System

Abstract

A system is provided.SOLUTION: A system comprising: means for storing information in a tag format based on a specialized area and experience of each employee; means for recording a coverage and a responsibility degree of each team as numerical values in a database; means for receiving an input of consultation contents by a user; means for extracting a necessary tag and a responsibility degree from the consultation contents; and means for generating information of an appropriate escalation destination and notifying the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] This project aims to solve the "internal Dragon Quest" phenomenon that occurs in corporate organizations during project progress, a problem where coordination and information gathering take a huge amount of time and effort. Specifically, the combination of three factors - lack of information, difficulty in coordination, and unclear responsibilities - makes it difficult to quickly find the appropriate escalation point. This hinders efficient internal communication and the smooth execution of projects. [Means for solving the problem]

[0005] These issues are resolved by a system that includes a means for storing information in tag format based on each employee's area of ​​expertise and experience, a means for recording each team's scope of responsibility and degree of responsibility in a database as a number, a means for accepting user input of consultation content, a means for extracting the necessary tags and degree of responsibility from the consultation content, a means for searching the database for the optimal escalation destination based on the extracted tags and degree of responsibility, a means for generating information on the appropriate escalation destination and notifying the user, and a means for tracking each team's degree of responsibility and updating the evaluation. This allows necessary information to be quickly collected, facilitating coordination, and clarifying the scope of responsibility for escalations, enabling efficient project progress.

[0006] "Tag format" refers to a method of classifying and identifying information using specific keywords or labels (tags).

[0007] "Responsibility" is a numerical representation of the degree of responsibility that a particular team or individual has for a particular task or issue.

[0008] A "database" is a system or structured collection of data for efficiently storing, retrieving, and updating information.

[0009] "User" refers to the person who uses the system or application, i.e., the end user.

[0010] "Extraction" means selecting specific elements from data or information.

[0011] "Escalation" is the process of transferring or progressing a problem or issue to a higher level for resolution.

[0012] "Generation" refers to the process of creating new information or data.

[0013] "Tracking" means to continuously monitor and record specific data or conditions.

[0014] "Evaluation" means judging the value, performance, quality, etc. of a specific object and assigning a numerical value or grade to it. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention is an efficient in-house escalation management system that stores each employee's area of ​​expertise in tag format and quantifies and records their degree of responsibility in a database, making it possible to quickly search for the most appropriate escalation destination and notify the user.

[0037] Program processing

[0038] Data Storage

[0039] Server: Store each employee's area of ​​expertise and experience in the employee directory in "tag format." For example, assign tags such as "project management," "data analysis," and "front-end development."

[0040] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "Technology Development" is "High."

[0041] Submit a consultation

[0042] User: Posts a request through the UI. For example, they might write, "I need data analysis for a new project," and set the associated tag as "Data Analysis" and the required level of responsibility as "Medium."

[0043] Terminal: Sends the consultation details entered by the user to the server.

[0044] Escalation selection and notification

[0045] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility levels." For example, the "data analysis" tag and "medium" responsibility level are extracted.

[0046] Generative AI: Searches for suitable teams from the database based on the extracted tags and responsibility levels. It uses a tag matching algorithm to filter out the best teams and selects the team whose responsibility level meets the criteria.

[0047] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be suitable, it generates the team's expertise and contact information.

[0048] Server: Notifies the user of the generated team introduction information. For example, informs the user that "Team B is suitable for data analysis and has a medium level of responsibility."

[0049] Specific examples

[0050] scenario

[0051] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project.

[0052] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0053] 2. Terminal: Sends this information to the server.

[0054] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels.

[0055] 4. Generative AI: Based on the extracted information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0056] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0057] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0058] 7. Terminal: Notify the user of Team B's introduction information.

[0059] 8. User: Check the notified information and contact Team B.

[0060] This system will streamline escalation and information gathering within the company, eliminating the "internal Dragon Quest" phenomenon, and ultimately promoting faster project progress and efficient problem solving.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[0064] Step 2:

[0065] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[0066] Step 3:

[0067] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[0068] Step 4:

[0069] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[0070] Step 5:

[0071] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." Specifically, it parses the request content and extracts the information such as "new project," "technical issues," and "high" responsibility level.

[0072] Step 6:

[0073] Generative AI: Searches for the most suitable team from the database based on the extracted tags and responsibility levels. Specifically, it uses a tag-matching algorithm to filter relevant teams and selects the team whose responsibility level meets the criteria.

[0074] Step 7:

[0075] Generative AI: Generates introduction information for the selected team, specifically creating written information about the selected team's areas of expertise, responsibilities, and contact information.

[0076] Step 8:

[0077] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[0078] Step 9:

[0079] Terminal: Notify the user of the escalation destination and team introduction information. Specifically, the introduction information is displayed on the UI, and the notification function is used to notify the user as needed.

[0080] Step 10:

[0081] User: Review the information provided and contact the appropriate escalation channel, either by contacting the team directly using the contact information provided or by requesting their help in resolving the issue.

[0082] By following these steps, necessary information can be gathered quickly and the appropriate escalation point can be efficiently selected. This will eliminate the "internal Dragon Quest" phenomenon within the company and make the progress of the project much smoother.

[0083] Example 1

[0084] 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."

[0085] Conventional corporate escalation management systems make it difficult to quickly find the appropriate escalation contact point, making it difficult to resolve problems efficiently. In particular, they lack sufficient information management based on the expertise and experience of each employee or team, making it time-consuming to select the optimal escalation contact point based on the level of responsibility. Furthermore, inappropriate selection of the escalation contact point can delay problem resolution, negatively impacting the overall progress of the project.

[0086] 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.

[0087] In this invention, the server includes a means for storing information in tag format based on each employee's area of ​​expertise and experience, a means for recording each team's scope of responsibility and degree of responsibility in a database as numerical values, and a means for accepting input of consultation content by users and transmitting the content to the server, thereby enabling efficient escalation management.

[0088] "Tag format" is a metadata format that identifies each employee's area of ​​expertise and experience, and is additional information that makes searching and filtering easier.

[0089] "Degree of responsibility" is a numerical representation of the level of responsibility each team or individual has for a specific job or task, and is used to select the destination of escalation.

[0090] A "database" is a system for systematically storing, managing, and searching related data such as employee information, team responsibilities, and levels of responsibility.

[0091] The "contents of consultation" is text information that the user inputs in response to a specific problem or question, and is reference information when selecting an escalation destination.

[0092] "Generated artificial intelligence" refers to algorithms and models that search a database for optimal escalation destinations and generate appropriate referral information.

[0093] A "tag matching algorithm" is a calculation method for detecting matches between multiple tag data and selecting the optimal combination.

[0094] "Notification" is a communication method for informing the user of important information, and includes the results of selection of the escalation destination.

[0095] "Tracking" is the process of tracking each team's responsibility level and recording any fluctuations.

[0096] "Evaluation" is the process of measuring the performance and response capabilities of each team or employee based on data such as tracked responsibility levels.

[0097] The present invention relates to a system for realizing efficient escalation management within a company, and is implemented using the following hardware and software configuration.

[0098] Hardware and Software Configuration

[0099] server

[0100] The server is the central part of the system and performs the following functions:

[0101] Employee directory management: The server stores each employee's area of ​​expertise and experience in the form of tags. For example, tags such as "project management," "data analysis," and "front-end development" are assigned.

[0102] Team information management: The server records each team's scope of responsibility and degree of responsibility in a database as a numerical value. For example, Team A's degree of responsibility for "technology development" is "high."

[0103] Receiving and analyzing consultation content: The server receives the consultation content from the user and extracts the necessary tags and responsibility levels.

[0104] Escalation Selection: The server uses a generative AI model to search the database for the appropriate team.

[0105] Notification function: The server generates appropriate escalation information and notifies the user.

[0106] Terminal

[0107] Terminals provide the interface through which users access and operate the system:

[0108] Input of consultation content: The user inputs the consultation content through the device UI. For example, the user inputs "Data analysis is required for a new project," sets the related tag as "Data analysis," and sets the required responsibility level as "Medium."

[0109] Data transmission: The terminal transmits the consultation details entered by the user to the server.

[0110] User

[0111] The user does the following:

[0112] Posting a consultation: A user posts a consultation regarding a specific problem or question.

[0113] Receiving the result: The user receives the notification from the server and checks the contents.

[0114] Contacting the escalation destination: The user contacts the notified escalation destination.

[0115] Data processing and calculation

[0116] 1. Data storage: First, the server retrieves each employee's area of ​​expertise from the employee directory and stores it in the database in tag format. It also records the scope of each team's responsibilities and the degree of responsibility as a number.

[0117] 2. Posting and sending consultation details: The user inputs the consultation details through the device's UI, and the device sends the information to the server.

[0118] 3. Analysis of consultation content: The server analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[0119] 4. Selection of escalation destination: The generative AI model searches the database for the optimal escalation destination based on the extracted tags and degree of responsibility.

[0120] 5. Notification: The server notifies the user of the information about the created escalation destination.

[0121] Specific examples

[0122] For example, if a user in department A is looking for an escalation point to "resolve technical issues related to a new project":

[0123] 1. The user enters the consultation content in the UI, selects the tags "Technical Issue" and "New Project," and sets the required level of responsibility to "High."

[0124] 2. The terminal sends the input information to the server.

[0125] 3. The server analyzes the received information and extracts the necessary tags and responsibility levels.

[0126] 4. The generative AI model searches the database for the optimal team. In this case, it determines that Team B is the best team because it can handle the technical challenges.

[0127] 5. The server notifies the user of Team B's introduction information.

[0128] Prompt Sentence Examples

[0129] "A user with a technical issue related to a new project is looking for an appropriate escalation point. The user posts the consultation as 'Solving the technical issue for the new project,' selects 'Technical issue' and 'New project' as tags, and sets the required level of responsibility as 'High.' Please analyze this information, search the database for the most suitable team, and notify the user of the introduction information."

[0130] The above is an embodiment of the invention.

[0131] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0132] Step 1:

[0133] Stores employee specialties in tag format

[0134] Server: Extracts each employee's area of ​​expertise and experience from the employee directory and formats them into "tag format." For example, it generates tags such as "project management," "data analysis," and "front-end development."

[0135] Input: Employee directory data

[0136] Data processing and data calculation: An extraction algorithm is used to obtain area of ​​expertise information from the employee directory, and a tagging algorithm is used to generate tags.

[0137] Output: Tagged domain data

[0138] What happens: The server inserts new records into the "expertise" table of the database, adding each employee's ID and corresponding tag.

[0139] Step 2:

[0140] Record each team's scope of responsibility and level of responsibility

[0141] Server: Determines the scope of each team's responsibilities and their degree of responsibility, quantifies them, and records them in the database. For example, Team A's responsibility level for "Technology Development" is "High."

[0142] Input: Team Roles and Responsibilities

[0143] Data processing and calculation: The scope of responsibility and degree of responsibility are quantified and stored in the database.

[0144] Output: Updated database

[0145] Specific operation: The server creates a "team information" table in the database and adds each team's ID, area of ​​responsibility, and degree of responsibility.

[0146] Step 3:

[0147] Users post their inquiries

[0148] User: Enter the details of the consultation using the dedicated UI. Write specific details such as "Data analysis is required for a new project," and set the related tag "Data Analysis" and the required level of responsibility as "Medium."

[0149] Input: consultation content, tags, degree of responsibility

[0150] Output: User input data

[0151] Specific operation: The user enters the necessary information into the input form and clicks the "Submit" button.

[0152] Step 4:

[0153] The entered data is sent to the server

[0154] Terminal: The consultation details entered by the user are sent to the server as an HTTP request. At this time, the consultation details, tags, and responsibility level are sent in JSON format.

[0155] Input: User-entered data

[0156] Data processing and data calculation: Convert user input data into JSON format and send it to the server.

[0157] Output: JSON format data

[0158] Specific operation: A POST request is generated from the browser to the server, and the content is included in the request body.

[0159] Step 5:

[0160] Analyze received consultation content

[0161] Server: Parses the received JSON data, extracts the consultation content, tags, and responsibility level, and validates the content for accuracy.

[0162] Input: JSON format data

[0163] Data processing and data calculation: JSON parsing and data validation.

[0164] Output: Extracted tags and responsibility counts

[0165] Specific behavior: Uses a JSON parser to store data in variables and checks for required fields.

[0166] Step 6:

[0167] Find the right team

[0168] Generative AI: Search for suitable teams in the database based on the extracted tag "Data Analysis" and the responsibility level "Medium". Filter candidate teams using a tag matching algorithm.

[0169] Input: Extracted tags and responsibility levels

[0170] Data processing and data calculation: Issue an SQL query to extract teams that match the criteria from the database.

[0171] Output: Optimal team

[0172] What it does: Runs an SQL query to search the database and selects teams that match the criteria.

[0173] Step 7:

[0174] Generate introduction information for selected teams

[0175] Generative AI: Generates introductory information for the selected team—for example, Team B's areas of expertise and contact information.

[0176] Input: Best team information

[0177] Data processing and data calculation: Run a script to automatically generate an introduction.

[0178] Output: Generated referral information

[0179] Specific operation: Run a script to generate an introduction based on the acquired team information.

[0180] Step 8:

[0181] Notify user

[0182] Server: Prepares the generated team introduction information for notification to the user. For example, it formats the notification content to say, "Team B is suitable for data analysis and has medium responsibility."

[0183] Input: Generated referral information

[0184] Data processing and data calculation: The notification content is inserted into an HTML template to create a response for display in the user's UI.

[0185] Output: User notification

[0186] Specific operation: The notification content is formatted in HTML and a response is sent to the user's device.

[0187] The above are the processing steps of the program for this system.

[0188] (Application example 1)

[0189] 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."

[0190] Conventional escalation management systems have made it difficult to quickly select and respond to problems and technical issues that arise within a company. As a result, it often takes time to resolve problems, resulting in a decline in production efficiency. Furthermore, particularly with factory equipment, a delayed response to an abnormality can lead to major losses or accidents. To solve these issues, an escalation management system needs the ability to select and notify the most appropriate engineer in real time.

[0191] 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.

[0192] In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and degree of responsibility in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and degrees of responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and degrees of responsibility; means for generating information on the appropriate escalation destination and notifying the user; means for posting a problem in cooperation with a robot that detects abnormalities in factory equipment; means for analyzing the area of ​​expertise and degree of responsibility required for the problem and searching for an appropriate engineer; means for sending a notification to the engineer based on the search results; and means for tracking each team's degree of responsibility and updating their evaluation. This makes it possible to select the optimal engineer in real time to respond quickly to abnormalities and technical issues in factory equipment.

[0193] An "area of ​​expertise" is a field or range of fields in which an employee with specific skills or knowledge excels.

[0194] "Experience" refers to the accumulation of knowledge and skills that an employee has gained from actual work or projects they have undertaken in the past.

[0195] "Tag format" is a method of assigning specific keywords or categories to each piece of information, making it easier to classify and search for information.

[0196] "Degree of responsibility" is a numerical representation of the degree of responsibility each team or employee has for a specific task or project.

[0197] A "database" is an information system that stores data based on a certain structure and enables efficient searching and processing.

[0198] A "user" is an individual or department that uses the system to input the details of a consultation.

[0199] "Consultation content" refers to detailed information about a problem or issue that a user enters through the system.

[0200] "Extraction" refers to the process of selecting necessary elements and keywords from the provided information.

[0201] An "optimal escalation point" is a team or employee selected to best respond to a particular issue or challenge.

[0202] "Generation" is the process of creating new information or data using algorithms or programs.

[0203] "Notification" refers to the act of sending information from the system to users or technicians, or that information.

[0204] "Factory equipment" refers to all machines and devices used in production lines and manufacturing processes.

[0205] An "abnormality" is a phenomenon or event that deviates from the standard operating conditions of factory equipment.

[0206] A "robot" is a mechanical device that performs autonomous or controlled operations within a factory facility.

[0207] An "engineer" is a professional who has specific techniques and skills and who solves problems and maintains equipment.

[0208] "Tracking" refers to the process or means of tracking and recording specific data or circumstances.

[0209] Evaluation is the process of quantifying or verbalizing the behavior and achievements of a team or employee based on specific criteria.

[0210] This invention is a system for efficient escalation management that utilizes tags and responsibility levels based on employees' areas of expertise and experience. The system is composed of the following means.

[0211] Data storage method

[0212] The server stores each employee's area of ​​expertise and experience in "tag format." For example, tags such as "mechanical engineering," "electrical engineering," and "program control" are assigned. Furthermore, the scope of each team's responsibilities and degree of responsibility are recorded as numerical values ​​in the database. For example, Team A's level of responsibility for "mechanical problems" is set to "high."

[0213] Detecting anomalies in factory equipment and reporting problems

[0214] The robot detects abnormalities within factory equipment, such as abnormal vibrations or control errors. The detected abnormalities are sent to the server, along with detailed information about the abnormality (for example, "abnormal vibration detected, restart failed, cause unknown").

[0215] Analysis of consultation content and selection of escalation destination

[0216] The server analyzes the received consultation content. In this analysis, it extracts the necessary "tags" and "responsibility levels." For example, the "mechanical problem" tag and "high" responsibility level are extracted.

[0217] The generative AI model is then used to search the database for the most suitable technician based on the extracted tags and responsibilities, using a tag-matching algorithm. For example, Technician B is determined to be the best fit, and his / her expertise and contact information are generated.

[0218] Notification method for technicians

[0219] The server notifies the robot of the generated engineer information. The robot then notifies the engineer of the received information in real time. For example, it may send a notification saying, "We will ask Engineer B to identify the cause of the abnormal vibration and repair it."

[0220] Evaluation and Update Methods

[0221] The server tracks the responsibility rating of each team and engineer and updates the rating. For example, if Engineer B resolves the issue quickly and effectively, his / her responsibility rating will be updated from "medium" to "high."

[0222] Specific examples

[0223] Consider a scenario where abnormal vibrations are detected in a factory.

[0224] 1. The robot sends a message to the server saying, "Abnormal vibration detected, restart failed, cause unknown."

[0225] 2. The server analyzes the problem content and extracts the "mechanical problem" tag and the "high" responsibility score.

[0226] 3. The generative AI model selects Technician B from the database as the best person to escalate the issue based on the tag and degree of responsibility.

[0227] 4. The server notifies the robot of the generated engineer information, and the robot notifies Engineer B in real time.

[0228] 5. Engineer B solves the problem, the result is recorded on the server, and the responsibility score is updated.

[0229] Example prompt for a generative AI model:

[0230] "Select the most suitable engineer based on the employee's area of ​​expertise and level of responsibility, and generate engineer information that matches the following tags and levels of responsibility: Tag: ['Mechanical Problem'] Level of Responsibility: 'High'"

[0231] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0232] Step 1:

[0233] The server stores each employee's area of ​​expertise and experience in the form of tags. To do this, it receives employee profile data and stores their area of ​​expertise (e.g., "mechanical engineering," "electrical engineering," etc.) and experience level (e.g., "entry," "intermediate," "advanced") as tags in the database. The input is the employee profile data, and the output is the updated database record.

[0234] Step 2:

[0235] The server records each team's scope of responsibility and degree of responsibility as a numerical value in the database. This allows each team's area of ​​expertise and its degree of responsibility (e.g., "high," "medium," or "low") to be stored as structured data. The input is the information on each team's scope of responsibility and degree of responsibility, and the output is the numerical data stored in the database.

[0236] Step 3:

[0237] The robot detects anomalies in factory equipment and sends details to a server. For example, it analyzes sensor data to identify anomalies such as "abnormal vibration detected, restart failed, cause unknown" and sends that information to the server. The input is the sensor data and detailed information about the anomaly, and the output is an anomaly report sent to the server.

