technology for identifying a user's emotions (e.g., tension, anxiety, disappointment, etc.) from text data.

[1392] A "personnel" is a person within a company who is responsible for solving problems for a particular task or project.

[1393] "Generative AI" is an AI technology that automatically generates solutions and answers based on past cases and data.

[1394] "Notification" refers to the action or means for informing the user or person in charge of the analysis results or generated answers, and includes email and chat notifications.

[1395] This invention is a system for quickly and efficiently resolving project problems that arise within a company. This system collects communication data, analyzes the problem and related keywords using natural language processing technology, identifies the most appropriate person to handle the problem based on the analysis results, and, in some cases, generates a solution using generative artificial intelligence and notifies the user of the solution.

[1396] Hardware or software used

[1397] The server is the main component of this system, and uses the following hardware and software:

[1398] Hardware: High-performance computing servers (e.g. general-purpose servers)

[1399] software:

[1400] Natural language processing libraries (e.g., natural language processing APIs provided by popular manufacturers)

[1401] Sentiment analysis engine (e.g., general analysis engine API)

[1402] Generative artificial intelligence models (e.g., widely used generative AI models)

[1403] Notification systems (e.g. email API, chat notification API)

[1404] System configuration

[1405] The system consists of the following main components:

[1406] 1. Collection of Communications Data:

[1407] The server collects data using APIs for communication tools such as email, chat, and video conferencing. For example, it uses email APIs and video conferencing APIs to obtain communication data in real time and saves it in internal storage.

[1408] 2. Data Analysis:

[1409] The server analyzes the collected communication data using natural language processing (NLP) technology. Using NLP technology, it extracts problems and related keywords. For example, from an email that says "Project X isn't progressing," it extracts keywords such as "Project X," "progress delay," and "code bug."

[1410] 3. Emotion analysis:

[1411] The emotion engine recognizes the user's emotions from the analyzed text data. The emotion analysis engine identifies emotions such as "tension," "anxiety," and "disappointment" that the user is feeling.

[1412] 4. Identify the person in charge:

[1413] The server searches the database for the most suitable agent based on the analysis and emotion analysis results, and can refer to past cases to identify the agent who can handle the specific problem or emotional state.

[1414] 5. Use of generative artificial intelligence:

[1415] If the server cannot find a suitable person, it uses a generative artificial intelligence model to generate a solution. It references accumulated data and automatically generates a solution based on similar past cases.

[1416] 6. Notice:

[1417] The server notifies the person in charge or the user of the analysis results and generated solutions via email, chat notification, dashboard alerts, etc. The notification includes a summary of the problem, related keywords, sentiment analysis results, and the optimal response.

[1418] Specific examples

[1419] Example 1: Email about a code bug

[1420] If a user sends an email stating "Project X isn't progressing. I think there might be a bug in the code," the system will respond with the following prompt:

[1421] procedure:

[1422] 1. The server collects emails using an email API.

[1423] 2. The server uses a natural language processing API to analyze the content of the email and extract the keywords "Project X," "code," and "bug."

[1424] 3. The emotion engine analyzes the content of the email and identifies emotions such as "tension" and "anxiety."

[1425] 4. The server searches the database to identify the appropriate person who handled the bug for "Project X."

[1426] 5. Once the appropriate person has been identified, the server uses the notification system to send a notification to the person saying, "There is a suspected bug in the code of Project X."

[1427] Example 2: Marketing Campaign Issues

[1428] If a user says in a video conference, "My marketing campaigns aren't performing as expected," the system will respond with the following prompt:

[1429] procedure:

[1430] 1. The server collects the transcript of the meeting using the video conferencing API.

[1431] 2. The server uses a natural language processing API to analyze the transcript and extract the keywords "marketing campaign," "results," and "failed."

[1432] 3. The emotion engine analyzes the content of the meeting and identifies emotions such as "disappointment" and "sense of challenge."

[1433] 4. The server searches the database for a suitable agent, and if not found, uses a generative artificial intelligence model to generate advice such as "Try a new strategy."

[1434] 5. The server uses a notification system to notify the user of the generated advice.

[1435] In this way, the system of the present invention efficiently supports problem-solving within companies by performing a series of processes, including collecting communication data, analyzing it, recognizing emotions, identifying the person in charge, and using generative artificial intelligence and sending notifications.

[1436] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1437] Step 1: Data collection

[1438] The server collects communication data such as emails, chat histories, and video conference transcripts. Specifically, it does the following:

[1439] Input: Requests to each communication tool's API (email API, chat API, video conferencing API)

[1440] Data processing: new messages and meeting transcripts retrieved via API requests

[1441] Output: Save the acquired communication data to the internal storage.

[1442] For example, a server calls an email API to retrieve new emails and save them in storage.