[0238] Step 4:

[0239] The server analyzes the received anomaly report and extracts the necessary tags and responsibility levels. This analysis uses natural language processing technology to derive, for example, a "mechanical problem" tag and a "high" responsibility level. The input is the anomaly report, and the output is the extracted tags and responsibility levels.

[0240] Step 5:

[0241] The server uses a generative AI model to search the database for the most suitable engineer based on the extracted tags and responsibility levels. This process uses a tag-matching algorithm to select the engineer who best matches, for example, the "mechanical engineering" tag and "high" responsibility level. The input is the tag and responsibility level, and the output is the information on the most suitable engineer.

[0242] Step 6:

[0243] The server notifies the robot of the generated technician information, which includes the technician's specialty and contact information. The input is the information of the best technician, and the output is the technician notification sent to the robot.

[0244] Step 7:

[0245] The robot sends a real-time notification to the appropriate technician based on the received technician information. For example, it may send a message saying, "We will ask technician B to identify the cause of the abnormal vibration and repair it." The input is the technician notification, and the output is the notification message to the technician.

[0246] Step 8:

[0247] The engineer solves the problem and reports the results to the server, which receives the report and updates the engineer's responsibility score. The input is the problem-solving report, and the output is a database record of the updated responsibility score.

[0248] 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.

[0249] This invention is a system that combines an emotion engine with an efficient in-house escalation management system, which recognizes the user's emotions and suggests the most appropriate escalation destination, enabling efficient and empathetic responses.

[0250] Program processing

[0251] Data Storage

[0252] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[0253] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[0254] Consultation posting and sentiment analysis

[0255] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[0256] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[0257] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[0258] Escalation selection and notification

[0259] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level," while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issues," "high" responsibility level, and "urgency."

[0260] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility levels, and emotional information. It uses a tag-matching algorithm to filter relevant teams and selects the team that meets the responsibility level criteria and takes emotional information into account.

[0261] Generation AI: Generates introductory information for the selected team. For example, if Team B is determined to be suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[0262] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[0263] Response and evaluation

[0264] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[0265] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[0266] Server: Continuously tracks each team's responsibility rating and updates the rating based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, the server updates their responsibility rating and emotional response rating.

[0267] Specific examples

[0268] scenario

[0269] A user in department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is highly stressed and needs a solution quickly.

[0270] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0271] 2. Terminal: Sends this information to the server.

[0272] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user feels a high level of urgency.

[0273] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0274] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0275] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0276] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[0277] 8. User: Check the notified information and contact Team B urgently.

[0278] This satisfying collaboration allows necessary information to be gathered quickly and the appropriate escalation point to be selected efficiently. This eliminates the "internal Dragon Quest" phenomenon within the company and makes project progress much smoother. Furthermore, by taking the user's feelings into consideration, a more empathetic and prompt response is possible.

[0279] The processing flow will be explained below.

[0280] Step 1:

[0281] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, tags such as "data analysis," "project management," and "front-end development" are extracted from each employee's resume and project experience and stored in the database.

[0282] Step 2:

[0283] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "technology development" is registered as "high," and Team B's level of responsibility for "market analysis" is registered as "medium."

[0284] Step 3:

[0285] User: Enters and posts the content of the consultation through the UI. For example, to discuss technical issues related to a new project, the user selects the tags "New Project" and "Technical Issues" and sets the required level of responsibility as "High."

[0286] Step 4:

[0287] Terminal: Sends the consultation details entered by the user to the server. Specifically, the entered data is sent to the server as an HTTP request from the form.

[0288] Step 5:

[0289] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." For example, it parses and extracts information on "new projects," "technical issues," and "high" responsibility level.

[0290] Step 6:

[0291] Emotion engine: Analyzes the text of the consultation content and determines the user's emotions. Specifically, it uses natural language processing technology to detect whether the user is feeling urgency or stress. For example, it extracts the emotion "very urgent" from the consultation content.

[0292] Step 7:

[0293] Generative AI: Searches the database for the most appropriate escalation destination based on required tags, responsibility, and sentiment information. It uses a tag-matching algorithm to filter relevant teams, and also takes sentiment information into account to select teams with a suitable responsibility level.

[0294] Step 8:

[0295] Generation AI: Generates introductory information about the selected team. For example, it creates detailed information in text format, such as "Team B can handle technical issues and is suitable for emergency response."

[0296] Step 9:

[0297] Server: Stores the generated team introduction information in a database and returns it to the terminal. The generated introduction information is added to the database and sent to the terminal as an HTTP response.

[0298] Step 10:

[0299] Device: Notify the user of the escalation destination and team introduction information. Specifically, display on the UI the message "Team B is suitable, and the contact information for the person in charge is as follows," and notify by push notification or email as necessary.

[0300] Step 11:

[0301] User: Review the information provided and contact the appropriate escalation point. Specifically, use the provided contact information to contact Team B directly or request their cooperation in resolving the issue.

[0302] Step 12:

[0303] Server: Tracks each team's responsibility rating and updates it based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, its responsibility rating and emotional response rating will be updated.

[0304] By performing these steps sequentially, the optimal escalation destination is selected taking into account the user's feelings, enabling efficient and empathetic problem solving.

[0305] Example 2

[0306] 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."

[0307] Conventional escalation management systems simply determine the escalation destination based on the work content and the specialist area of ​​the person in charge, without considering the user's feelings or urgency, making it difficult to provide a quick and empathetic response. Furthermore, if the appropriate person in charge is not selected properly, problem resolution is delayed and work efficiency decreases.

[0308] 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 storing information in tag format based on each employee's skill area and work experience; means for recording each team's scope of work and responsibility in a database as numerical values; means for accepting input of consultation content by a user; means for transmitting the input consultation content to the server; means for analyzing the user's emotions from the consultation content; means for extracting necessary tags and responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags, responsibility, and emotion information; means for generating information on appropriate escalation destinations and notifying the user; and means for tracking each team's responsibility and updating the evaluation. This enables quick and empathetic selection of an escalation destination that also takes into account the user's emotions and urgency.

[0309] 1. "Skill areas of each employee"

[0310] Each employee's skill area refers to the field or area in which the employee has expertise or experience, such as data analysis, project management, or front-end development.

[0311] 2. "Work experience"

[0312] Work experience refers to the experience and achievements of an employee in the work or projects they have worked on in the past, which reveals their skill set and expertise.

[0313] 3. "Tag Format"

[0314] Tagging refers to a data format that categorizes information with specific keywords or labels to facilitate searching and filtering. It is used to represent each employee's skill areas and work experience.

[0315] 4. "Scope of Work"

[0316] The scope of work refers to the area of ​​work or project that each team is responsible for, specifically, the team's work content, such as technology development or market analysis.

[0317] 5. “Responsibility”

[0318] Responsibility is a numerical representation of how much responsibility each team or employee has for a particular task or issue, and can be high, medium, or low.

[0319] 6. "Consultation Content"

[0320] Consultation content refers to specific problems or issues that users post through the system for which they seek advice or support, including technical issues related to new projects.

[0321] 7. “Emotional Analysis”

[0322] Sentiment analysis refers to the process of analyzing a user's emotional state (e.g., stress, urgency) from text data using natural language processing techniques.

[0323] 8. "Best escalation point"

[0324] The optimal escalation destination is the team or employee that is determined to be able to respond most appropriately based on the content of the consultation and the results of sentiment analysis.

[0325] 9. "Generate Information"

[0326] Information generation refers to the process of creating specific text or data formats to notify users based on the extracted data.

[0327] 10. "Tracking"

[0328] Tracking is the process of continuously monitoring specific data or metrics, recording and evaluating them as needed, to continually assess each team's accountability.

[0329] 11. "Update your rating"

[0330] Refreshing ratings refers to the process of keeping each team or employee's responsibilities and performance ratings up to date based on the data and feedback obtained through tracking.

[0331] This invention is an efficient in-company escalation management system that is implemented in a form that combines an emotion engine. This enables efficient and empathetic responses by recognizing the user's emotions and suggesting the most appropriate escalation destination. The specific configuration and operation are described below.

[0332] 1. Data Storage

[0333] Server: Stores information in tag format based on each employee's skill area and work experience. Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[0334] Server: Records the scope of work and level of responsibility of each team in a database as a number. For example, each team can register the level of responsibility for the field or issue they are responsible for (e.g., "technology development" or "market analysis") as a number such as "high," "medium," or "low."

[0335] 2. Posting of consultations and sentiment analysis

[0336] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, select tags such as "new project" or "technical issues" and set the required level of responsibility as "high."

[0337] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[0338] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[0339] 3. Escalation Selection and Notification

[0340] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility level, while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issue," "high" responsibility level, and "urgency."

[0341] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility, and emotion information. It uses a tag matching algorithm to filter relevant teams and selects the team that meets the responsibility criteria and takes emotion information into account.

[0342] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be the most suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[0343] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[0344] 4. Response and Evaluation

[0345] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[0346] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[0347] Server: Continuously tracks each team's responsibility and updates their evaluation based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, it updates their responsibility and emotional response.

[0348] Specific examples

[0349] scenario

[0350] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is feeling very stressed and needs a solution quickly.

[0351] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0352] 2. Terminal: Sends this information to the server.

[0353] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user has a high level of urgency.

[0354] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0355] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0356] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0357] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[0358] 8. User: Check the notified information and contact Team B urgently.

[0359] In this way, necessary information is gathered quickly and the appropriate escalation point is efficiently selected. This eliminates the "internal Dragon Quest" phenomenon within the company and makes the progress of projects smoother. Also, by taking the user's feelings into consideration, more empathetic and prompt responses are possible.

[0360] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0361] Step 1:

[0362] Server: Stores information in tag form based on each employee's skill area and work experience.

[0363] Specific operation:

[0364] Input: Resume and project experience data for each employee.

[0365] Data processing: Extract tags such as "data analysis," "project management," and "front-end development" from each employee's resume and project experience.

[0366] Output: Save the extracted tags to a database.

[0367] Step 2:

[0368] Server: Record each team's scope of work and level of responsibility in a database.

[0369] Specific operation:

[0370] Input: Data on each team's work content and scope of responsibilities.

[0371] Data processing: Classify the level of responsibility for each team's scope of work (such as "technology development" or "market analysis") into a numerical value of "high," "medium," or "low."

[0372] Output: Record the classified responsibility in a database.

[0373] Step 3:

[0374] User: Enters the consultation details through the UI and posts.

[0375] Specific operation:

[0376] Input: The consultation topic, tags (e.g., "New Project" or "Technical Issue"), and responsibility level (e.g., "High") that the user enters into the UI form.

[0377] Data processing: The input consultation content is classified in tag format and the required level of responsibility is confirmed.

[0378] Output: The submitted consultation content is sent to the server via the form.

[0379] Step 4:

[0380] Terminal: Sends the entered consultation details to the server.

[0381] Specific operation:

[0382] Input: Consultation content data entered by the user.

[0383] Data processing: Convert the data entered in the form into an HTTP request.

[0384] Output: Forwarded to the server as an HTTP request.

[0385] Step 5:

[0386] Emotion engine: Analyzes the user's emotions from the content of the consultation.

[0387] Specific operation:

[0388] Input: Text data of the consultation content sent from the server.

[0389] Data processing: Using text analysis techniques, we analyze emotions such as stress and urgency felt by the user.

[0390] Output: Generates sentiment analysis results (e.g., "urgent" or "stressed").

[0391] Step 6:

[0392] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[0393] Specific operation:

[0394] Input: Consultation details and emotion analysis results sent from the device.

[0395] Data processing: Extract tags such as "new project," "technical issue," and "high" responsibility level, as well as emotional information, from the consultation content.

[0396] Output: The extracted information is sent to a generative AI model.

[0397] Step 7:

[0398] Generative AI: Searches for the appropriate team from the database based on extracted tags, responsibilities, and sentiment information, and generates introduction information.

[0399] Specific operation:

[0400] Input: Tags, responsibility, and emotion information sent from the server.

[0401] Data processing: Using a tag-matching algorithm, we filter relevant teams from the database and select the most suitable team based on responsibility and sentiment information.

[0402] Output: Generates introductory information about the selected team (team name, area of ​​expertise, area of ​​responsibility, contact information).

[0403] Step 8:

[0404] Server: Stores the generated team introduction information in a database and returns it to the terminal.

[0405] Specific operation:

[0406] Input: Team introduction information sent from the generation AI.

[0407] Data processing: Store the information in a database and convert it into an HTTP response format.

[0408] Output: Sends a reply to the terminal.

[0409] Step 9:

[0410] Terminal: Notifies user of escalation and team introduction information.

[0411] Specific operation:

[0412] Input: Team introduction information sent from the server.

[0413] Data processing: Formatting data in a format that can be displayed on the UI.

[0414] Output: The referral information is notified to the user.

[0415] Step 10:

[0416] User: Review the information provided and contact the appropriate escalation point.

[0417] Specific operation:

[0418] Input: Contact information for escalation from the terminal.

[0419] Data processing: We will contact the team directly using the contact information you provide.

[0420] Output: A query is made.

[0421] Step 11:

[0422] Server: Continuously track each team's accountability and update the ratings.

[0423] Specific operation:

[0424] Input: Feedback data from each team and the analysis results of the emotion engine.

[0425] Data processing: Based on feedback data and sentiment information, update each team's responsibility and performance evaluation.

[0426] Output: Responsibility and rating are updated in the database.

[0427] (Application example 2)

[0428] 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."

[0429] In conventional factories, there is a need for a system that can detect equipment anomalies early and efficiently notify the appropriate escalation contact point. It is particularly important to respond quickly and accurately to urgent problems. However, typical escalation management systems often do not take emotional information into account and instead rely solely on mechanical responses. This results in delayed responses after an anomaly is detected, leading to problems such as reduced productivity throughout the factory. The present invention addresses these problems.

[0430] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and responsibility level in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and responsibility levels from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and responsibility levels; means for generating information on appropriate escalation destinations and notifying the user; means for tracking each team's responsibility level and updating their evaluations; means including a group of sensors for detecting abnormalities in factory equipment; means including an emotion engine for analyzing abnormality data and generating emotion information based on the severity of the abnormality; and means for suggesting an appropriate escalation destination based on the emotion information. This enables quick and accurate escalation responses that take into account the nature and urgency of the abnormality.

[0431] An "employee" is an individual employed to perform a specific function in a factory or company.

[0432] An "area of ​​expertise" is an area in which an employee has particular knowledge, skills, and is particularly knowledgeable.

[0433] "Tag format" is a method of categorizing and organizing information by assigning keywords and labels to make it easier to distinguish.

[0434] A database is an information system that systematically organizes and stores large amounts of information, allowing it to be quickly searched and retrieved as needed.

[0435] "Degree of responsibility" is a numerical representation of the importance and degree of responsibility for a specific area of ​​responsibility or task.

[0436] "Consultation content" refers to issues or concerns that employees or users input into the system as problems or questions.

[0437] "Extraction" refers to the process of extracting specific elements or information from data.

[0438] An "escalation destination" is the next department or team to address to resolve a particular problem or issue.

[0439] An "emotion engine" is a system that analyzes the user's emotions from input information and suggests appropriate responses based on that information.

[0440] "Abnormality" refers to the occurrence of behavior or phenomena in equipment or systems that are outside the normal range.

[0441] A "sensor group" is a collection of multiple sensors that measure the status of equipment and the environment and detect abnormalities.

[0442] A "suggestion" is the act of suggesting appropriate actions or options for a particular situation or task.

[0443] This invention is a system for detecting abnormalities in equipment in a factory and selecting the appropriate escalation destination, and it proposes the most appropriate escalation destination based on emotional information. How the system is implemented will be explained below in detail.

[0444] System Overview

[0445] The system consists of the following main components:

[0446] 1. Sensors

[0447] 2. Server

[0448] 3. Emotion Engine

[0449] 4. Generation AI

[0450] 5. User Interface

[0451] Hardware and Software

[0452] Sensors: Temperature sensors, vibration sensors, sound sensors, etc. installed on equipment. These sensors collect environmental data within the factory in real time.

[0453] Server: A server for data storage and processing. The database stores information on each employee's area of ​​expertise, and each team's scope and level of responsibility.

[0454] Emotion Engine: A software component that performs emotion analysis. It uses text analysis techniques to generate emotion information from anomaly data.

[0455] Generative AI: An artificial intelligence model that selects the optimal escalation point and generates the necessary information.

[0456] User interface: The interface for displaying the escalation notification and accepting user input.

[0457] Data processing and calculation

[0458] 1. Data entry and problem detection

[0459] The sensors collect data and transmit it to a server, including temperature, vibration, and sound data.

[0460] The server analyzes the received data, and if an abnormality is detected, it sends detailed information to the emotion engine.

[0461] 2. Emotion analysis

[0462] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, if the severity of the anomaly is high, the emotion information generated is "urgent."

[0463] 3. Escalation destination selection

[0464] The server uses the emotional information obtained from the emotion engine to search the database for the optimal escalation destination.

[0465] The generation AI selects the appropriate team and experts based on the extracted emotional information, area of ​​expertise tags, and degree of responsibility, and generates detailed escalation information.

[0466] 4. Notification and Response

[0467] The server notifies the user interface of the escalation information created by the generation AI.

[0468] The user reviews the notification and takes the appropriate action based on the information provided.

[0469] Specific examples

[0470] For example, if the operating temperature of a factory device becomes too high and abnormal vibrations are detected, the prompt might look like this:

[0471] "The temperature has reached 80 degrees, the vibration rate has reached 0.5g, and the noise level is 20dB. Does this abnormal operating condition require urgent attention? A quick cool-down or detailed maintenance is required."

[0472] This system detects abnormalities in factory equipment early and selects the escalation destination based on the urgency of the situation. It also promptly notifies users of appropriate countermeasures, which is expected to improve factory productivity and safety.

[0473] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0474] Step 1:

[0475] A group of sensors collects status data (temperature, vibration, sound, etc.) from factory equipment and sends it to a server. Specifically, the sensors monitor environmental data in real time and use an anomaly detection algorithm to detect abnormal data. The server receives this as input, and if it contains abnormal data, passes it on to the next step. The input data are numerical values ​​for temperature, vibration, and sound, and the output data are the results of the abnormality detection.

[0476] Step 2:

[0477] The server analyzes the transmitted data, and if an abnormality is detected, it sends detailed information to the emotion engine. Specifically, an abnormal data analysis module runs within the server and identifies the type and severity of the abnormality (for example, a temperature of 80 degrees or a vibration level of 0.5g). The input data is the details of the abnormal data, and the output data is the abnormality information to be passed to the emotion engine.

[0478] Step 3:

[0479] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, it gives information such as "high urgency" or "immediate response required." The input data is the anomaly information, and the output data is emotion information. The emotion engine uses text analysis technology to generate an emotion score based on pre-set rules.

[0480] Step 4:

[0481] The server searches the database for the most appropriate escalation destination based on the emotional information obtained from the emotion engine. Specifically, it uses a tag matching algorithm to filter relevant teams and experts, and then selects the appropriate person in charge. The input data is emotional information along with tags and responsibility level information, and the output data is information on the selected escalation destination.

[0482] Step 5:

[0483] The generation AI selects the most appropriate escalation contact and generates detailed escalation information. This information is generated in text format, including information on the selected team's area of ​​expertise, contact person, contact information, etc. The input data is tag and sentiment information, and the generated output data is detailed escalation contact information.