[1443] Step 2: Data analysis

[1444] The server analyzes the collected communication data and extracts the problem and related keywords. The specific operations are as follows:

[1445] Input: Text data stored in internal storage

[1446] Data processing: Extracting keywords and issues from text data using natural language processing (NLP) techniques

[1447] Output: Extracted keywords and issues

[1448] For example, the server calls a natural language processing API to extract the keywords "Project X," "Delayed progress," and "Code bug" from the text "Project X is not progressing."

[1449] Step 3: Sentiment Analysis

[1450] The emotion engine recognizes the user's emotion from the analyzed text data. The specific operation is as follows:

[1451] Input: Text data extracted by data analysis

[1452] Data processing: Use a sentiment analysis engine to identify sentiment categories from text data

[1453] Output: Identified emotion (e.g., "tension," "anxiety," "disappointment")

[1454] For example, an emotion engine can analyze the text "Project X isn't progressing" and identify the emotions "tension" and "anxiety."

[1455] Step 4: Identify the person in charge

[1456] The server searches the database for the most suitable agent based on the analysis results and the sentiment analysis results. The specific operations are as follows:

[1457] Input: Extracted keywords and identified sentiments

[1458] Data manipulation: Performing database queries to find the right person

[1459] Output: Optimal Rep

[1460] For example, the server might search the database for keywords like "Project X," "progress delay," and "code bug" to identify people who have solved similar problems in the past.

[1461] Step 5: Use generative AI

[1462] If the server cannot find a suitable person, it uses generative artificial intelligence to generate a solution. The specific operation is as follows:

[1463] Input: Keywords and sentiment analysis results

[1464] Data processing: Invoking generative AI to generate solutions

[1465] Output: The generated solution

[1466] For example, a generative artificial intelligence model generates a solution to the problem of "delays in the progress of Project X."

[1467] Step 6: Notification

[1468] The server notifies the person in charge or the user of the analysis results and generated solutions. The specific operations are as follows:

[1469] Input: Assignee or generated solution

[1470] Data processing: Creating notification messages

[1471] Output: Email, chat notification, dashboard alert

[1472] For example, the server might use a notification system to send a message to a responsible party saying, "There is a suspected bug in the code for project X."

[1473] In this way, the system efficiently supports problem-solving within companies through the steps of data collection, data analysis, sentiment analysis, identifying responsible parties, utilizing generative artificial intelligence, and notification.

[1474] (Application example 2)

[1475] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1476] In factories, various problems occur daily with the operation of robots and various equipment. Quickly identifying these problems and finding the appropriate person or solution is essential for improving productivity and streamlining troubleshooting. However, with conventional systems, the process from problem detection to resolution was complicated and took a lot of time and effort. In addition, emotion analysis was not incorporated, making it difficult to respond efficiently while taking into account the urgency of the problem and the emotional state of the personnel.

[1477] 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.

[1478] In this invention, the server includes means for collecting communication data, means for analyzing the communication data for problems and related keywords using natural language processing, means for searching a database for a relevant person based on the analyzed keywords, means for generating a response using generative artificial intelligence if the person is not found, means for notifying the person or the generated response, means including an emotion engine for recognizing the emotional state of the analyzed communication, means for coordinating an appropriate response based on the recognized emotional state, and means for including communication data provided by robots in the factory. This makes it possible to quickly and efficiently identify and analyze problems occurring in the factory and propose appropriate people or solutions.

[1479] "Communications data" refers to information collected within a factory or other environment in the form of emails, chat histories, video conference transcripts, sensor data from robots, etc.

[1480] "Natural language processing" is a technology for understanding text information from communication data and analyzing problems and related keywords.

[1481] "Keywords" are important words or phrases extracted through natural language processing to identify issues and related information.

[1482] A "database" is a collection of information that searches for relevant personnel based on analyzed keywords.

[1483] "Generative AI" refers to artificial intelligence technology that automatically generates answers and suggestions to solve problems.

[1484] An "emotion engine" is a device or program that recognizes the user's emotional state from analyzed communication data and adjusts appropriate responses based on that information.

[1485] A "personnel" is a person with specialized knowledge and skills for solving a problem.

[1486] A "robot" is a machine or device used to automate work in a factory.

[1487] "Means of notification" refers to the means for notifying the relevant personnel or systems of the analysis results and generated solutions.

[1488] The present invention is a system for quickly and efficiently identifying problems occurring within a factory and recommending appropriate personnel or solutions. The system is composed of the following main components:

[1489] Hardware and Software Configuration

[1490] server

[1491] The server has the following functions:

[1492] 1. Communication data collection: Collect various communication data provided by robots and operators in the factory. Through API access, obtain emails, chat history, video conference transcripts, and sensor data from robots in real time.