[0484] Step 6:

[0485] The server notifies the user interface of the escalation information created by the generation AI. Specifically, it sends the escalation information as an HTTP response and displays it on the user's device. It prompts the user for confirmation and, if necessary, issues an alert using a notification mechanism. The input data is the escalation information, and the output data is the notification displayed to the user.

[0486] Step 7:

[0487] The user reviews the notification and takes the appropriate action based on the information provided, such as contacting a designated escalation point or viewing the steps to resolve the problem. The input data is the displayed escalation information, and the user's actions are the output. This process ensures that equipment anomalies are handled quickly and accurately.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] [Second embodiment]

[0492] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0493] 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.

[0494] 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).

[0495] 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.

[0496] 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.

[0497] 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).

[0498] 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.

[0499] 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.

[0500] 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.

[0501] 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.

[0502] 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.

[0503] 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."

[0504] This invention is an efficient in-house escalation management system that stores each employee's area of ​​expertise in tag format and quantifies and records their degree of responsibility in a database, making it possible to quickly search for the most appropriate escalation destination and notify the user.

[0505] Program processing

[0506] Data Storage

[0507] Server: Store each employee's area of ​​expertise and experience in the employee directory in "tag format." For example, assign tags such as "project management," "data analysis," and "front-end development."

[0508] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "Technology Development" is "High."

[0509] Submit a consultation

[0510] User: Posts a request through the UI. For example, they might write, "I need data analysis for a new project," and set the associated tag as "Data Analysis" and the required level of responsibility as "Medium."

[0511] Terminal: Sends the consultation details entered by the user to the server.

[0512] Escalation selection and notification

[0513] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility levels." For example, the "data analysis" tag and "medium" responsibility level are extracted.

[0514] Generative AI: Searches for suitable teams from the database based on the extracted tags and responsibility levels. It uses a tag matching algorithm to filter out the best teams and selects the team whose responsibility level meets the criteria.

[0515] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be suitable, it generates the team's expertise and contact information.

[0516] Server: Notifies the user of the generated team introduction information. For example, informs the user that "Team B is suitable for data analysis and has a medium level of responsibility."

[0517] Specific examples

[0518] scenario

[0519] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project.

[0520] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0521] 2. Terminal: Sends this information to the server.

[0522] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels.

[0523] 4. Generative AI: Based on the extracted information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0524] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0525] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0526] 7. Terminal: Notify the user of Team B's introduction information.

[0527] 8. User: Check the notified information and contact Team B.

[0528] This system will streamline escalation and information gathering within the company, eliminating the "internal Dragon Quest" phenomenon, and ultimately promoting faster project progress and efficient problem solving.

[0529] The processing flow will be explained below.

[0530] Step 1:

[0531] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[0532] Step 2:

[0533] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[0534] Step 3:

[0535] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[0536] Step 4:

[0537] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[0538] Step 5:

[0539] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." Specifically, it parses the request content and extracts the information such as "new project," "technical issues," and "high" responsibility level.

[0540] Step 6:

[0541] Generative AI: Searches for the most suitable team from the database based on the extracted tags and responsibility levels. Specifically, it uses a tag-matching algorithm to filter relevant teams and selects the team whose responsibility level meets the criteria.

[0542] Step 7:

[0543] Generative AI: Generates introduction information for the selected team, specifically creating written information about the selected team's areas of expertise, responsibilities, and contact information.

[0544] Step 8:

[0545] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[0546] Step 9:

[0547] Terminal: Notify the user of the escalation destination and team introduction information. Specifically, the introduction information is displayed on the UI, and the notification function is used to notify the user as needed.

[0548] Step 10:

[0549] User: Review the information provided and contact the appropriate escalation channel, either by contacting the team directly using the contact information provided or by requesting their help in resolving the issue.

[0550] By following these steps, necessary information can be gathered quickly and the appropriate escalation point can be efficiently selected. This will eliminate the "internal Dragon Quest" phenomenon within the company and make the progress of the project much smoother.

[0551] Example 1

[0552] 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."

[0553] Conventional corporate escalation management systems make it difficult to quickly find the appropriate escalation contact point, making it difficult to resolve problems efficiently. In particular, they lack sufficient information management based on the expertise and experience of each employee or team, making it time-consuming to select the optimal escalation contact point based on the level of responsibility. Furthermore, inappropriate selection of the escalation contact point can delay problem resolution, negatively impacting the overall progress of the project.

[0554] 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.

[0555] In this invention, the server includes a means for storing information in tag format based on each employee's area of ​​expertise and experience, a means for recording each team's scope of responsibility and degree of responsibility in a database as numerical values, and a means for accepting input of consultation content by users and transmitting the content to the server, thereby enabling efficient escalation management.

[0556] "Tag format" is a metadata format that identifies each employee's area of ​​expertise and experience, and is additional information that makes searching and filtering easier.

[0557] "Degree of responsibility" is a numerical representation of the level of responsibility each team or individual has for a specific job or task, and is used to select the destination of escalation.

[0558] A "database" is a system for systematically storing, managing, and searching related data such as employee information, team responsibilities, and levels of responsibility.

[0559] The "contents of consultation" is text information that the user inputs in response to a specific problem or question, and is reference information when selecting an escalation destination.

[0560] "Generated artificial intelligence" refers to algorithms and models that search a database for optimal escalation destinations and generate appropriate referral information.

[0561] A "tag matching algorithm" is a calculation method for detecting matches between multiple tag data and selecting the optimal combination.

[0562] "Notification" is a communication method for informing the user of important information, and includes the results of selection of the escalation destination.

[0563] "Tracking" is the process of tracking each team's responsibility level and recording any fluctuations.

[0564] "Evaluation" is the process of measuring the performance and response capabilities of each team or employee based on data such as tracked responsibility levels.

[0565] The present invention relates to a system for realizing efficient escalation management within a company, and is implemented using the following hardware and software configuration.

[0566] Hardware and Software Configuration

[0567] server

[0568] The server is the central part of the system and performs the following functions:

[0569] Employee directory management: The server stores each employee's area of ​​expertise and experience in the form of tags. For example, tags such as "project management," "data analysis," and "front-end development" are assigned.

[0570] Team information management: The server records each team's scope of responsibility and degree of responsibility in a database as a numerical value. For example, Team A's degree of responsibility for "technology development" is "high."

[0571] Receiving and analyzing consultation content: The server receives the consultation content from the user and extracts the necessary tags and responsibility levels.

[0572] Escalation Selection: The server uses a generative AI model to search the database for the appropriate team.

[0573] Notification function: The server generates appropriate escalation information and notifies the user.

[0574] Terminal

[0575] Terminals provide the interface through which users access and operate the system:

[0576] Input of consultation content: The user inputs the consultation content through the device UI. For example, the user inputs "Data analysis is required for a new project," sets the related tag as "Data analysis," and sets the required responsibility level as "Medium."

[0577] Data transmission: The terminal transmits the consultation details entered by the user to the server.

[0578] User

[0579] The user does the following:

[0580] Posting a consultation: A user posts a consultation regarding a specific problem or question.

[0581] Receiving the result: The user receives the notification from the server and checks the contents.

[0582] Contacting the escalation destination: The user contacts the notified escalation destination.

[0583] Data processing and calculation

[0584] 1. Data storage: First, the server retrieves each employee's area of ​​expertise from the employee directory and stores it in the database in tag format. It also records the scope of each team's responsibilities and the degree of responsibility as a number.

[0585] 2. Posting and sending consultation details: The user inputs the consultation details through the device's UI, and the device sends the information to the server.

[0586] 3. Analysis of consultation content: The server analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[0587] 4. Selection of escalation destination: The generative AI model searches the database for the optimal escalation destination based on the extracted tags and degree of responsibility.

[0588] 5. Notification: The server notifies the user of the information about the created escalation destination.

[0589] Specific examples

[0590] For example, if a user in department A is looking for an escalation point to "resolve technical issues related to a new project":

[0591] 1. The user enters the consultation content in the UI, selects the tags "Technical Issue" and "New Project," and sets the required level of responsibility to "High."

[0592] 2. The terminal sends the input information to the server.

[0593] 3. The server analyzes the received information and extracts the necessary tags and responsibility levels.

[0594] 4. The generative AI model searches the database for the optimal team. In this case, it determines that Team B is the best team because it can handle the technical challenges.

[0595] 5. The server notifies the user of Team B's introduction information.

[0596] Prompt Sentence Examples

[0597] "A user with a technical issue related to a new project is looking for an appropriate escalation point. The user posts the consultation as 'Solving the technical issue for the new project,' selects 'Technical issue' and 'New project' as tags, and sets the required level of responsibility as 'High.' Please analyze this information, search the database for the most suitable team, and notify the user of the introduction information."

[0598] The above is an embodiment of the invention.

[0599] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] Stores employee specialties in tag format

[0602] Server: Extracts each employee's area of ​​expertise and experience from the employee directory and formats them into "tag format." For example, it generates tags such as "project management," "data analysis," and "front-end development."

[0603] Input: Employee directory data

[0604] Data processing and data calculation: An extraction algorithm is used to obtain area of ​​expertise information from the employee directory, and a tagging algorithm is used to generate tags.

[0605] Output: Tagged domain data

[0606] What happens: The server inserts new records into the "expertise" table of the database, adding each employee's ID and corresponding tag.

[0607] Step 2:

[0608] Record each team's scope of responsibility and level of responsibility

[0609] Server: Determines the scope of each team's responsibilities and their degree of responsibility, quantifies them, and records them in the database. For example, Team A's responsibility level for "Technology Development" is "High."

[0610] Input: Team Roles and Responsibilities

[0611] Data processing and calculation: The scope of responsibility and degree of responsibility are quantified and stored in the database.

[0612] Output: Updated database

[0613] Specific operation: The server creates a "team information" table in the database and adds each team's ID, area of ​​responsibility, and degree of responsibility.

[0614] Step 3:

[0615] Users post their inquiries

[0616] User: Enter the details of the consultation using the dedicated UI. Write specific details such as "Data analysis is required for a new project," and set the related tag "Data Analysis" and the required level of responsibility as "Medium."

[0617] Input: consultation content, tags, degree of responsibility

[0618] Output: User input data

[0619] Specific operation: The user enters the necessary information into the input form and clicks the "Submit" button.

[0620] Step 4:

[0621] The entered data is sent to the server

[0622] Terminal: The consultation details entered by the user are sent to the server as an HTTP request. At this time, the consultation details, tags, and responsibility level are sent in JSON format.

[0623] Input: User-entered data

[0624] Data processing and data calculation: Convert user input data into JSON format and send it to the server.

[0625] Output: JSON format data

[0626] Specific operation: A POST request is generated from the browser to the server, and the content is included in the request body.

[0627] Step 5:

[0628] Analyze received consultation content

[0629] Server: Parses the received JSON data, extracts the consultation content, tags, and responsibility level, and validates the content for accuracy.

[0630] Input: JSON format data

[0631] Data processing and data calculation: JSON parsing and data validation.

[0632] Output: Extracted tags and responsibility counts

[0633] Specific behavior: Uses a JSON parser to store data in variables and checks for required fields.

[0634] Step 6:

[0635] Find the right team

[0636] Generative AI: Search for suitable teams in the database based on the extracted tag "Data Analysis" and the responsibility level "Medium". Filter candidate teams using a tag matching algorithm.

[0637] Input: Extracted tags and responsibility levels

[0638] Data processing and data calculation: Issue an SQL query to extract teams that match the criteria from the database.

[0639] Output: Optimal team

[0640] What it does: Runs an SQL query to search the database and selects teams that match the criteria.

[0641] Step 7:

[0642] Generate introduction information for selected teams

[0643] Generative AI: Generates introductory information for the selected team—for example, Team B's areas of expertise and contact information.

[0644] Input: Best team information

[0645] Data processing and data calculation: Run a script to automatically generate an introduction.

[0646] Output: Generated referral information

[0647] Specific operation: Run a script to generate an introduction based on the acquired team information.

[0648] Step 8:

[0649] Notify user

[0650] Server: Prepares the generated team introduction information for notification to the user. For example, it formats the notification content to say, "Team B is suitable for data analysis and has medium responsibility."

[0651] Input: Generated referral information

[0652] Data processing and data calculation: The notification content is inserted into an HTML template to create a response for display in the user's UI.

[0653] Output: User notification

[0654] Specific operation: The notification content is formatted in HTML and a response is sent to the user's device.

[0655] The above are the processing steps of the program for this system.

[0656] (Application example 1)

[0657] 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."

[0658] Conventional escalation management systems have made it difficult to quickly select and respond to problems and technical issues that arise within a company. As a result, it often takes time to resolve problems, resulting in a decline in production efficiency. Furthermore, particularly with factory equipment, a delayed response to an abnormality can lead to major losses or accidents. To solve these issues, an escalation management system needs the ability to select and notify the most appropriate engineer in real time.

[0659] 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.

[0660] In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and degree of responsibility in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and degrees of responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and degrees of responsibility; means for generating information on the appropriate escalation destination and notifying the user; means for posting a problem in cooperation with a robot that detects abnormalities in factory equipment; means for analyzing the area of ​​expertise and degree of responsibility required for the problem and searching for an appropriate engineer; means for sending a notification to the engineer based on the search results; and means for tracking each team's degree of responsibility and updating their evaluation. This makes it possible to select the optimal engineer in real time to respond quickly to abnormalities and technical issues in factory equipment.

[0661] An "area of ​​expertise" is a field or range of fields in which an employee with specific skills or knowledge excels.

[0662] "Experience" refers to the accumulation of knowledge and skills that an employee has gained from actual work or projects they have undertaken in the past.

[0663] "Tag format" is a method of assigning specific keywords or categories to each piece of information, making it easier to classify and search for information.

[0664] "Degree of responsibility" is a numerical representation of the degree of responsibility each team or employee has for a specific task or project.

[0665] A "database" is an information system that stores data based on a certain structure and enables efficient searching and processing.

[0666] A "user" is an individual or department that uses the system to input the details of a consultation.

[0667] "Consultation content" refers to detailed information about a problem or issue that a user enters through the system.

[0668] "Extraction" refers to the process of selecting necessary elements and keywords from the provided information.

[0669] An "optimal escalation point" is a team or employee selected to best respond to a particular issue or challenge.

[0670] "Generation" is the process of creating new information or data using algorithms or programs.

[0671] "Notification" refers to the act of sending information from the system to users or technicians, or that information.

[0672] "Factory equipment" refers to all machines and devices used in production lines and manufacturing processes.

[0673] An "abnormality" is a phenomenon or event that deviates from the standard operating conditions of factory equipment.

[0674] A "robot" is a mechanical device that performs autonomous or controlled operations within a factory facility.

[0675] An "engineer" is a professional who has specific techniques and skills and who solves problems and maintains equipment.

[0676] "Tracking" refers to the process or means of tracking and recording specific data or circumstances.

[0677] Evaluation is the process of quantifying or verbalizing the behavior and achievements of a team or employee based on specific criteria.

[0678] This invention is a system for efficient escalation management that utilizes tags and responsibility levels based on employees' areas of expertise and experience. The system is composed of the following means.

[0679] Data storage method

[0680] The server stores each employee's area of ​​expertise and experience in "tag format." For example, tags such as "mechanical engineering," "electrical engineering," and "program control" are assigned. Furthermore, the scope of each team's responsibilities and degree of responsibility are recorded as numerical values ​​in the database. For example, Team A's level of responsibility for "mechanical problems" is set to "high."

[0681] Detecting anomalies in factory equipment and reporting problems

[0682] The robot detects abnormalities within factory equipment, such as abnormal vibrations or control errors. The detected abnormalities are sent to the server, along with detailed information about the abnormality (for example, "abnormal vibration detected, restart failed, cause unknown").

[0683] Analysis of consultation content and selection of escalation destination

[0684] The server analyzes the received consultation content. In this analysis, it extracts the necessary "tags" and "responsibility levels." For example, the "mechanical problem" tag and "high" responsibility level are extracted.

[0685] The generative AI model is then used to search the database for the most suitable technician based on the extracted tags and responsibilities, using a tag-matching algorithm. For example, Technician B is determined to be the best fit, and his / her expertise and contact information are generated.

[0686] Notification method for technicians

[0687] The server notifies the robot of the generated engineer information. The robot then notifies the engineer of the received information in real time. For example, it may send a notification saying, "We will ask Engineer B to identify the cause of the abnormal vibration and repair it."

[0688] Evaluation and Update Methods

[0689] The server tracks the responsibility rating of each team and engineer and updates the rating. For example, if Engineer B resolves the issue quickly and effectively, his / her responsibility rating will be updated from "medium" to "high."

[0690] Specific examples

[0691] Consider a scenario where abnormal vibrations are detected in a factory.

[0692] 1. The robot sends a message to the server saying, "Abnormal vibration detected, restart failed, cause unknown."

[0693] 2. The server analyzes the problem content and extracts the "mechanical problem" tag and the "high" responsibility score.

[0694] 3. The generative AI model selects Technician B from the database as the best person to escalate the issue based on the tag and degree of responsibility.

[0695] 4. The server notifies the robot of the generated engineer information, and the robot notifies Engineer B in real time.

[0696] 5. Engineer B solves the problem, the result is recorded on the server, and the responsibility score is updated.

[0697] Example prompt for a generative AI model:

[0698] "Select the most suitable engineer based on the employee's area of ​​expertise and level of responsibility, and generate engineer information that matches the following tags and levels of responsibility: Tag: ['Mechanical Problem'] Level of Responsibility: 'High'"

[0699] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0700] Step 1:

[0701] The server stores each employee's area of ​​expertise and experience in the form of tags. To do this, it receives employee profile data and stores their area of ​​expertise (e.g., "mechanical engineering," "electrical engineering," etc.) and experience level (e.g., "entry," "intermediate," "advanced") as tags in the database. The input is the employee profile data, and the output is the updated database record.

[0702] Step 2:

[0703] The server records each team's scope of responsibility and degree of responsibility as a numerical value in the database. This allows each team's area of ​​expertise and its degree of responsibility (e.g., "high," "medium," or "low") to be stored as structured data. The input is the information on each team's scope of responsibility and degree of responsibility, and the output is the numerical data stored in the database.

[0704] Step 3:

[0705] The robot detects anomalies in factory equipment and sends details to a server. For example, it analyzes sensor data to identify anomalies such as "abnormal vibration detected, restart failed, cause unknown" and sends that information to the server. The input is the sensor data and detailed information about the anomaly, and the output is an anomaly report sent to the server.

[0706] Step 4:

[0707] The server analyzes the received anomaly report and extracts the necessary tags and responsibility levels. This analysis uses natural language processing technology to derive, for example, a "mechanical problem" tag and a "high" responsibility level. The input is the anomaly report, and the output is the extracted tags and responsibility levels.

[0708] Step 5:

[0709] The server uses a generative AI model to search the database for the most suitable engineer based on the extracted tags and responsibility levels. This process uses a tag-matching algorithm to select the engineer who best matches, for example, the "mechanical engineering" tag and "high" responsibility level. The input is the tag and responsibility level, and the output is the information on the most suitable engineer.

[0710] Step 6:

[0711] The server notifies the robot of the generated technician information, which includes the technician's specialty and contact information. The input is the information of the best technician, and the output is the technician notification sent to the robot.

[0712] Step 7:

[0713] The robot sends a real-time notification to the appropriate technician based on the received technician information. For example, it may send a message saying, "We will ask technician B to identify the cause of the abnormal vibration and repair it." The input is the technician notification, and the output is the notification message to the technician.

[0714] Step 8:

[0715] The engineer solves the problem and reports the results to the server, which receives the report and updates the engineer's responsibility score. The input is the problem-solving report, and the output is a database record of the updated responsibility score.

[0716] 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.

[0717] This invention is a system that combines an emotion engine with an efficient in-house escalation management system, which recognizes the user's emotions and suggests the most appropriate escalation destination, enabling efficient and empathetic responses.

[0718] Program processing

[0719] Data Storage

[0720] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[0721] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[0722] Consultation posting and sentiment analysis

[0723] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[0724] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[0725] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[0726] Escalation selection and notification

[0727] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level," while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issues," "high" responsibility level, and "urgency."

[0728] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility levels, and emotional information. It uses a tag-matching algorithm to filter relevant teams and selects the team that meets the responsibility level criteria and takes emotional information into account.

[0729] Generation AI: Generates introductory information for the selected team. For example, if Team B is determined to be suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[0730] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[0731] Response and evaluation

[0732] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[0733] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[0734] Server: Continuously tracks each team's responsibility rating and updates the rating based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, the server updates their responsibility rating and emotional response rating.

[0735] Specific examples

[0736] scenario

[0737] A user in department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is highly stressed and needs a solution quickly.

[0738] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0739] 2. Terminal: Sends this information to the server.

[0740] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user feels a high level of urgency.

[0741] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0742] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0743] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0744] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[0745] 8. User: Check the notified information and contact Team B urgently.

[0746] This satisfying collaboration allows necessary information to be gathered quickly and the appropriate escalation point to be selected efficiently. This eliminates the "internal Dragon Quest" phenomenon within the company and makes project progress much smoother. Furthermore, by taking the user's feelings into consideration, a more empathetic and prompt response is possible.

[0747] The processing flow will be explained below.

[0748] Step 1:

[0749] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, tags such as "data analysis," "project management," and "front-end development" are extracted from each employee's resume and project experience and stored in the database.

[0750] Step 2:

[0751] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "technology development" is registered as "high," and Team B's level of responsibility for "market analysis" is registered as "medium."

[0752] Step 3:

[0753] User: Enters and posts the content of the consultation through the UI. For example, to discuss technical issues related to a new project, the user selects the tags "New Project" and "Technical Issues" and sets the required level of responsibility as "High."

[0754] Step 4:

[0755] Terminal: Sends the consultation details entered by the user to the server. Specifically, the entered data is sent to the server as an HTTP request from the form.

[0756] Step 5:

[0757] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." For example, it parses and extracts information on "new projects," "technical issues," and "high" responsibility level.

[0758] Step 6:

[0759] Emotion engine: Analyzes the text of the consultation content and determines the user's emotions. Specifically, it uses natural language processing technology to detect whether the user is feeling urgency or stress. For example, it extracts the emotion "very urgent" from the consultation content.

[0760] Step 7:

[0761] Generative AI: Searches the database for the most appropriate escalation destination based on required tags, responsibility, and sentiment information. It uses a tag-matching algorithm to filter relevant teams, and also takes sentiment information into account to select teams with a suitable responsibility level.

[0762] Step 8:

[0763] Generation AI: Generates introductory information about the selected team. For example, it creates detailed information in text format, such as "Team B can handle technical issues and is suitable for emergency response."

[0764] Step 9:

[0765] Server: Stores the generated team introduction information in a database and returns it to the terminal. The generated introduction information is added to the database and sent to the terminal as an HTTP response.

[0766] Step 10:

[0767] Device: Notify the user of the escalation destination and team introduction information. Specifically, display on the UI the message "Team B is suitable, and the contact information for the person in charge is as follows," and notify by push notification or email as necessary.

[0768] Step 11:

[0769] User: Review the information provided and contact the appropriate escalation point. Specifically, use the provided contact information to contact Team B directly or request their cooperation in resolving the issue.

[0770] Step 12:

[0771] Server: Tracks each team's responsibility rating and updates it based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, its responsibility rating and emotional response rating will be updated.

[0772] By performing these steps sequentially, the optimal escalation destination is selected taking into account the user's feelings, enabling efficient and empathetic problem solving.

[0773] Example 2

[0774] 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."

[0775] Conventional escalation management systems simply determine the escalation destination based on the work content and the specialist area of ​​the person in charge, without considering the user's feelings or urgency, making it difficult to provide a quick and empathetic response. Furthermore, if the appropriate person in charge is not selected properly, problem resolution is delayed and work efficiency decreases.

[0776] 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 storing information in tag format based on each employee's skill area and work experience; means for recording each team's scope of work and responsibility in a database as numerical values; means for accepting input of consultation content by a user; means for transmitting the input consultation content to the server; means for analyzing the user's emotions from the consultation content; means for extracting necessary tags and responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags, responsibility, and emotion information; means for generating information on appropriate escalation destinations and notifying the user; and means for tracking each team's responsibility and updating the evaluation. This enables quick and empathetic selection of an escalation destination that also takes into account the user's emotions and urgency.

[0777] 1. "Skill areas of each employee"

[0778] Each employee's skill area refers to the field or area in which the employee has expertise or experience, such as data analysis, project management, or front-end development.

[0779] 2. "Work experience"

[0780] Work experience refers to the experience and achievements of an employee in the work or projects they have worked on in the past, which reveals their skill set and expertise.

[0781] 3. "Tag Format"

[0782] Tagging refers to a data format that categorizes information with specific keywords or labels to facilitate searching and filtering. It is used to represent each employee's skill areas and work experience.

[0783] 4. "Scope of Work"

[0784] The scope of work refers to the area of ​​work or project that each team is responsible for, specifically, the team's work content, such as technology development or market analysis.

[0785] 5. “Responsibility”

[0786] Responsibility is a numerical representation of how much responsibility each team or employee has for a particular task or issue, and can be high, medium, or low.

[0787] 6. "Consultation Content"

[0788] Consultation content refers to specific problems or issues that users post through the system for which they seek advice or support, including technical issues related to new projects.

[0789] 7. “Emotional Analysis”

[0790] Sentiment analysis refers to the process of analyzing a user's emotional state (e.g., stress, urgency) from text data using natural language processing techniques.

[0791] 8. "Best escalation point"

[0792] The optimal escalation destination is the team or employee that is determined to be able to respond most appropriately based on the content of the consultation and the results of sentiment analysis.

[0793] 9. "Generate Information"

[0794] Information generation refers to the process of creating specific text or data formats to notify users based on the extracted data.

[0795] 10. "Tracking"

[0796] Tracking is the process of continuously monitoring specific data or metrics, recording and evaluating them as needed, to continually assess each team's accountability.

[0797] 11. "Update your rating"

[0798] Refreshing ratings refers to the process of keeping each team or employee's responsibilities and performance ratings up to date based on the data and feedback obtained through tracking.

[0799] This invention is an efficient in-company escalation management system that is implemented in a form that combines an emotion engine. This enables efficient and empathetic responses by recognizing the user's emotions and suggesting the most appropriate escalation destination. The specific configuration and operation are described below.

[0800] 1. Data Storage

[0801] Server: Stores information in tag format based on each employee's skill area and work experience. Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[0802] Server: Records the scope of work and level of responsibility of each team in a database as a number. For example, each team can register the level of responsibility for the field or issue they are responsible for (e.g., "technology development" or "market analysis") as a number such as "high," "medium," or "low."

[0803] 2. Posting of consultations and sentiment analysis

[0804] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, select tags such as "new project" or "technical issues" and set the required level of responsibility as "high."

[0805] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[0806] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[0807] 3. Escalation Selection and Notification

[0808] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility level, while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issue," "high" responsibility level, and "urgency."

[0809] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility, and emotion information. It uses a tag matching algorithm to filter relevant teams and selects the team that meets the responsibility criteria and takes emotion information into account.

[0810] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be the most suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[0811] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[0812] 4. Response and Evaluation

[0813] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[0814] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[0815] Server: Continuously tracks each team's responsibility and updates their evaluation based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, it updates their responsibility and emotional response.

[0816] Specific examples

[0817] scenario

[0818] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is feeling very stressed and needs a solution quickly.

[0819] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0820] 2. Terminal: Sends this information to the server.

[0821] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user has a high level of urgency.

[0822] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0823] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0824] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0825] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[0826] 8. User: Check the notified information and contact Team B urgently.

[0827] In this way, necessary information is gathered quickly and the appropriate escalation point is efficiently selected. This eliminates the "internal Dragon Quest" phenomenon within the company and makes the progress of projects smoother. Also, by taking the user's feelings into consideration, more empathetic and prompt responses are possible.

[0828] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0829] Step 1:

[0830] Server: Stores information in tag form based on each employee's skill area and work experience.

[0831] Specific operation:

[0832] Input: Resume and project experience data for each employee.

[0833] Data processing: Extract tags such as "data analysis," "project management," and "front-end development" from each employee's resume and project experience.

[0834] Output: Save the extracted tags to a database.

[0835] Step 2:

[0836] Server: Record each team's scope of work and level of responsibility in a database.

[0837] Specific operation:

[0838] Input: Data on each team's work content and scope of responsibilities.

[0839] Data processing: Classify the level of responsibility for each team's scope of work (such as "technology development" or "market analysis") into a numerical value of "high," "medium," or "low."

[0840] Output: Record the classified responsibility in a database.

[0841] Step 3:

[0842] User: Enters the consultation details through the UI and posts.

[0843] Specific operation:

[0844] Input: The consultation topic, tags (e.g., "New Project" or "Technical Issue"), and responsibility level (e.g., "High") that the user enters into the UI form.

[0845] Data processing: The input consultation content is classified in tag format and the required level of responsibility is confirmed.

[0846] Output: The submitted consultation content is sent to the server via the form.

[0847] Step 4:

[0848] Terminal: Sends the entered consultation details to the server.

[0849] Specific operation:

[0850] Input: Consultation content data entered by the user.

[0851] Data processing: Convert the data entered in the form into an HTTP request.

[0852] Output: Forwarded to the server as an HTTP request.

[0853] Step 5:

[0854] Emotion engine: Analyzes the user's emotions from the content of the consultation.

[0855] Specific operation:

[0856] Input: Text data of the consultation content sent from the server.

[0857] Data processing: Using text analysis techniques, we analyze emotions such as stress and urgency felt by the user.

[0858] Output: Generates sentiment analysis results (e.g., "urgent" or "stressed").

[0859] Step 6:

[0860] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[0861] Specific operation:

[0862] Input: Consultation details and emotion analysis results sent from the device.

[0863] Data processing: Extract tags such as "new project," "technical issue," and "high" responsibility level, as well as emotional information, from the consultation content.

[0864] Output: The extracted information is sent to a generative AI model.

[0865] Step 7:

[0866] Generative AI: Searches for the appropriate team from the database based on extracted tags, responsibilities, and sentiment information, and generates introduction information.

[0867] Specific operation:

[0868] Input: Tags, responsibility, and emotion information sent from the server.

[0869] Data processing: Using a tag-matching algorithm, we filter relevant teams from the database and select the most suitable team based on responsibility and sentiment information.

[0870] Output: Generates introductory information about the selected team (team name, area of ​​expertise, area of ​​responsibility, contact information).

[0871] Step 8:

[0872] Server: Stores the generated team introduction information in a database and returns it to the terminal.

[0873] Specific operation:

[0874] Input: Team introduction information sent from the generation AI.

[0875] Data processing: Store the information in a database and convert it into an HTTP response format.

[0876] Output: Sends a reply to the terminal.

[0877] Step 9:

[0878] Terminal: Notifies user of escalation and team introduction information.

[0879] Specific operation:

[0880] Input: Team introduction information sent from the server.

[0881] Data processing: Formatting data in a format that can be displayed on the UI.

[0882] Output: The referral information is notified to the user.

[0883] Step 10:

[0884] User: Review the information provided and contact the appropriate escalation point.

[0885] Specific operation:

[0886] Input: Contact information for escalation from the terminal.

[0887] Data processing: We will contact the team directly using the contact information you provide.

[0888] Output: A query is made.

[0889] Step 11:

[0890] Server: Continuously track each team's accountability and update the ratings.

[0891] Specific operation:

[0892] Input: Feedback data from each team and the analysis results of the emotion engine.

[0893] Data processing: Based on feedback data and sentiment information, update each team's responsibility and performance evaluation.

[0894] Output: Responsibility and rating are updated in the database.

[0895] (Application example 2)

[0896] 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."

[0897] In conventional factories, there is a need for a system that can detect equipment anomalies early and efficiently notify the appropriate escalation contact point. It is particularly important to respond quickly and accurately to urgent problems. However, typical escalation management systems often do not take emotional information into account and instead rely solely on mechanical responses. This results in delayed responses after an anomaly is detected, leading to problems such as reduced productivity throughout the factory. The present invention addresses these problems.

[0898] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and responsibility level in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and responsibility levels from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and responsibility levels; means for generating information on appropriate escalation destinations and notifying the user; means for tracking each team's responsibility level and updating their evaluations; means including a group of sensors for detecting abnormalities in factory equipment; means including an emotion engine for analyzing abnormality data and generating emotion information based on the severity of the abnormality; and means for suggesting an appropriate escalation destination based on the emotion information. This enables quick and accurate escalation responses that take into account the nature and urgency of the abnormality.

[0899] An "employee" is an individual employed to perform a specific function in a factory or company.

[0900] An "area of ​​expertise" is an area in which an employee has particular knowledge, skills, and is particularly knowledgeable.

[0901] "Tag format" is a method of categorizing and organizing information by assigning keywords and labels to make it easier to distinguish.

[0902] A database is an information system that systematically organizes and stores large amounts of information, allowing it to be quickly searched and retrieved as needed.

[0903] "Degree of responsibility" is a numerical representation of the importance and degree of responsibility for a specific area of ​​responsibility or task.

[0904] "Consultation content" refers to issues or concerns that employees or users input into the system as problems or questions.

[0905] "Extraction" refers to the process of extracting specific elements or information from data.

[0906] An "escalation destination" is the next department or team to address to resolve a particular problem or issue.

[0907] An "emotion engine" is a system that analyzes the user's emotions from input information and suggests appropriate responses based on that information.

[0908] "Abnormality" refers to the occurrence of behavior or phenomena in equipment or systems that are outside the normal range.

[0909] A "sensor group" is a collection of multiple sensors that measure the status of equipment and the environment and detect abnormalities.

[0910] A "suggestion" is the act of suggesting appropriate actions or options for a particular situation or task.

[0911] This invention is a system for detecting abnormalities in equipment in a factory and selecting the appropriate escalation destination, and it proposes the most appropriate escalation destination based on emotional information. How the system is implemented will be explained below in detail.

[0912] System Overview

[0913] The system consists of the following main components:

[0914] 1. Sensors

[0915] 2. Server

[0916] 3. Emotion Engine

[0917] 4. Generation AI

[0918] 5. User Interface

[0919] Hardware and Software

[0920] Sensors: Temperature sensors, vibration sensors, sound sensors, etc. installed on equipment. These sensors collect environmental data within the factory in real time.

[0921] Server: A server for data storage and processing. The database stores information on each employee's area of ​​expertise, and each team's scope and level of responsibility.

[0922] Emotion Engine: A software component that performs emotion analysis. It uses text analysis techniques to generate emotion information from anomaly data.

[0923] Generative AI: An artificial intelligence model that selects the optimal escalation point and generates the necessary information.

[0924] User interface: The interface for displaying the escalation notification and accepting user input.

[0925] Data processing and calculation

[0926] 1. Data entry and problem detection

[0927] The sensors collect data and transmit it to a server, including temperature, vibration, and sound data.

[0928] The server analyzes the received data, and if an abnormality is detected, it sends detailed information to the emotion engine.

[0929] 2. Emotion analysis

[0930] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, if the severity of the anomaly is high, the emotion information generated is "urgent."

[0931] 3. Escalation destination selection

[0932] The server uses the emotional information obtained from the emotion engine to search the database for the optimal escalation destination.

[0933] The generation AI selects the appropriate team and experts based on the extracted emotional information, area of ​​expertise tags, and degree of responsibility, and generates detailed escalation information.

[0934] 4. Notification and Response

[0935] The server notifies the user interface of the escalation information created by the generation AI.

[0936] The user reviews the notification and takes the appropriate action based on the information provided.

[0937] Specific examples

[0938] For example, if the operating temperature of a factory device becomes too high and abnormal vibrations are detected, the prompt might look like this:

[0939] "The temperature has reached 80 degrees, the vibration rate has reached 0.5g, and the noise level is 20dB. Does this abnormal operating condition require urgent attention? A quick cool-down or detailed maintenance is required."

[0940] This system detects abnormalities in factory equipment early and selects the escalation destination based on the urgency of the situation. It also promptly notifies users of appropriate countermeasures, which is expected to improve factory productivity and safety.

[0941] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0942] Step 1:

[0943] A group of sensors collects status data (temperature, vibration, sound, etc.) from factory equipment and sends it to a server. Specifically, the sensors monitor environmental data in real time and use an anomaly detection algorithm to detect abnormal data. The server receives this as input, and if it contains abnormal data, passes it on to the next step. The input data are numerical values ​​for temperature, vibration, and sound, and the output data are the results of the abnormality detection.

[0944] Step 2:

[0945] The server analyzes the transmitted data, and if an abnormality is detected, it sends detailed information to the emotion engine. Specifically, an abnormal data analysis module runs within the server and identifies the type and severity of the abnormality (for example, a temperature of 80 degrees or a vibration level of 0.5g). The input data is the details of the abnormal data, and the output data is the abnormality information to be passed to the emotion engine.

[0946] Step 3:

[0947] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, it gives information such as "high urgency" or "immediate response required." The input data is the anomaly information, and the output data is emotion information. The emotion engine uses text analysis technology to generate an emotion score based on pre-set rules.

[0948] Step 4:

[0949] The server searches the database for the most appropriate escalation destination based on the emotional information obtained from the emotion engine. Specifically, it uses a tag matching algorithm to filter relevant teams and experts, and then selects the appropriate person in charge. The input data is emotional information along with tags and responsibility level information, and the output data is information on the selected escalation destination.

[0950] Step 5:

[0951] The generation AI selects the most appropriate escalation contact and generates detailed escalation information. This information is generated in text format, including information on the selected team's area of ​​expertise, contact person, contact information, etc. The input data is tag and sentiment information, and the generated output data is detailed escalation contact information.

[0952] Step 6:

[0953] The server notifies the user interface of the escalation information created by the generation AI. Specifically, it sends the escalation information as an HTTP response and displays it on the user's device. It prompts the user for confirmation and, if necessary, issues an alert using a notification mechanism. The input data is the escalation information, and the output data is the notification displayed to the user.

[0954] Step 7:

[0955] The user reviews the notification and takes the appropriate action based on the information provided, such as contacting a designated escalation point or viewing the steps to resolve the problem. The input data is the displayed escalation information, and the user's actions are the output. This process ensures that equipment anomalies are handled quickly and accurately.

[0956] 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.

[0957] 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.

[0958] 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.

[0959] [Third embodiment]

[0960] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0961] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0962] 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).

[0963] 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.

[0964] 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.

[0965] 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).

[0966] 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.

[0967] 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.

[0968] 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.

[0969] 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.

[0970] 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.

[0971] 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."

[0972] This invention is an efficient in-house escalation management system that stores each employee's area of ​​expertise in tag format and quantifies and records their degree of responsibility in a database, making it possible to quickly search for the most appropriate escalation destination and notify the user.

[0973] Program processing

[0974] Data Storage

[0975] Server: Store each employee's area of ​​expertise and experience in the employee directory in "tag format." For example, assign tags such as "project management," "data analysis," and "front-end development."

[0976] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "Technology Development" is "High."