[1493] 2. Data analysis: The collected data is analyzed using natural language processing (NLP) technology to extract keywords related to the problem. Examples of NLP technology used include TextBlob.

[1494] 3. Use of emotion engine: Recognize the user's emotional state from the analyzed text data. The emotion engine identifies the urgency and stress the user (operator or robot) is feeling.

[1495] 4. Agent Search: Based on the results of the analysis and sentiment analysis, the database is searched for the most suitable agent. Agents are identified based on their past experience and skill sets stored in the database.

[1496] 5. Use of generative AI: If no suitable person can be found, a solution can be automatically generated using generative AI, which learns from past cases and provides solutions to similar problems.

[1497] 6. Notification: Notify personnel or users of the analysis results and generated solutions. Notification methods include email, chat notifications, and dashboard alerts.

[1498] Terminal

[1499] User devices that can be used to access the system include PCs, smartphones, and tablets.

[1500] Specific examples

[1501] Example 1: Case of a sensor abnormality in a factory robot

[1502] The server collects communication data from the robot indicating that the sensor is malfunctioning.

[1503] The data is analyzed using natural language processing technology to extract keywords such as "sensor malfunction" and "robot."

[1504] An emotion engine is used to analyze user emotions and identify "anxiety" and "urgency."

[1505] The system searches the database for staff who have dealt with similar problems in the past, and if no such staff is found, it uses generative artificial intelligence to generate a solution.

[1506] Notify generated solutions and assignees.

[1507] Prompt Sentence Examples

[1508] "Please suggest a solution if the robot's battery is rapidly depleting."

[1509] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1510] Step 1:

[1511] The server collects communication data provided by robots and operators in the factory. Specifically, emails, chat history, video conference transcripts, and sensor data from the robots are obtained in real time through API access and stored in internal storage. The input is a variety of communication data, and the output is data ready for analysis.

[1512] Step 2:

[1513] The server analyzes the collected communication data using natural language processing (NLP). The specific operations performed here are text extraction and keyword analysis. For example, TextBlob is used to extract keywords such as "sensor malfunction" and "robot." The input is the collected communication data, and the output is the extracted keywords.

[1514] Step 3:

[1515] The server recognizes the user's emotional state from the text data analyzed using the emotion engine. In this step, the emotion the user is feeling, such as "anxiety" or "urgency," is identified. The emotion engine performs emotion analysis on the input text data, and the identified emotional state is output.

[1516] Step 4:

[1517] The server searches the database for relevant staff members based on the analysis and sentiment analysis results. Specifically, it searches for staff members who have solved similar problems in the past and identifies the most suitable staff member. The input is keywords and sentiment analysis results, and the output is information about the identified staff member.

[1518] Step 5:

[1519] If the server cannot find a suitable person, it uses generative AI to automatically generate a solution. Here, it references past cases and generates solutions to similar problems. The input is the extracted keywords, and the output is the solution generated by the AI.

[1520] Step 6:

[1521] The server notifies the person in charge or the user of the analysis results and the generated solution. In this step, notifications are made via email, chat notifications, or dashboard alerts. The input is the generated solution and the person in charge information, and the output is the notification result sent to the user.

[1522] Example operation

[1523] As an example, consider the case where a factory robot reports a "sensor malfunction."

[1524] Step 1: Collect communication data from the robot regarding "sensor malfunctions."

[1525] Step 2: Analyze the collected data for keywords such as "sensor malfunction" and "robot."

[1526] Step 3: Use the emotion engine to recognize the emotion "anxiety" from the data.

[1527] Step 4: Search the database to identify the person who responded to the "sensor malfunction."

[1528] Step 5: If no suitable person can be found, use generative artificial intelligence to generate a solution.

[1529] Step 6: Notify the person or user of the generated solution.

[1530] Example prompt sentence:

[1531] "Please suggest a solution if the robot's battery is rapidly depleting."

[1532] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1533] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1534] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1535] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1536] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1537] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1538] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1539] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1540] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1541] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1542] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1543] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1544] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1545] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1546] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1547] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1548] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1549] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1550] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1551] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1552] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1553] The following is further disclosed regarding the above embodiment.

[1554] (Claim 1)

[1555] a means for collecting communications data;

[1556] means for analyzing the communication data using natural language processing to identify problems and related keywords;

[1557] A means for searching for relevant personnel from a database based on the analyzed keywords;

[1558] A means for generating an answer using generative artificial intelligence when the person in charge cannot be found;

[1559] The system includes a means for notifying the person or the generated answer.

[1560] (Claim 2)

[1561] The system of claim 1 , wherein the communication data includes emails, chat histories, and video conference transcripts.