[0977] Submit a consultation

[0978] User: Posts a request through the UI. For example, they might write, "I need data analysis for a new project," and set the associated tag as "Data Analysis" and the required level of responsibility as "Medium."

[0979] Terminal: Sends the consultation details entered by the user to the server.

[0980] Escalation selection and notification

[0981] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility levels." For example, the "data analysis" tag and "medium" responsibility level are extracted.

[0982] Generative AI: Searches for suitable teams from the database based on the extracted tags and responsibility levels. It uses a tag matching algorithm to filter out the best teams and selects the team whose responsibility level meets the criteria.

[0983] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be suitable, it generates the team's expertise and contact information.

[0984] Server: Notifies the user of the generated team introduction information. For example, informs the user that "Team B is suitable for data analysis and has a medium level of responsibility."

[0985] Specific examples

[0986] scenario

[0987] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project.

[0988] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[0989] 2. Terminal: Sends this information to the server.

[0990] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels.

[0991] 4. Generative AI: Based on the extracted information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[0992] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[0993] 6. Server: Stores the generated information in a database and returns it to the terminal.

[0994] 7. Terminal: Notify the user of Team B's introduction information.

[0995] 8. User: Check the notified information and contact Team B.

[0996] This system will streamline escalation and information gathering within the company, eliminating the "internal Dragon Quest" phenomenon, and ultimately promoting faster project progress and efficient problem solving.

[0997] The processing flow will be explained below.

[0998] Step 1:

[0999] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[1000] Step 2:

[1001] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[1002] Step 3:

[1003] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[1004] Step 4:

[1005] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[1006] Step 5:

[1007] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." Specifically, it parses the request content and extracts the information such as "new project," "technical issues," and "high" responsibility level.

[1008] Step 6:

[1009] Generative AI: Searches for the most suitable team from the database based on the extracted tags and responsibility levels. Specifically, it uses a tag-matching algorithm to filter relevant teams and selects the team whose responsibility level meets the criteria.

[1010] Step 7:

[1011] Generative AI: Generates introduction information for the selected team, specifically creating written information about the selected team's areas of expertise, responsibilities, and contact information.

[1012] Step 8:

[1013] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[1014] Step 9:

[1015] Terminal: Notify the user of the escalation destination and team introduction information. Specifically, the introduction information is displayed on the UI, and the notification function is used to notify the user as needed.

[1016] Step 10:

[1017] User: Review the information provided and contact the appropriate escalation channel, either by contacting the team directly using the contact information provided or by requesting their help in resolving the issue.

[1018] By following these steps, necessary information can be gathered quickly and the appropriate escalation point can be efficiently selected. This will eliminate the "internal Dragon Quest" phenomenon within the company and make the progress of the project much smoother.

[1019] Example 1

[1020] 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."

[1021] Conventional corporate escalation management systems make it difficult to quickly find the appropriate escalation contact point, making it difficult to resolve problems efficiently. In particular, they lack sufficient information management based on the expertise and experience of each employee or team, making it time-consuming to select the optimal escalation contact point based on the level of responsibility. Furthermore, inappropriate selection of the escalation contact point can delay problem resolution, negatively impacting the overall progress of the project.

[1022] 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.

[1023] In this invention, the server includes a means for storing information in tag format based on each employee's area of ​​expertise and experience, a means for recording each team's scope of responsibility and degree of responsibility in a database as numerical values, and a means for accepting input of consultation content by users and transmitting the content to the server, thereby enabling efficient escalation management.

[1024] "Tag format" is a metadata format that identifies each employee's area of ​​expertise and experience, and is additional information that makes searching and filtering easier.

[1025] "Degree of responsibility" is a numerical representation of the level of responsibility each team or individual has for a specific job or task, and is used to select the destination of escalation.

[1026] A "database" is a system for systematically storing, managing, and searching related data such as employee information, team responsibilities, and levels of responsibility.

[1027] The "contents of consultation" is text information that the user inputs in response to a specific problem or question, and is reference information when selecting an escalation destination.

[1028] "Generated artificial intelligence" refers to algorithms and models that search a database for optimal escalation destinations and generate appropriate referral information.

[1029] A "tag matching algorithm" is a calculation method for detecting matches between multiple tag data and selecting the optimal combination.

[1030] "Notification" is a communication method for informing the user of important information, and includes the results of selection of the escalation destination.

[1031] "Tracking" is the process of tracking each team's responsibility level and recording any fluctuations.

[1032] "Evaluation" is the process of measuring the performance and response capabilities of each team or employee based on data such as tracked responsibility levels.

[1033] The present invention relates to a system for realizing efficient escalation management within a company, and is implemented using the following hardware and software configuration.

[1034] Hardware and Software Configuration

[1035] server

[1036] The server is the central part of the system and performs the following functions:

[1037] Employee directory management: The server stores each employee's area of ​​expertise and experience in the form of tags. For example, tags such as "project management," "data analysis," and "front-end development" are assigned.

[1038] Team information management: The server records each team's scope of responsibility and degree of responsibility in a database as a numerical value. For example, Team A's degree of responsibility for "technology development" is "high."

[1039] Receiving and analyzing consultation content: The server receives the consultation content from the user and extracts the necessary tags and responsibility levels.

[1040] Escalation Selection: The server uses a generative AI model to search the database for the appropriate team.

[1041] Notification function: The server generates appropriate escalation information and notifies the user.

[1042] Terminal

[1043] Terminals provide the interface through which users access and operate the system:

[1044] Input of consultation content: The user inputs the consultation content through the device UI. For example, the user inputs "Data analysis is required for a new project," sets the related tag as "Data analysis," and sets the required responsibility level as "Medium."

[1045] Data transmission: The terminal transmits the consultation details entered by the user to the server.

[1046] User

[1047] The user does the following:

[1048] Posting a consultation: A user posts a consultation regarding a specific problem or question.

[1049] Receiving the result: The user receives the notification from the server and checks the contents.

[1050] Contacting the escalation destination: The user contacts the notified escalation destination.

[1051] Data processing and calculation

[1052] 1. Data storage: First, the server retrieves each employee's area of ​​expertise from the employee directory and stores it in the database in tag format. It also records the scope of each team's responsibilities and the degree of responsibility as a number.

[1053] 2. Posting and sending consultation details: The user inputs the consultation details through the device's UI, and the device sends the information to the server.

[1054] 3. Analysis of consultation content: The server analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[1055] 4. Selection of escalation destination: The generative AI model searches the database for the optimal escalation destination based on the extracted tags and degree of responsibility.

[1056] 5. Notification: The server notifies the user of the information about the created escalation destination.

[1057] Specific examples

[1058] For example, if a user in department A is looking for an escalation point to "resolve technical issues related to a new project":

[1059] 1. The user enters the consultation content in the UI, selects the tags "Technical Issue" and "New Project," and sets the required level of responsibility to "High."

[1060] 2. The terminal sends the input information to the server.

[1061] 3. The server analyzes the received information and extracts the necessary tags and responsibility levels.

[1062] 4. The generative AI model searches the database for the optimal team. In this case, it determines that Team B is the best team because it can handle the technical challenges.

[1063] 5. The server notifies the user of Team B's introduction information.

[1064] Prompt Sentence Examples

[1065] "A user with a technical issue related to a new project is looking for an appropriate escalation point. The user posts the consultation as 'Solving the technical issue for the new project,' selects 'Technical issue' and 'New project' as tags, and sets the required level of responsibility as 'High.' Please analyze this information, search the database for the most suitable team, and notify the user of the introduction information."

[1066] The above is an embodiment of the invention.

[1067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1068] Step 1:

[1069] Stores employee specialties in tag format

[1070] Server: Extracts each employee's area of ​​expertise and experience from the employee directory and formats them into "tag format." For example, it generates tags such as "project management," "data analysis," and "front-end development."

[1071] Input: Employee directory data

[1072] Data processing and data calculation: An extraction algorithm is used to obtain area of ​​expertise information from the employee directory, and a tagging algorithm is used to generate tags.

[1073] Output: Tagged domain data

[1074] What happens: The server inserts new records into the "expertise" table of the database, adding each employee's ID and corresponding tag.

[1075] Step 2:

[1076] Record each team's scope of responsibility and level of responsibility

[1077] Server: Determines the scope of each team's responsibilities and their degree of responsibility, quantifies them, and records them in the database. For example, Team A's responsibility level for "Technology Development" is "High."

[1078] Input: Team Roles and Responsibilities

[1079] Data processing and calculation: The scope of responsibility and degree of responsibility are quantified and stored in the database.

[1080] Output: Updated database

[1081] Specific operation: The server creates a "team information" table in the database and adds each team's ID, area of ​​responsibility, and degree of responsibility.

[1082] Step 3:

[1083] Users post their inquiries

[1084] User: Enter the details of the consultation using the dedicated UI. Write specific details such as "Data analysis is required for a new project," and set the related tag "Data Analysis" and the required level of responsibility as "Medium."

[1085] Input: consultation content, tags, degree of responsibility

[1086] Output: User input data

[1087] Specific operation: The user enters the necessary information into the input form and clicks the "Submit" button.

[1088] Step 4:

[1089] The entered data is sent to the server

[1090] Terminal: The consultation details entered by the user are sent to the server as an HTTP request. At this time, the consultation details, tags, and responsibility level are sent in JSON format.

[1091] Input: User-entered data

[1092] Data processing and data calculation: Convert user input data into JSON format and send it to the server.

[1093] Output: JSON format data

[1094] Specific operation: A POST request is generated from the browser to the server, and the content is included in the request body.

[1095] Step 5:

[1096] Analyze received consultation content

[1097] Server: Parses the received JSON data, extracts the consultation content, tags, and responsibility level, and validates the content for accuracy.

[1098] Input: JSON format data

[1099] Data processing and data calculation: JSON parsing and data validation.

[1100] Output: Extracted tags and responsibility counts

[1101] Specific behavior: Uses a JSON parser to store data in variables and checks for required fields.

[1102] Step 6:

[1103] Find the right team

[1104] Generative AI: Search for suitable teams in the database based on the extracted tag "Data Analysis" and the responsibility level "Medium". Filter candidate teams using a tag matching algorithm.

[1105] Input: Extracted tags and responsibility levels

[1106] Data processing and data calculation: Issue an SQL query to extract teams that match the criteria from the database.

[1107] Output: Optimal team

[1108] What it does: Runs an SQL query to search the database and selects teams that match the criteria.

[1109] Step 7:

[1110] Generate introduction information for selected teams

[1111] Generative AI: Generates introductory information for the selected team—for example, Team B's areas of expertise and contact information.

[1112] Input: Best team information

[1113] Data processing and data calculation: Run a script to automatically generate an introduction.

[1114] Output: Generated referral information

[1115] Specific operation: Run a script to generate an introduction based on the acquired team information.

[1116] Step 8:

[1117] Notify user

[1118] Server: Prepares the generated team introduction information for notification to the user. For example, it formats the notification content to say, "Team B is suitable for data analysis and has medium responsibility."

[1119] Input: Generated referral information

[1120] Data processing and data calculation: The notification content is inserted into an HTML template to create a response for display in the user's UI.

[1121] Output: User notification

[1122] Specific operation: The notification content is formatted in HTML and a response is sent to the user's device.

[1123] The above are the processing steps of the program for this system.

[1124] (Application example 1)

[1125] 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."

[1126] Conventional escalation management systems have made it difficult to quickly select and respond to problems and technical issues that arise within a company. As a result, it often takes time to resolve problems, resulting in a decline in production efficiency. Furthermore, particularly with factory equipment, a delayed response to an abnormality can lead to major losses or accidents. To solve these issues, an escalation management system needs the ability to select and notify the most appropriate engineer in real time.

[1127] 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.

[1128] In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and degree of responsibility in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and degrees of responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and degrees of responsibility; means for generating information on the appropriate escalation destination and notifying the user; means for posting a problem in cooperation with a robot that detects abnormalities in factory equipment; means for analyzing the area of ​​expertise and degree of responsibility required for the problem and searching for an appropriate engineer; means for sending a notification to the engineer based on the search results; and means for tracking each team's degree of responsibility and updating their evaluation. This makes it possible to select the optimal engineer in real time to respond quickly to abnormalities and technical issues in factory equipment.

[1129] An "area of ​​expertise" is a field or range of fields in which an employee with specific skills or knowledge excels.

[1130] "Experience" refers to the accumulation of knowledge and skills that an employee has gained from actual work or projects they have undertaken in the past.

[1131] "Tag format" is a method of assigning specific keywords or categories to each piece of information, making it easier to classify and search for information.

[1132] "Degree of responsibility" is a numerical representation of the degree of responsibility each team or employee has for a specific task or project.

[1133] A "database" is an information system that stores data based on a certain structure and enables efficient searching and processing.

[1134] A "user" is an individual or department that uses the system to input the details of a consultation.

[1135] "Consultation content" refers to detailed information about a problem or issue that a user enters through the system.

[1136] "Extraction" refers to the process of selecting necessary elements and keywords from the provided information.

[1137] An "optimal escalation point" is a team or employee selected to best respond to a particular issue or challenge.

[1138] "Generation" is the process of creating new information or data using algorithms or programs.

[1139] "Notification" refers to the act of sending information from the system to users or technicians, or that information.

[1140] "Factory equipment" refers to all machines and devices used in production lines and manufacturing processes.

[1141] An "abnormality" is a phenomenon or event that deviates from the standard operating conditions of factory equipment.

[1142] A "robot" is a mechanical device that performs autonomous or controlled operations within a factory facility.

[1143] An "engineer" is a professional who has specific techniques and skills and who solves problems and maintains equipment.

[1144] "Tracking" refers to the process or means of tracking and recording specific data or circumstances.

[1145] Evaluation is the process of quantifying or verbalizing the behavior and achievements of a team or employee based on specific criteria.

[1146] This invention is a system for efficient escalation management that utilizes tags and responsibility levels based on employees' areas of expertise and experience. The system is composed of the following means.

[1147] Data storage method

[1148] The server stores each employee's area of ​​expertise and experience in "tag format." For example, tags such as "mechanical engineering," "electrical engineering," and "program control" are assigned. Furthermore, the scope of each team's responsibilities and degree of responsibility are recorded as numerical values ​​in the database. For example, Team A's level of responsibility for "mechanical problems" is set to "high."

[1149] Detecting anomalies in factory equipment and reporting problems

[1150] The robot detects abnormalities within factory equipment, such as abnormal vibrations or control errors. The detected abnormalities are sent to the server, along with detailed information about the abnormality (for example, "abnormal vibration detected, restart failed, cause unknown").

[1151] Analysis of consultation content and selection of escalation destination

[1152] The server analyzes the received consultation content. In this analysis, it extracts the necessary "tags" and "responsibility levels." For example, the "mechanical problem" tag and "high" responsibility level are extracted.

[1153] The generative AI model is then used to search the database for the most suitable technician based on the extracted tags and responsibilities, using a tag-matching algorithm. For example, Technician B is determined to be the best fit, and his / her expertise and contact information are generated.

[1154] Notification method for technicians

[1155] The server notifies the robot of the generated engineer information. The robot then notifies the engineer of the received information in real time. For example, it may send a notification saying, "We will ask Engineer B to identify the cause of the abnormal vibration and repair it."

[1156] Evaluation and Update Methods

[1157] The server tracks the responsibility rating of each team and engineer and updates the rating. For example, if Engineer B resolves the issue quickly and effectively, his / her responsibility rating will be updated from "medium" to "high."

[1158] Specific examples

[1159] Consider a scenario where abnormal vibrations are detected in a factory.

[1160] 1. The robot sends a message to the server saying, "Abnormal vibration detected, restart failed, cause unknown."

[1161] 2. The server analyzes the problem content and extracts the "mechanical problem" tag and the "high" responsibility score.

[1162] 3. The generative AI model selects Technician B from the database as the best person to escalate the issue based on the tag and degree of responsibility.

[1163] 4. The server notifies the robot of the generated engineer information, and the robot notifies Engineer B in real time.

[1164] 5. Engineer B solves the problem, the result is recorded on the server, and the responsibility score is updated.

[1165] Example prompt for a generative AI model:

[1166] "Select the most suitable engineer based on the employee's area of ​​expertise and level of responsibility, and generate engineer information that matches the following tags and levels of responsibility: Tag: ['Mechanical Problem'] Level of Responsibility: 'High'"

[1167] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1168] Step 1:

[1169] The server stores each employee's area of ​​expertise and experience in the form of tags. To do this, it receives employee profile data and stores their area of ​​expertise (e.g., "mechanical engineering," "electrical engineering," etc.) and experience level (e.g., "entry," "intermediate," "advanced") as tags in the database. The input is the employee profile data, and the output is the updated database record.

[1170] Step 2:

[1171] The server records each team's scope of responsibility and degree of responsibility as a numerical value in the database. This allows each team's area of ​​expertise and its degree of responsibility (e.g., "high," "medium," or "low") to be stored as structured data. The input is the information on each team's scope of responsibility and degree of responsibility, and the output is the numerical data stored in the database.

[1172] Step 3:

[1173] The robot detects anomalies in factory equipment and sends details to a server. For example, it analyzes sensor data to identify anomalies such as "abnormal vibration detected, restart failed, cause unknown" and sends that information to the server. The input is the sensor data and detailed information about the anomaly, and the output is an anomaly report sent to the server.

[1174] Step 4:

[1175] The server analyzes the received anomaly report and extracts the necessary tags and responsibility levels. This analysis uses natural language processing technology to derive, for example, a "mechanical problem" tag and a "high" responsibility level. The input is the anomaly report, and the output is the extracted tags and responsibility levels.

[1176] Step 5:

[1177] The server uses a generative AI model to search the database for the most suitable engineer based on the extracted tags and responsibility levels. This process uses a tag-matching algorithm to select the engineer who best matches, for example, the "mechanical engineering" tag and "high" responsibility level. The input is the tag and responsibility level, and the output is the information on the most suitable engineer.

[1178] Step 6:

[1179] The server notifies the robot of the generated technician information, which includes the technician's specialty and contact information. The input is the information of the best technician, and the output is the technician notification sent to the robot.

[1180] Step 7:

[1181] The robot sends a real-time notification to the appropriate technician based on the received technician information. For example, it may send a message saying, "We will ask technician B to identify the cause of the abnormal vibration and repair it." The input is the technician notification, and the output is the notification message to the technician.

[1182] Step 8:

[1183] The engineer solves the problem and reports the results to the server, which receives the report and updates the engineer's responsibility score. The input is the problem-solving report, and the output is a database record of the updated responsibility score.

[1184] 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.

[1185] This invention is a system that combines an emotion engine with an efficient in-house escalation management system, which recognizes the user's emotions and suggests the most appropriate escalation destination, enabling efficient and empathetic responses.

[1186] Program processing

[1187] Data Storage

[1188] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[1189] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[1190] Consultation posting and sentiment analysis

[1191] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[1192] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[1193] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[1194] Escalation selection and notification

[1195] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level," while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issues," "high" responsibility level, and "urgency."

[1196] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility levels, and emotional information. It uses a tag-matching algorithm to filter relevant teams and selects the team that meets the responsibility level criteria and takes emotional information into account.

[1197] Generation AI: Generates introductory information for the selected team. For example, if Team B is determined to be suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[1198] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[1199] Response and evaluation

[1200] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[1201] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[1202] Server: Continuously tracks each team's responsibility rating and updates the rating based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, the server updates their responsibility rating and emotional response rating.

[1203] Specific examples

[1204] scenario

[1205] A user in department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is highly stressed and needs a solution quickly.

[1206] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[1207] 2. Terminal: Sends this information to the server.

[1208] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user feels a high level of urgency.

[1209] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[1210] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[1211] 6. Server: Stores the generated information in a database and returns it to the terminal.

[1212] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[1213] 8. User: Check the notified information and contact Team B urgently.

[1214] This satisfying collaboration allows necessary information to be gathered quickly and the appropriate escalation point to be selected efficiently. This eliminates the "internal Dragon Quest" phenomenon within the company and makes project progress much smoother. Furthermore, by taking the user's feelings into consideration, a more empathetic and prompt response is possible.

[1215] The processing flow will be explained below.

[1216] Step 1:

[1217] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, tags such as "data analysis," "project management," and "front-end development" are extracted from each employee's resume and project experience and stored in the database.

[1218] Step 2:

[1219] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "technology development" is registered as "high," and Team B's level of responsibility for "market analysis" is registered as "medium."

[1220] Step 3:

[1221] User: Enters and posts the content of the consultation through the UI. For example, to discuss technical issues related to a new project, the user selects the tags "New Project" and "Technical Issues" and sets the required level of responsibility as "High."

[1222] Step 4:

[1223] Terminal: Sends the consultation details entered by the user to the server. Specifically, the entered data is sent to the server as an HTTP request from the form.

[1224] Step 5:

[1225] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." For example, it parses and extracts information on "new projects," "technical issues," and "high" responsibility level.

[1226] Step 6:

[1227] Emotion engine: Analyzes the text of the consultation content and determines the user's emotions. Specifically, it uses natural language processing technology to detect whether the user is feeling urgency or stress. For example, it extracts the emotion "very urgent" from the consultation content.

[1228] Step 7:

[1229] Generative AI: Searches the database for the most appropriate escalation destination based on required tags, responsibility, and sentiment information. It uses a tag-matching algorithm to filter relevant teams, and also takes sentiment information into account to select teams with a suitable responsibility level.

[1230] Step 8:

[1231] Generation AI: Generates introductory information about the selected team. For example, it creates detailed information in text format, such as "Team B can handle technical issues and is suitable for emergency response."

[1232] Step 9:

[1233] Server: Stores the generated team introduction information in a database and returns it to the terminal. The generated introduction information is added to the database and sent to the terminal as an HTTP response.

[1234] Step 10:

[1235] Device: Notify the user of the escalation destination and team introduction information. Specifically, display on the UI the message "Team B is suitable, and the contact information for the person in charge is as follows," and notify by push notification or email as necessary.

[1236] Step 11:

[1237] User: Review the information provided and contact the appropriate escalation point. Specifically, use the provided contact information to contact Team B directly or request their cooperation in resolving the issue.

[1238] Step 12:

[1239] Server: Tracks each team's responsibility rating and updates it based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, its responsibility rating and emotional response rating will be updated.

[1240] By performing these steps sequentially, the optimal escalation destination is selected taking into account the user's feelings, enabling efficient and empathetic problem solving.

[1241] Example 2

[1242] 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."

[1243] Conventional escalation management systems simply determine the escalation destination based on the work content and the specialist area of ​​the person in charge, without considering the user's feelings or urgency, making it difficult to provide a quick and empathetic response. Furthermore, if the appropriate person in charge is not selected properly, problem resolution is delayed and work efficiency decreases.

[1244] 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 storing information in tag format based on each employee's skill area and work experience; means for recording each team's scope of work and responsibility in a database as numerical values; means for accepting input of consultation content by a user; means for transmitting the input consultation content to the server; means for analyzing the user's emotions from the consultation content; means for extracting necessary tags and responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags, responsibility, and emotion information; means for generating information on appropriate escalation destinations and notifying the user; and means for tracking each team's responsibility and updating the evaluation. This enables quick and empathetic selection of an escalation destination that also takes into account the user's emotions and urgency.

[1245] 1. "Skill areas of each employee"

[1246] Each employee's skill area refers to the field or area in which the employee has expertise or experience, such as data analysis, project management, or front-end development.

[1247] 2. "Work experience"

[1248] Work experience refers to the experience and achievements of an employee in the work or projects they have worked on in the past, which reveals their skill set and expertise.

[1249] 3. "Tag Format"

[1250] Tagging refers to a data format that categorizes information with specific keywords or labels to facilitate searching and filtering. It is used to represent each employee's skill areas and work experience.

[1251] 4. "Scope of Work"

[1252] The scope of work refers to the area of ​​work or project that each team is responsible for, specifically, the team's work content, such as technology development or market analysis.

[1253] 5. “Responsibility”

[1254] Responsibility is a numerical representation of how much responsibility each team or employee has for a particular task or issue, and can be high, medium, or low.

[1255] 6. "Consultation Content"

[1256] Consultation content refers to specific problems or issues that users post through the system for which they seek advice or support, including technical issues related to new projects.

[1257] 7. “Emotional Analysis”

[1258] Sentiment analysis refers to the process of analyzing a user's emotional state (e.g., stress, urgency) from text data using natural language processing techniques.

[1259] 8. "Best escalation point"

[1260] The optimal escalation destination is the team or employee that is determined to be able to respond most appropriately based on the content of the consultation and the results of sentiment analysis.

[1261] 9. "Generate Information"

[1262] Information generation refers to the process of creating specific text or data formats to notify users based on the extracted data.

[1263] 10. "Tracking"

[1264] Tracking is the process of continuously monitoring specific data or metrics, recording and evaluating them as needed, to continually assess each team's accountability.

[1265] 11. "Update your rating"

[1266] Refreshing ratings refers to the process of keeping each team or employee's responsibilities and performance ratings up to date based on the data and feedback obtained through tracking.

[1267] This invention is an efficient in-company escalation management system that is implemented in a form that combines an emotion engine. This enables efficient and empathetic responses by recognizing the user's emotions and suggesting the most appropriate escalation destination. The specific configuration and operation are described below.

[1268] 1. Data Storage

[1269] Server: Stores information in tag format based on each employee's skill area and work experience. Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[1270] Server: Records the scope of work and level of responsibility of each team in a database as a number. For example, each team can register the level of responsibility for the field or issue they are responsible for (e.g., "technology development" or "market analysis") as a number such as "high," "medium," or "low."

[1271] 2. Posting of consultations and sentiment analysis

[1272] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, select tags such as "new project" or "technical issues" and set the required level of responsibility as "high."

[1273] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[1274] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[1275] 3. Escalation Selection and Notification

[1276] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility level, while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issue," "high" responsibility level, and "urgency."

[1277] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility, and emotion information. It uses a tag matching algorithm to filter relevant teams and selects the team that meets the responsibility criteria and takes emotion information into account.

[1278] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be the most suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[1279] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[1280] 4. Response and Evaluation

[1281] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[1282] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[1283] Server: Continuously tracks each team's responsibility and updates their evaluation based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, it updates their responsibility and emotional response.

[1284] Specific examples

[1285] scenario

[1286] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is feeling very stressed and needs a solution quickly.

[1287] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[1288] 2. Terminal: Sends this information to the server.

[1289] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user has a high level of urgency.

[1290] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[1291] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[1292] 6. Server: Stores the generated information in a database and returns it to the terminal.

[1293] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[1294] 8. User: Check the notified information and contact Team B urgently.

[1295] In this way, necessary information is gathered quickly and the appropriate escalation point is efficiently selected. This eliminates the "internal Dragon Quest" phenomenon within the company and makes the progress of projects smoother. Also, by taking the user's feelings into consideration, more empathetic and prompt responses are possible.

[1296] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1297] Step 1:

[1298] Server: Stores information in tag form based on each employee's skill area and work experience.

[1299] Specific operation:

[1300] Input: Resume and project experience data for each employee.

[1301] Data processing: Extract tags such as "data analysis," "project management," and "front-end development" from each employee's resume and project experience.

[1302] Output: Save the extracted tags to a database.

[1303] Step 2:

[1304] Server: Record each team's scope of work and level of responsibility in a database.

[1305] Specific operation:

[1306] Input: Data on each team's work content and scope of responsibilities.

[1307] Data processing: Classify the level of responsibility for each team's scope of work (such as "technology development" or "market analysis") into a numerical value of "high," "medium," or "low."

[1308] Output: Record the classified responsibility in a database.

[1309] Step 3:

[1310] User: Enters the consultation details through the UI and posts.

[1311] Specific operation:

[1312] Input: The consultation topic, tags (e.g., "New Project" or "Technical Issue"), and responsibility level (e.g., "High") that the user enters into the UI form.

[1313] Data processing: The input consultation content is classified in tag format and the required level of responsibility is confirmed.

[1314] Output: The submitted consultation content is sent to the server via the form.

[1315] Step 4:

[1316] Terminal: Sends the entered consultation details to the server.

[1317] Specific operation:

[1318] Input: Consultation content data entered by the user.

[1319] Data processing: Convert the data entered in the form into an HTTP request.

[1320] Output: Forwarded to the server as an HTTP request.

[1321] Step 5:

[1322] Emotion engine: Analyzes the user's emotions from the content of the consultation.

[1323] Specific operation:

[1324] Input: Text data of the consultation content sent from the server.

[1325] Data processing: Using text analysis techniques, we analyze emotions such as stress and urgency felt by the user.

[1326] Output: Generates sentiment analysis results (e.g., "urgent" or "stressed").

[1327] Step 6:

[1328] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[1329] Specific operation:

[1330] Input: Consultation details and emotion analysis results sent from the device.

[1331] Data processing: Extract tags such as "new project," "technical issue," and "high" responsibility level, as well as emotional information, from the consultation content.

[1332] Output: The extracted information is sent to a generative AI model.

[1333] Step 7:

[1334] Generative AI: Searches for the appropriate team from the database based on extracted tags, responsibilities, and sentiment information, and generates introduction information.

[1335] Specific operation:

[1336] Input: Tags, responsibility, and emotion information sent from the server.

[1337] Data processing: Using a tag-matching algorithm, we filter relevant teams from the database and select the most suitable team based on responsibility and sentiment information.

[1338] Output: Generates introductory information about the selected team (team name, area of ​​expertise, area of ​​responsibility, contact information).

[1339] Step 8:

[1340] Server: Stores the generated team introduction information in a database and returns it to the terminal.

[1341] Specific operation:

[1342] Input: Team introduction information sent from the generation AI.

[1343] Data processing: Store the information in a database and convert it into an HTTP response format.

[1344] Output: Sends a reply to the terminal.

[1345] Step 9:

[1346] Terminal: Notifies user of escalation and team introduction information.

[1347] Specific operation:

[1348] Input: Team introduction information sent from the server.

[1349] Data processing: Formatting data in a format that can be displayed on the UI.

[1350] Output: The referral information is notified to the user.

[1351] Step 10:

[1352] User: Review the information provided and contact the appropriate escalation point.

[1353] Specific operation:

[1354] Input: Contact information for escalation from the terminal.

[1355] Data processing: We will contact the team directly using the contact information you provide.

[1356] Output: A query is made.

[1357] Step 11:

[1358] Server: Continuously track each team's accountability and update the ratings.

[1359] Specific operation:

[1360] Input: Feedback data from each team and the analysis results of the emotion engine.

[1361] Data processing: Based on feedback data and sentiment information, update each team's responsibility and performance evaluation.

[1362] Output: Responsibility and rating are updated in the database.

[1363] (Application example 2)

[1364] 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."

[1365] In conventional factories, there is a need for a system that can detect equipment anomalies early and efficiently notify the appropriate escalation contact point. It is particularly important to respond quickly and accurately to urgent problems. However, typical escalation management systems often do not take emotional information into account and instead rely solely on mechanical responses. This results in delayed responses after an anomaly is detected, leading to problems such as reduced productivity throughout the factory. The present invention addresses these problems.

[1366] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and responsibility level in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and responsibility levels from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and responsibility levels; means for generating information on appropriate escalation destinations and notifying the user; means for tracking each team's responsibility level and updating their evaluations; means including a group of sensors for detecting abnormalities in factory equipment; means including an emotion engine for analyzing abnormality data and generating emotion information based on the severity of the abnormality; and means for suggesting an appropriate escalation destination based on the emotion information. This enables quick and accurate escalation responses that take into account the nature and urgency of the abnormality.

[1367] An "employee" is an individual employed to perform a specific function in a factory or company.

[1368] An "area of ​​expertise" is an area in which an employee has particular knowledge, skills, and is particularly knowledgeable.

[1369] "Tag format" is a method of categorizing and organizing information by assigning keywords and labels to make it easier to distinguish.

[1370] A database is an information system that systematically organizes and stores large amounts of information, allowing it to be quickly searched and retrieved as needed.

[1371] "Degree of responsibility" is a numerical representation of the importance and degree of responsibility for a specific area of ​​responsibility or task.

[1372] "Consultation content" refers to issues or concerns that employees or users input into the system as problems or questions.

[1373] "Extraction" refers to the process of extracting specific elements or information from data.

[1374] An "escalation destination" is the next department or team to address to resolve a particular problem or issue.

[1375] An "emotion engine" is a system that analyzes the user's emotions from input information and suggests appropriate responses based on that information.

[1376] "Abnormality" refers to the occurrence of behavior or phenomena in equipment or systems that are outside the normal range.

[1377] A "sensor group" is a collection of multiple sensors that measure the status of equipment and the environment and detect abnormalities.

[1378] A "suggestion" is the act of suggesting appropriate actions or options for a particular situation or task.

[1379] This invention is a system for detecting abnormalities in equipment in a factory and selecting the appropriate escalation destination, and it proposes the most appropriate escalation destination based on emotional information. How the system is implemented will be explained below in detail.

[1380] System Overview

[1381] The system consists of the following main components:

[1382] 1. Sensors

[1383] 2. Server

[1384] 3. Emotion Engine

[1385] 4. Generation AI

[1386] 5. User Interface

[1387] Hardware and Software

[1388] Sensors: Temperature sensors, vibration sensors, sound sensors, etc. installed on equipment. These sensors collect environmental data within the factory in real time.

[1389] Server: A server for data storage and processing. The database stores information on each employee's area of ​​expertise, and each team's scope and level of responsibility.

[1390] Emotion Engine: A software component that performs emotion analysis. It uses text analysis techniques to generate emotion information from anomaly data.

[1391] Generative AI: An artificial intelligence model that selects the optimal escalation point and generates the necessary information.

[1392] User interface: The interface for displaying the escalation notification and accepting user input.

[1393] Data processing and calculation

[1394] 1. Data entry and problem detection

[1395] The sensors collect data and transmit it to a server, including temperature, vibration, and sound data.

[1396] The server analyzes the received data, and if an abnormality is detected, it sends detailed information to the emotion engine.

[1397] 2. Emotion analysis

[1398] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, if the severity of the anomaly is high, the emotion information generated is "urgent."

[1399] 3. Escalation destination selection

[1400] The server uses the emotional information obtained from the emotion engine to search the database for the optimal escalation destination.

[1401] The generation AI selects the appropriate team and experts based on the extracted emotional information, area of ​​expertise tags, and degree of responsibility, and generates detailed escalation information.

[1402] 4. Notification and Response

[1403] The server notifies the user interface of the escalation information created by the generation AI.

[1404] The user reviews the notification and takes the appropriate action based on the information provided.

[1405] Specific examples

[1406] For example, if the operating temperature of a factory device becomes too high and abnormal vibrations are detected, the prompt might look like this:

[1407] "The temperature has reached 80 degrees, the vibration rate has reached 0.5g, and the noise level is 20dB. Does this abnormal operating condition require urgent attention? A quick cool-down or detailed maintenance is required."

[1408] This system detects abnormalities in factory equipment early and selects the escalation destination based on the urgency of the situation. It also promptly notifies users of appropriate countermeasures, which is expected to improve factory productivity and safety.

[1409] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1410] Step 1:

[1411] A group of sensors collects status data (temperature, vibration, sound, etc.) from factory equipment and sends it to a server. Specifically, the sensors monitor environmental data in real time and use an anomaly detection algorithm to detect abnormal data. The server receives this as input, and if it contains abnormal data, passes it on to the next step. The input data are numerical values ​​for temperature, vibration, and sound, and the output data are the results of the abnormality detection.

[1412] Step 2:

[1413] The server analyzes the transmitted data, and if an abnormality is detected, it sends detailed information to the emotion engine. Specifically, an abnormal data analysis module runs within the server and identifies the type and severity of the abnormality (for example, a temperature of 80 degrees or a vibration level of 0.5g). The input data is the details of the abnormal data, and the output data is the abnormality information to be passed to the emotion engine.

[1414] Step 3:

[1415] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, it gives information such as "high urgency" or "immediate response required." The input data is the anomaly information, and the output data is emotion information. The emotion engine uses text analysis technology to generate an emotion score based on pre-set rules.

[1416] Step 4:

[1417] The server searches the database for the most appropriate escalation destination based on the emotional information obtained from the emotion engine. Specifically, it uses a tag matching algorithm to filter relevant teams and experts, and then selects the appropriate person in charge. The input data is emotional information along with tags and responsibility level information, and the output data is information on the selected escalation destination.

[1418] Step 5:

[1419] The generation AI selects the most appropriate escalation contact and generates detailed escalation information. This information is generated in text format, including information on the selected team's area of ​​expertise, contact person, contact information, etc. The input data is tag and sentiment information, and the generated output data is detailed escalation contact information.

[1420] Step 6:

[1421] The server notifies the user interface of the escalation information created by the generation AI. Specifically, it sends the escalation information as an HTTP response and displays it on the user's device. It prompts the user for confirmation and, if necessary, issues an alert using a notification mechanism. The input data is the escalation information, and the output data is the notification displayed to the user.

[1422] Step 7:

[1423] The user reviews the notification and takes the appropriate action based on the information provided, such as contacting a designated escalation point or viewing the steps to resolve the problem. The input data is the displayed escalation information, and the user's actions are the output. This process ensures that equipment anomalies are handled quickly and accurately.

[1424] 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.

[1425] 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.

[1426] 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.

[1427] [Fourth embodiment]

[1428] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1429] 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.

[1430] 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).

[1431] 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.

[1432] 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.

[1433] 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).

[1434] 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.

[1435] 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.

[1436] 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.

[1437] 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.

[1438] 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.

[1439] 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.

[1440] 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."

[1441] This invention is an efficient in-house escalation management system that stores each employee's area of ​​expertise in tag format and quantifies and records their degree of responsibility in a database, making it possible to quickly search for the most appropriate escalation destination and notify the user.

[1442] Program processing

[1443] Data Storage

[1444] Server: Store each employee's area of ​​expertise and experience in the employee directory in "tag format." For example, assign tags such as "project management," "data analysis," and "front-end development."

[1445] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "Technology Development" is "High."

[1446] Submit a consultation

[1447] User: Posts a request through the UI. For example, they might write, "I need data analysis for a new project," and set the associated tag as "Data Analysis" and the required level of responsibility as "Medium."

[1448] Terminal: Sends the consultation details entered by the user to the server.

[1449] Escalation selection and notification

[1450] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility levels." For example, the "data analysis" tag and "medium" responsibility level are extracted.

[1451] Generative AI: Searches for suitable teams from the database based on the extracted tags and responsibility levels. It uses a tag matching algorithm to filter out the best teams and selects the team whose responsibility level meets the criteria.

[1452] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be suitable, it generates the team's expertise and contact information.

[1453] Server: Notifies the user of the generated team introduction information. For example, informs the user that "Team B is suitable for data analysis and has a medium level of responsibility."

[1454] Specific examples

[1455] scenario

[1456] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project.

[1457] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[1458] 2. Terminal: Sends this information to the server.

[1459] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels.