[1562] (Claim 3)

[1563] 2. The system of claim 1, wherein the natural language processing based analysis includes keyword extraction and problem recognition.

[1564] (Claim 4)

[1565] 2. The system according to claim 1, wherein the means for searching for relevant personnel from the database evaluates the relevance based on past correspondence records.

[1566] (Claim 5)

[1567] 2. The system according to claim 1, wherein the means for generating an answer using the generative artificial intelligence generates an appropriate answer based on past cases.

[1568] "Example 1"

[1569] (Claim 1)

[1570] a means for collecting communications data;

[1571] means for analyzing the communication data using natural language processing to identify problems and related keywords;

[1572] A means for searching for relevant personnel from a database based on the analyzed keywords;

[1573] A means for generating an answer using generative artificial intelligence when the person in charge cannot be found;

[1574] means for notifying the person in charge or the generated answer;

[1575] A means for executing each process of collecting, analyzing, searching for a person in charge, using the generation AI, and notifying the communication data using each API;

[1576] A system including:

[1577] (Claim 2)

[1578] The system of claim 1 , wherein the communication data includes emails, chat histories, and video conference transcripts.

[1579] (Claim 3)

[1580] 2. The system of claim 1, wherein the natural language processing based analysis includes keyword extraction and problem recognition.

[1581] "Application Example 1"

[1582] (Claim 1)

[1583] a means for collecting communications data;

[1584] means for analyzing the communication data using natural language processing to identify problems and related keywords;

[1585] A means for searching for relevant personnel from a database based on the analyzed keywords;

[1586] A means for generating an answer using generative artificial intelligence when the person in charge cannot be found;

[1587] means for notifying the person in charge or the generated answer;

[1588] A means of monitoring abnormalities on the production line in real time, identifying problems as they occur, and quickly notifying the appropriate technicians.

[1589] A means of proposing optimal solutions via a generative AI model using automatically generated prompts;

[1590] A system including:

[1591] (Claim 2)

[1592] 10. The system of claim 1, wherein the communication data includes emails, chat histories, video conference transcripts, and manufacturing line monitoring data.

[1593] (Claim 3)

[1594] 2. The system of claim 1, wherein the natural language processing based analysis includes keyword extraction and problem recognition.

[1595] "Example 2: Combining Emotion Engines"

[1596] (Claim 1)

[1597] a means for collecting communications data;

[1598] means for analyzing the communication data using natural language processing to identify problems and related keywords;

[1599] means for identifying a user's emotion using the analyzed keywords and an emotion analysis engine;

[1600] A means for searching for relevant personnel from a database based on the analysis results;

[1601] A means for generating an answer using generative artificial intelligence when the person in charge cannot be found;

[1602] The system includes a means for notifying the person or the generated answer.

[1603] (Claim 2)

[1604] The system of claim 1 , wherein the communication data includes emails, chat histories, and video conference transcripts.

[1605] (Claim 3)

[1606] 2. The system of claim 1, wherein the natural language processing based analysis includes keyword extraction and problem recognition.

[1607] "Application example 2 when combining emotion engines"

[1608] (Claim 1)

[1609] a means for collecting communications data;

[1610] means for analyzing the communication data using natural language processing to identify problems and related keywords;

[1611] A means for searching for relevant personnel from a database based on the analyzed keywords;

[1612] A means for generating an answer using generative artificial intelligence when the person in charge cannot be found;

[1613] means for notifying the person in charge or the generated answer;

[1614] means including an emotion engine for recognizing an emotional state of the analyzed communication;

[1615] a means of tailoring appropriate responses based on the perceived emotional state;

[1616] Means including communication data provided by robots in factories

[1617] A system including:

[1618] (Claim 2)

[1619] 10. The system of claim 1, wherein the communication data includes emails, chat histories, video conference transcripts, and sensor data collected from robots in a factory.

[1620] (Claim 3)

[1621] 2. The system of claim 1, wherein the natural language processing based analysis includes keyword extraction and issue recognition and sentiment analysis. [Explanation of symbols]

[1622] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting communications data; means for analyzing the communication data using natural language processing to identify problems and related keywords; A means for searching for relevant personnel from a database based on the analyzed keywords; A means for generating an answer using generative artificial intelligence when the person in charge cannot be found; The system includes a means for notifying the person or the generated answer.

2. The system of claim 1 , wherein the communication data includes emails, chat histories, and video conference transcripts.

3. The system of claim 1 , wherein the natural language processing based analysis includes keyword extraction and problem recognition.

4. 2. The system according to claim 1, wherein the means for searching for relevant personnel from the database evaluates the relevance based on past correspondence records.

5. The system according to claim 1 , wherein the means for generating an answer using the generative artificial intelligence generates an appropriate answer based on past cases.

Images