[1460] 4. Generative AI: Based on the extracted information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[1461] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[1462] 6. Server: Stores the generated information in a database and returns it to the terminal.

[1463] 7. Terminal: Notify the user of Team B's introduction information.

[1464] 8. User: Check the notified information and contact Team B.

[1465] This system will streamline escalation and information gathering within the company, eliminating the "internal Dragon Quest" phenomenon, and ultimately promoting faster project progress and efficient problem solving.

[1466] The processing flow will be explained below.

[1467] Step 1:

[1468] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[1469] Step 2:

[1470] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[1471] Step 3:

[1472] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[1473] Step 4:

[1474] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[1475] Step 5:

[1476] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." Specifically, it parses the request content and extracts the information such as "new project," "technical issues," and "high" responsibility level.

[1477] Step 6:

[1478] Generative AI: Searches for the most suitable team from the database based on the extracted tags and responsibility levels. Specifically, it uses a tag-matching algorithm to filter relevant teams and selects the team whose responsibility level meets the criteria.

[1479] Step 7:

[1480] Generative AI: Generates introduction information for the selected team, specifically creating written information about the selected team's areas of expertise, responsibilities, and contact information.

[1481] Step 8:

[1482] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[1483] Step 9:

[1484] Terminal: Notify the user of the escalation destination and team introduction information. Specifically, the introduction information is displayed on the UI, and the notification function is used to notify the user as needed.

[1485] Step 10:

[1486] User: Review the information provided and contact the appropriate escalation channel, either by contacting the team directly using the contact information provided or by requesting their help in resolving the issue.

[1487] By following these steps, necessary information can be gathered quickly and the appropriate escalation point can be efficiently selected. This will eliminate the "internal Dragon Quest" phenomenon within the company and make the progress of the project much smoother.

[1488] Example 1

[1489] 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."

[1490] Conventional corporate escalation management systems make it difficult to quickly find the appropriate escalation contact point, making it difficult to resolve problems efficiently. In particular, they lack sufficient information management based on the expertise and experience of each employee or team, making it time-consuming to select the optimal escalation contact point based on the level of responsibility. Furthermore, inappropriate selection of the escalation contact point can delay problem resolution, negatively impacting the overall progress of the project.

[1491] 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.

[1492] In this invention, the server includes a means for storing information in tag format based on each employee's area of ​​expertise and experience, a means for recording each team's scope of responsibility and degree of responsibility in a database as numerical values, and a means for accepting input of consultation content by users and transmitting the content to the server, thereby enabling efficient escalation management.

[1493] "Tag format" is a metadata format that identifies each employee's area of ​​expertise and experience, and is additional information that makes searching and filtering easier.

[1494] "Degree of responsibility" is a numerical representation of the level of responsibility each team or individual has for a specific job or task, and is used to select the destination of escalation.

[1495] A "database" is a system for systematically storing, managing, and searching related data such as employee information, team responsibilities, and levels of responsibility.

[1496] The "contents of consultation" is text information that the user inputs in response to a specific problem or question, and is reference information when selecting an escalation destination.

[1497] "Generated artificial intelligence" refers to algorithms and models that search a database for optimal escalation destinations and generate appropriate referral information.

[1498] A "tag matching algorithm" is a calculation method for detecting matches between multiple tag data and selecting the optimal combination.

[1499] "Notification" is a communication method for informing the user of important information, and includes the results of selection of the escalation destination.

[1500] "Tracking" is the process of tracking each team's responsibility level and recording any fluctuations.

[1501] "Evaluation" is the process of measuring the performance and response capabilities of each team or employee based on data such as tracked responsibility levels.

[1502] The present invention relates to a system for realizing efficient escalation management within a company, and is implemented using the following hardware and software configuration.

[1503] Hardware and Software Configuration

[1504] server

[1505] The server is the central part of the system and performs the following functions:

[1506] Employee directory management: The server stores each employee's area of ​​expertise and experience in the form of tags. For example, tags such as "project management," "data analysis," and "front-end development" are assigned.

[1507] Team information management: The server records each team's scope of responsibility and degree of responsibility in a database as a numerical value. For example, Team A's degree of responsibility for "technology development" is "high."

[1508] Receiving and analyzing consultation content: The server receives the consultation content from the user and extracts the necessary tags and responsibility levels.

[1509] Escalation Selection: The server uses a generative AI model to search the database for the appropriate team.

[1510] Notification function: The server generates appropriate escalation information and notifies the user.

[1511] Terminal

[1512] Terminals provide the interface through which users access and operate the system:

[1513] Input of consultation content: The user inputs the consultation content through the device UI. For example, the user inputs "Data analysis is required for a new project," sets the related tag as "Data analysis," and sets the required responsibility level as "Medium."

[1514] Data transmission: The terminal transmits the consultation details entered by the user to the server.

[1515] User

[1516] The user does the following:

[1517] Posting a consultation: A user posts a consultation regarding a specific problem or question.

[1518] Receiving the result: The user receives the notification from the server and checks the contents.

[1519] Contacting the escalation destination: The user contacts the notified escalation destination.

[1520] Data processing and calculation

[1521] 1. Data storage: First, the server retrieves each employee's area of ​​expertise from the employee directory and stores it in the database in tag format. It also records the scope of each team's responsibilities and the degree of responsibility as a number.

[1522] 2. Posting and sending consultation details: The user inputs the consultation details through the device's UI, and the device sends the information to the server.

[1523] 3. Analysis of consultation content: The server analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[1524] 4. Selection of escalation destination: The generative AI model searches the database for the optimal escalation destination based on the extracted tags and degree of responsibility.

[1525] 5. Notification: The server notifies the user of the information about the created escalation destination.

[1526] Specific examples

[1527] For example, if a user in department A is looking for an escalation point to "resolve technical issues related to a new project":

[1528] 1. The user enters the consultation content in the UI, selects the tags "Technical Issue" and "New Project," and sets the required level of responsibility to "High."

[1529] 2. The terminal sends the input information to the server.

[1530] 3. The server analyzes the received information and extracts the necessary tags and responsibility levels.

[1531] 4. The generative AI model searches the database for the optimal team. In this case, it determines that Team B is the best team because it can handle the technical challenges.

[1532] 5. The server notifies the user of Team B's introduction information.

[1533] Prompt Sentence Examples

[1534] "A user with a technical issue related to a new project is looking for an appropriate escalation point. The user posts the consultation as 'Solving the technical issue for the new project,' selects 'Technical issue' and 'New project' as tags, and sets the required level of responsibility as 'High.' Please analyze this information, search the database for the most suitable team, and notify the user of the introduction information."

[1535] The above is an embodiment of the invention.

[1536] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1537] Step 1:

[1538] Stores employee specialties in tag format

[1539] Server: Extracts each employee's area of ​​expertise and experience from the employee directory and formats them into "tag format." For example, it generates tags such as "project management," "data analysis," and "front-end development."

[1540] Input: Employee directory data

[1541] Data processing and data calculation: An extraction algorithm is used to obtain area of ​​expertise information from the employee directory, and a tagging algorithm is used to generate tags.

[1542] Output: Tagged domain data

[1543] What happens: The server inserts new records into the "expertise" table of the database, adding each employee's ID and corresponding tag.

[1544] Step 2:

[1545] Record each team's scope of responsibility and level of responsibility

[1546] Server: Determines the scope of each team's responsibilities and their degree of responsibility, quantifies them, and records them in the database. For example, Team A's responsibility level for "Technology Development" is "High."

[1547] Input: Team Roles and Responsibilities

[1548] Data processing and calculation: The scope of responsibility and degree of responsibility are quantified and stored in the database.

[1549] Output: Updated database

[1550] Specific operation: The server creates a "team information" table in the database and adds each team's ID, area of ​​responsibility, and degree of responsibility.

[1551] Step 3:

[1552] Users post their inquiries

[1553] User: Enter the details of the consultation using the dedicated UI. Write specific details such as "Data analysis is required for a new project," and set the related tag "Data Analysis" and the required level of responsibility as "Medium."

[1554] Input: consultation content, tags, degree of responsibility

[1555] Output: User input data

[1556] Specific operation: The user enters the necessary information into the input form and clicks the "Submit" button.

[1557] Step 4:

[1558] The entered data is sent to the server

[1559] Terminal: The consultation details entered by the user are sent to the server as an HTTP request. At this time, the consultation details, tags, and responsibility level are sent in JSON format.

[1560] Input: User-entered data

[1561] Data processing and data calculation: Convert user input data into JSON format and send it to the server.

[1562] Output: JSON format data

[1563] Specific operation: A POST request is generated from the browser to the server, and the content is included in the request body.

[1564] Step 5:

[1565] Analyze received consultation content

[1566] Server: Parses the received JSON data, extracts the consultation content, tags, and responsibility level, and validates the content for accuracy.

[1567] Input: JSON format data

[1568] Data processing and data calculation: JSON parsing and data validation.

[1569] Output: Extracted tags and responsibility counts

[1570] Specific behavior: Uses a JSON parser to store data in variables and checks for required fields.

[1571] Step 6:

[1572] Find the right team

[1573] Generative AI: Search for suitable teams in the database based on the extracted tag "Data Analysis" and the responsibility level "Medium". Filter candidate teams using a tag matching algorithm.

[1574] Input: Extracted tags and responsibility levels

[1575] Data processing and data calculation: Issue an SQL query to extract teams that match the criteria from the database.

[1576] Output: Optimal team

[1577] What it does: Runs an SQL query to search the database and selects teams that match the criteria.

[1578] Step 7:

[1579] Generate introduction information for selected teams

[1580] Generative AI: Generates introductory information for the selected team—for example, Team B's areas of expertise and contact information.

[1581] Input: Best team information

[1582] Data processing and data calculation: Run a script to automatically generate an introduction.

[1583] Output: Generated referral information

[1584] Specific operation: Run a script to generate an introduction based on the acquired team information.

[1585] Step 8:

[1586] Notify user

[1587] Server: Prepares the generated team introduction information for notification to the user. For example, it formats the notification content to say, "Team B is suitable for data analysis and has medium responsibility."

[1588] Input: Generated referral information

[1589] Data processing and data calculation: The notification content is inserted into an HTML template to create a response for display in the user's UI.

[1590] Output: User notification

[1591] Specific operation: The notification content is formatted in HTML and a response is sent to the user's device.

[1592] The above are the processing steps of the program for this system.

[1593] (Application example 1)

[1594] 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."

[1595] Conventional escalation management systems have made it difficult to quickly select and respond to problems and technical issues that arise within a company. As a result, it often takes time to resolve problems, resulting in a decline in production efficiency. Furthermore, particularly with factory equipment, a delayed response to an abnormality can lead to major losses or accidents. To solve these issues, an escalation management system needs the ability to select and notify the most appropriate engineer in real time.

[1596] 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.

[1597] In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and degree of responsibility in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and degrees of responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and degrees of responsibility; means for generating information on the appropriate escalation destination and notifying the user; means for posting a problem in cooperation with a robot that detects abnormalities in factory equipment; means for analyzing the area of ​​expertise and degree of responsibility required for the problem and searching for an appropriate engineer; means for sending a notification to the engineer based on the search results; and means for tracking each team's degree of responsibility and updating their evaluation. This makes it possible to select the optimal engineer in real time to respond quickly to abnormalities and technical issues in factory equipment.

[1598] An "area of ​​expertise" is a field or range of fields in which an employee with specific skills or knowledge excels.

[1599] "Experience" refers to the accumulation of knowledge and skills that an employee has gained from actual work or projects they have undertaken in the past.

[1600] "Tag format" is a method of assigning specific keywords or categories to each piece of information, making it easier to classify and search for information.

[1601] "Degree of responsibility" is a numerical representation of the degree of responsibility each team or employee has for a specific task or project.

[1602] A "database" is an information system that stores data based on a certain structure and enables efficient searching and processing.

[1603] A "user" is an individual or department that uses the system to input the details of a consultation.

[1604] "Consultation content" refers to detailed information about a problem or issue that a user enters through the system.

[1605] "Extraction" refers to the process of selecting necessary elements and keywords from the provided information.

[1606] An "optimal escalation point" is a team or employee selected to best respond to a particular issue or challenge.

[1607] "Generation" is the process of creating new information or data using algorithms or programs.

[1608] "Notification" refers to the act of sending information from the system to users or technicians, or that information.

[1609] "Factory equipment" refers to all machines and devices used in production lines and manufacturing processes.

[1610] An "abnormality" is a phenomenon or event that deviates from the standard operating conditions of factory equipment.

[1611] A "robot" is a mechanical device that performs autonomous or controlled operations within a factory facility.

[1612] An "engineer" is a professional who has specific techniques and skills and who solves problems and maintains equipment.

[1613] "Tracking" refers to the process or means of tracking and recording specific data or circumstances.

[1614] Evaluation is the process of quantifying or verbalizing the behavior and achievements of a team or employee based on specific criteria.

[1615] This invention is a system for efficient escalation management that utilizes tags and responsibility levels based on employees' areas of expertise and experience. The system is composed of the following means.

[1616] Data storage method

[1617] The server stores each employee's area of ​​expertise and experience in "tag format." For example, tags such as "mechanical engineering," "electrical engineering," and "program control" are assigned. Furthermore, the scope of each team's responsibilities and degree of responsibility are recorded as numerical values ​​in the database. For example, Team A's level of responsibility for "mechanical problems" is set to "high."

[1618] Detecting anomalies in factory equipment and reporting problems

[1619] The robot detects abnormalities within factory equipment, such as abnormal vibrations or control errors. The detected abnormalities are sent to the server, along with detailed information about the abnormality (for example, "abnormal vibration detected, restart failed, cause unknown").

[1620] Analysis of consultation content and selection of escalation destination

[1621] The server analyzes the received consultation content. In this analysis, it extracts the necessary "tags" and "responsibility levels." For example, the "mechanical problem" tag and "high" responsibility level are extracted.

[1622] The generative AI model is then used to search the database for the most suitable technician based on the extracted tags and responsibilities, using a tag-matching algorithm. For example, Technician B is determined to be the best fit, and his / her expertise and contact information are generated.

[1623] Notification method for technicians

[1624] The server notifies the robot of the generated engineer information. The robot then notifies the engineer of the received information in real time. For example, it may send a notification saying, "We will ask Engineer B to identify the cause of the abnormal vibration and repair it."

[1625] Evaluation and Update Methods

[1626] The server tracks the responsibility rating of each team and engineer and updates the rating. For example, if Engineer B resolves the issue quickly and effectively, his / her responsibility rating will be updated from "medium" to "high."

[1627] Specific examples

[1628] Consider a scenario where abnormal vibrations are detected in a factory.

[1629] 1. The robot sends a message to the server saying, "Abnormal vibration detected, restart failed, cause unknown."

[1630] 2. The server analyzes the problem content and extracts the "mechanical problem" tag and the "high" responsibility score.

[1631] 3. The generative AI model selects Technician B from the database as the best person to escalate the issue based on the tag and degree of responsibility.

[1632] 4. The server notifies the robot of the generated engineer information, and the robot notifies Engineer B in real time.

[1633] 5. Engineer B solves the problem, the result is recorded on the server, and the responsibility score is updated.

[1634] Example prompt for a generative AI model:

[1635] "Select the most suitable engineer based on the employee's area of ​​expertise and level of responsibility, and generate engineer information that matches the following tags and levels of responsibility: Tag: ['Mechanical Problem'] Level of Responsibility: 'High'"

[1636] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1637] Step 1:

[1638] The server stores each employee's area of ​​expertise and experience in the form of tags. To do this, it receives employee profile data and stores their area of ​​expertise (e.g., "mechanical engineering," "electrical engineering," etc.) and experience level (e.g., "entry," "intermediate," "advanced") as tags in the database. The input is the employee profile data, and the output is the updated database record.

[1639] Step 2:

[1640] The server records each team's scope of responsibility and degree of responsibility as a numerical value in the database. This allows each team's area of ​​expertise and its degree of responsibility (e.g., "high," "medium," or "low") to be stored as structured data. The input is the information on each team's scope of responsibility and degree of responsibility, and the output is the numerical data stored in the database.

[1641] Step 3:

[1642] The robot detects anomalies in factory equipment and sends details to a server. For example, it analyzes sensor data to identify anomalies such as "abnormal vibration detected, restart failed, cause unknown" and sends that information to the server. The input is the sensor data and detailed information about the anomaly, and the output is an anomaly report sent to the server.

[1643] Step 4:

[1644] The server analyzes the received anomaly report and extracts the necessary tags and responsibility levels. This analysis uses natural language processing technology to derive, for example, a "mechanical problem" tag and a "high" responsibility level. The input is the anomaly report, and the output is the extracted tags and responsibility levels.

[1645] Step 5:

[1646] The server uses a generative AI model to search the database for the most suitable engineer based on the extracted tags and responsibility levels. This process uses a tag-matching algorithm to select the engineer who best matches, for example, the "mechanical engineering" tag and "high" responsibility level. The input is the tag and responsibility level, and the output is the information on the most suitable engineer.

[1647] Step 6:

[1648] The server notifies the robot of the generated technician information, which includes the technician's specialty and contact information. The input is the information of the best technician, and the output is the technician notification sent to the robot.

[1649] Step 7:

[1650] The robot sends a real-time notification to the appropriate technician based on the received technician information. For example, it may send a message saying, "We will ask technician B to identify the cause of the abnormal vibration and repair it." The input is the technician notification, and the output is the notification message to the technician.

[1651] Step 8:

[1652] The engineer solves the problem and reports the results to the server, which receives the report and updates the engineer's responsibility score. The input is the problem-solving report, and the output is a database record of the updated responsibility score.

[1653] 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.

[1654] This invention is a system that combines an emotion engine with an efficient in-house escalation management system, which recognizes the user's emotions and suggests the most appropriate escalation destination, enabling efficient and empathetic responses.

[1655] Program processing

[1656] Data Storage

[1657] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[1658] Server: Records each team's scope of responsibility and degree of responsibility in a database as a numerical value. Specifically, for each team's field or issue (e.g., "technology development" or "market analysis"), the degree of responsibility is registered as a numerical value such as "high," "medium," or "low."

[1659] Consultation posting and sentiment analysis

[1660] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, you select tags such as "new project" and "technical issues" and set the required level of responsibility as "high."

[1661] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[1662] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[1663] Escalation selection and notification

[1664] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level," while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issues," "high" responsibility level, and "urgency."

[1665] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility levels, and emotional information. It uses a tag-matching algorithm to filter relevant teams and selects the team that meets the responsibility level criteria and takes emotional information into account.

[1666] Generation AI: Generates introductory information for the selected team. For example, if Team B is determined to be suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[1667] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[1668] Response and evaluation

[1669] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[1670] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[1671] Server: Continuously tracks each team's responsibility rating and updates the rating based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, the server updates their responsibility rating and emotional response rating.

[1672] Specific examples

[1673] scenario

[1674] A user in department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is highly stressed and needs a solution quickly.

[1675] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[1676] 2. Terminal: Sends this information to the server.

[1677] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user feels a high level of urgency.

[1678] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[1679] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[1680] 6. Server: Stores the generated information in a database and returns it to the terminal.

[1681] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[1682] 8. User: Check the notified information and contact Team B urgently.

[1683] This satisfying collaboration allows necessary information to be gathered quickly and the appropriate escalation point to be selected efficiently. This eliminates the "internal Dragon Quest" phenomenon within the company and makes project progress much smoother. Furthermore, by taking the user's feelings into consideration, a more empathetic and prompt response is possible.

[1684] The processing flow will be explained below.

[1685] Step 1:

[1686] Server: Stores each employee's area of ​​expertise and experience in the employee directory in "tag format." Specifically, tags such as "data analysis," "project management," and "front-end development" are extracted from each employee's resume and project experience and stored in the database.

[1687] Step 2:

[1688] Server: Records each team's scope of responsibility and level of responsibility in a database as a numerical value. For example, Team A's level of responsibility for "technology development" is registered as "high," and Team B's level of responsibility for "market analysis" is registered as "medium."

[1689] Step 3:

[1690] User: Enters and posts the content of the consultation through the UI. For example, to discuss technical issues related to a new project, the user selects the tags "New Project" and "Technical Issues" and sets the required level of responsibility as "High."

[1691] Step 4:

[1692] Terminal: Sends the consultation details entered by the user to the server. Specifically, the entered data is sent to the server as an HTTP request from the form.

[1693] Step 5:

[1694] Server: Analyzes the received consultation content and extracts the necessary "tags" and "responsibility level." For example, it parses and extracts information on "new projects," "technical issues," and "high" responsibility level.

[1695] Step 6:

[1696] Emotion engine: Analyzes the text of the consultation content and determines the user's emotions. Specifically, it uses natural language processing technology to detect whether the user is feeling urgency or stress. For example, it extracts the emotion "very urgent" from the consultation content.

[1697] Step 7:

[1698] Generative AI: Searches the database for the most appropriate escalation destination based on required tags, responsibility, and sentiment information. It uses a tag-matching algorithm to filter relevant teams, and also takes sentiment information into account to select teams with a suitable responsibility level.

[1699] Step 8:

[1700] Generation AI: Generates introductory information about the selected team. For example, it creates detailed information in text format, such as "Team B can handle technical issues and is suitable for emergency response."

[1701] Step 9:

[1702] Server: Stores the generated team introduction information in a database and returns it to the terminal. The generated introduction information is added to the database and sent to the terminal as an HTTP response.

[1703] Step 10:

[1704] Device: Notify the user of the escalation destination and team introduction information. Specifically, display on the UI the message "Team B is suitable, and the contact information for the person in charge is as follows," and notify by push notification or email as necessary.

[1705] Step 11:

[1706] User: Review the information provided and contact the appropriate escalation point. Specifically, use the provided contact information to contact Team B directly or request their cooperation in resolving the issue.

[1707] Step 12:

[1708] Server: Tracks each team's responsibility rating and updates it based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, its responsibility rating and emotional response rating will be updated.

[1709] By performing these steps sequentially, the optimal escalation destination is selected taking into account the user's feelings, enabling efficient and empathetic problem solving.

[1710] Example 2

[1711] 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."

[1712] Conventional escalation management systems simply determine the escalation destination based on the work content and the specialist area of ​​the person in charge, without considering the user's feelings or urgency, making it difficult to provide a quick and empathetic response. Furthermore, if the appropriate person in charge is not selected properly, problem resolution is delayed and work efficiency decreases.

[1713] 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 storing information in tag format based on each employee's skill area and work experience; means for recording each team's scope of work and responsibility in a database as numerical values; means for accepting input of consultation content by a user; means for transmitting the input consultation content to the server; means for analyzing the user's emotions from the consultation content; means for extracting necessary tags and responsibility from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags, responsibility, and emotion information; means for generating information on appropriate escalation destinations and notifying the user; and means for tracking each team's responsibility and updating the evaluation. This enables quick and empathetic selection of an escalation destination that also takes into account the user's emotions and urgency.

[1714] 1. "Skill areas of each employee"

[1715] Each employee's skill area refers to the field or area in which the employee has expertise or experience, such as data analysis, project management, or front-end development.

[1716] 2. "Work experience"

[1717] Work experience refers to the experience and achievements of an employee in the work or projects they have worked on in the past, which reveals their skill set and expertise.

[1718] 3. "Tag Format"

[1719] Tagging refers to a data format that categorizes information with specific keywords or labels to facilitate searching and filtering. It is used to represent each employee's skill areas and work experience.

[1720] 4. "Scope of Work"

[1721] The scope of work refers to the area of ​​work or project that each team is responsible for, specifically, the team's work content, such as technology development or market analysis.

[1722] 5. “Responsibility”

[1723] Responsibility is a numerical representation of how much responsibility each team or employee has for a particular task or issue, and can be high, medium, or low.

[1724] 6. "Consultation Content"

[1725] Consultation content refers to specific problems or issues that users post through the system for which they seek advice or support, including technical issues related to new projects.

[1726] 7. “Emotional Analysis”

[1727] Sentiment analysis refers to the process of analyzing a user's emotional state (e.g., stress, urgency) from text data using natural language processing techniques.

[1728] 8. "Best escalation point"

[1729] The optimal escalation destination is the team or employee that is determined to be able to respond most appropriately based on the content of the consultation and the results of sentiment analysis.

[1730] 9. "Generate Information"

[1731] Information generation refers to the process of creating specific text or data formats to notify users based on the extracted data.

[1732] 10. "Tracking"

[1733] Tracking is the process of continuously monitoring specific data or metrics, recording and evaluating them as needed, to continually assess each team's accountability.

[1734] 11. "Update your rating"

[1735] Refreshing ratings refers to the process of keeping each team or employee's responsibilities and performance ratings up to date based on the data and feedback obtained through tracking.

[1736] This invention is an efficient in-company escalation management system that is implemented in a form that combines an emotion engine. This enables efficient and empathetic responses by recognizing the user's emotions and suggesting the most appropriate escalation destination. The specific configuration and operation are described below.

[1737] 1. Data Storage

[1738] Server: Stores information in tag format based on each employee's skill area and work experience. Specifically, information extracted from each employee's resume and project experience is saved in the database as tags such as "data analysis," "project management," and "front-end development."

[1739] Server: Records the scope of work and level of responsibility of each team in a database as a number. For example, each team can register the level of responsibility for the field or issue they are responsible for (e.g., "technology development" or "market analysis") as a number such as "high," "medium," or "low."

[1740] 2. Posting of consultations and sentiment analysis

[1741] User: Enters and posts the content of the consultation through the UI. For example, if you want to consult about technical issues related to a new project, select tags such as "new project" or "technical issues" and set the required level of responsibility as "high."

[1742] Terminal: Sends the consultation details entered by the user to the server. Specifically, the data entered in the form is transferred to the server as an HTTP request.

[1743] Emotion engine: Analyzes the user's emotions from the content of the consultation. For example, it uses text analysis technology to determine whether the user is feeling stressed or urgent.

[1744] 3. Escalation Selection and Notification

[1745] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility level, while also including emotional information obtained from the emotion engine. For example, it extracts information such as "new project," "technical issue," "high" responsibility level, and "urgency."

[1746] Generative AI: Searches for suitable teams from the database based on the extracted tags, responsibility, and emotion information. It uses a tag matching algorithm to filter relevant teams and selects the team that meets the responsibility criteria and takes emotion information into account.

[1747] Generation AI: Generates introduction information for the selected team. For example, if Team B is determined to be the most suitable, it creates written information about the team, including their areas of expertise, responsibilities, and contact information.

[1748] Server: Stores the generated team introduction information in a database and returns it to the device. Specifically, the new introduction information is added to the database and returned to the device as an HTTP response.

[1749] 4. Response and Evaluation

[1750] Device: Notify users of escalation destinations and team introduction information. The introduction information is displayed on the UI and notifications are used to notify users as needed.

[1751] User: Review the information provided and contact the appropriate escalation channel. Use the contact information provided to contact the team directly or request their help in resolving the issue.

[1752] Server: Continuously tracks each team's responsibility and updates their evaluation based on feedback from the emotion engine. For example, if Team B responds quickly to an emergency, it updates their responsibility and emotional response.

[1753] Specific examples

[1754] scenario

[1755] A user in Department A is looking for the appropriate escalation point to resolve a technical issue related to a new project. The user is feeling very stressed and needs a solution quickly.

[1756] 1. User: Post the consultation content as "Solving technical issues in a new project" from the UI. Select "Technical Issue" and "New Project" as tags and set the required responsibility level as "High."

[1757] 2. Terminal: Sends this information to the server.

[1758] 3. Server: Analyzes the received information and extracts the necessary tags and responsibility levels. Furthermore, the emotion engine determines whether the user has a high level of urgency.

[1759] 4. Generative AI: Based on the extracted information and emotional information, the AI ​​searches the database for the most appropriate escalation destination. In this case, it determines that Team B, which can handle the technical issues, is the most appropriate.

[1760] 5. Generation AI: Generates introduction information for Team B and sends it to the server.

[1761] 6. Server: Stores the generated information in a database and returns it to the terminal.

[1762] 7. Terminal: Notify the user of the introduction information of Team B. The content is "Team B is suitable for technical issues that require urgent response, and this is the contact information for the person in charge."

[1763] 8. User: Check the notified information and contact Team B urgently.

[1764] In this way, necessary information is gathered quickly and the appropriate escalation point is efficiently selected. This eliminates the "internal Dragon Quest" phenomenon within the company and makes the progress of projects smoother. Also, by taking the user's feelings into consideration, more empathetic and prompt responses are possible.

[1765] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1766] Step 1:

[1767] Server: Stores information in tag form based on each employee's skill area and work experience.

[1768] Specific operation:

[1769] Input: Resume and project experience data for each employee.

[1770] Data processing: Extract tags such as "data analysis," "project management," and "front-end development" from each employee's resume and project experience.

[1771] Output: Save the extracted tags to a database.

[1772] Step 2:

[1773] Server: Record each team's scope of work and level of responsibility in a database.

[1774] Specific operation:

[1775] Input: Data on each team's work content and scope of responsibilities.

[1776] Data processing: Classify the level of responsibility for each team's scope of work (such as "technology development" or "market analysis") into a numerical value of "high," "medium," or "low."

[1777] Output: Record the classified responsibility in a database.

[1778] Step 3:

[1779] User: Enters the consultation details through the UI and posts.

[1780] Specific operation:

[1781] Input: The consultation topic, tags (e.g., "New Project" or "Technical Issue"), and responsibility level (e.g., "High") that the user enters into the UI form.

[1782] Data processing: The input consultation content is classified in tag format and the required level of responsibility is confirmed.

[1783] Output: The submitted consultation content is sent to the server via the form.

[1784] Step 4:

[1785] Terminal: Sends the entered consultation details to the server.

[1786] Specific operation:

[1787] Input: Consultation content data entered by the user.

[1788] Data processing: Convert the data entered in the form into an HTTP request.

[1789] Output: Forwarded to the server as an HTTP request.

[1790] Step 5:

[1791] Emotion engine: Analyzes the user's emotions from the content of the consultation.

[1792] Specific operation:

[1793] Input: Text data of the consultation content sent from the server.

[1794] Data processing: Using text analysis techniques, we analyze emotions such as stress and urgency felt by the user.

[1795] Output: Generates sentiment analysis results (e.g., "urgent" or "stressed").

[1796] Step 6:

[1797] Server: Analyzes the received consultation content and extracts the necessary tags and responsibility levels.

[1798] Specific operation:

[1799] Input: Consultation details and emotion analysis results sent from the device.

[1800] Data processing: Extract tags such as "new project," "technical issue," and "high" responsibility level, as well as emotional information, from the consultation content.

[1801] Output: The extracted information is sent to a generative AI model.

[1802] Step 7:

[1803] Generative AI: Searches for the appropriate team from the database based on extracted tags, responsibilities, and sentiment information, and generates introduction information.

[1804] Specific operation:

[1805] Input: Tags, responsibility, and emotion information sent from the server.

[1806] Data processing: Using a tag-matching algorithm, we filter relevant teams from the database and select the most suitable team based on responsibility and sentiment information.

[1807] Output: Generates introductory information about the selected team (team name, area of ​​expertise, area of ​​responsibility, contact information).

[1808] Step 8:

[1809] Server: Stores the generated team introduction information in a database and returns it to the terminal.

[1810] Specific operation:

[1811] Input: Team introduction information sent from the generation AI.

[1812] Data processing: Store the information in a database and convert it into an HTTP response format.

[1813] Output: Sends a reply to the terminal.

[1814] Step 9:

[1815] Terminal: Notifies user of escalation and team introduction information.

[1816] Specific operation:

[1817] Input: Team introduction information sent from the server.

[1818] Data processing: Formatting data in a format that can be displayed on the UI.

[1819] Output: The referral information is notified to the user.

[1820] Step 10:

[1821] User: Review the information provided and contact the appropriate escalation point.

[1822] Specific operation:

[1823] Input: Contact information for escalation from the terminal.

[1824] Data processing: We will contact the team directly using the contact information you provide.

[1825] Output: A query is made.

[1826] Step 11:

[1827] Server: Continuously track each team's accountability and update the ratings.

[1828] Specific operation:

[1829] Input: Feedback data from each team and the analysis results of the emotion engine.

[1830] Data processing: Based on feedback data and sentiment information, update each team's responsibility and performance evaluation.

[1831] Output: Responsibility and rating are updated in the database.

[1832] (Application example 2)

[1833] 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."

[1834] In conventional factories, there is a need for a system that can detect equipment anomalies early and efficiently notify the appropriate escalation contact point. It is particularly important to respond quickly and accurately to urgent problems. However, typical escalation management systems often do not take emotional information into account and instead rely solely on mechanical responses. This results in delayed responses after an anomaly is detected, leading to problems such as reduced productivity throughout the factory. The present invention addresses these problems.

[1835] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for storing information in tag format based on each employee's area of ​​expertise and experience; means for recording each team's scope of responsibility and responsibility level in a database as a numerical value; means for accepting user input of consultation content; means for extracting necessary tags and responsibility levels from the consultation content; means for searching the database for the optimal escalation destination based on the extracted tags and responsibility levels; means for generating information on appropriate escalation destinations and notifying the user; means for tracking each team's responsibility level and updating their evaluations; means including a group of sensors for detecting abnormalities in factory equipment; means including an emotion engine for analyzing abnormality data and generating emotion information based on the severity of the abnormality; and means for suggesting an appropriate escalation destination based on the emotion information. This enables quick and accurate escalation responses that take into account the nature and urgency of the abnormality.

[1836] An "employee" is an individual employed to perform a specific function in a factory or company.

[1837] An "area of ​​expertise" is an area in which an employee has particular knowledge, skills, and is particularly knowledgeable.

[1838] "Tag format" is a method of categorizing and organizing information by assigning keywords and labels to make it easier to distinguish.

[1839] A database is an information system that systematically organizes and stores large amounts of information, allowing it to be quickly searched and retrieved as needed.

[1840] "Degree of responsibility" is a numerical representation of the importance and degree of responsibility for a specific area of ​​responsibility or task.

[1841] "Consultation content" refers to issues or concerns that employees or users input into the system as problems or questions.

[1842] "Extraction" refers to the process of extracting specific elements or information from data.

[1843] An "escalation destination" is the next department or team to address to resolve a particular problem or issue.

[1844] An "emotion engine" is a system that analyzes the user's emotions from input information and suggests appropriate responses based on that information.

[1845] "Abnormality" refers to the occurrence of behavior or phenomena in equipment or systems that are outside the normal range.

[1846] A "sensor group" is a collection of multiple sensors that measure the status of equipment and the environment and detect abnormalities.

[1847] A "suggestion" is the act of suggesting appropriate actions or options for a particular situation or task.

[1848] This invention is a system for detecting abnormalities in equipment in a factory and selecting the appropriate escalation destination, and it proposes the most appropriate escalation destination based on emotional information. How the system is implemented will be explained below in detail.

[1849] System Overview

[1850] The system consists of the following main components:

[1851] 1. Sensors

[1852] 2. Server

[1853] 3. Emotion Engine

[1854] 4. Generation AI

[1855] 5. User Interface

[1856] Hardware and Software

[1857] Sensors: Temperature sensors, vibration sensors, sound sensors, etc. installed on equipment. These sensors collect environmental data within the factory in real time.

[1858] Server: A server for data storage and processing. The database stores information on each employee's area of ​​expertise, and each team's scope and level of responsibility.

[1859] Emotion Engine: A software component that performs emotion analysis. It uses text analysis techniques to generate emotion information from anomaly data.

[1860] Generative AI: An artificial intelligence model that selects the optimal escalation point and generates the necessary information.

[1861] User interface: The interface for displaying the escalation notification and accepting user input.

[1862] Data processing and calculation

[1863] 1. Data entry and problem detection

[1864] The sensors collect data and transmit it to a server, including temperature, vibration, and sound data.

[1865] The server analyzes the received data, and if an abnormality is detected, it sends detailed information to the emotion engine.

[1866] 2. Emotion analysis

[1867] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, if the severity of the anomaly is high, the emotion information generated is "urgent."

[1868] 3. Escalation destination selection

[1869] The server uses the emotional information obtained from the emotion engine to search the database for the optimal escalation destination.

[1870] The generation AI selects the appropriate team and experts based on the extracted emotional information, area of ​​expertise tags, and degree of responsibility, and generates detailed escalation information.

[1871] 4. Notification and Response

[1872] The server notifies the user interface of the escalation information created by the generation AI.

[1873] The user reviews the notification and takes the appropriate action based on the information provided.

[1874] Specific examples

[1875] For example, if the operating temperature of a factory device becomes too high and abnormal vibrations are detected, the prompt might look like this:

[1876] "The temperature has reached 80 degrees, the vibration rate has reached 0.5g, and the noise level is 20dB. Does this abnormal operating condition require urgent attention? A quick cool-down or detailed maintenance is required."

[1877] This system detects abnormalities in factory equipment early and selects the escalation destination based on the urgency of the situation. It also promptly notifies users of appropriate countermeasures, which is expected to improve factory productivity and safety.

[1878] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1879] Step 1:

[1880] A group of sensors collects status data (temperature, vibration, sound, etc.) from factory equipment and sends it to a server. Specifically, the sensors monitor environmental data in real time and use an anomaly detection algorithm to detect abnormal data. The server receives this as input, and if it contains abnormal data, passes it on to the next step. The input data are numerical values ​​for temperature, vibration, and sound, and the output data are the results of the abnormality detection.

[1881] Step 2:

[1882] The server analyzes the transmitted data, and if an abnormality is detected, it sends detailed information to the emotion engine. Specifically, an abnormal data analysis module runs within the server and identifies the type and severity of the abnormality (for example, a temperature of 80 degrees or a vibration level of 0.5g). The input data is the details of the abnormal data, and the output data is the abnormality information to be passed to the emotion engine.

[1883] Step 3:

[1884] The emotion engine analyzes the anomaly data and generates emotion information based on its urgency and importance. For example, it gives information such as "high urgency" or "immediate response required." The input data is the anomaly information, and the output data is emotion information. The emotion engine uses text analysis technology to generate an emotion score based on pre-set rules.

[1885] Step 4:

[1886] The server searches the database for the most appropriate escalation destination based on the emotional information obtained from the emotion engine. Specifically, it uses a tag matching algorithm to filter relevant teams and experts, and then selects the appropriate person in charge. The input data is emotional information along with tags and responsibility level information, and the output data is information on the selected escalation destination.

[1887] Step 5:

[1888] The generation AI selects the most appropriate escalation contact and generates detailed escalation information. This information is generated in text format, including information on the selected team's area of ​​expertise, contact person, contact information, etc. The input data is tag and sentiment information, and the generated output data is detailed escalation contact information.

[1889] Step 6:

[1890] The server notifies the user interface of the escalation information created by the generation AI. Specifically, it sends the escalation information as an HTTP response and displays it on the user's device. It prompts the user for confirmation and, if necessary, issues an alert using a notification mechanism. The input data is the escalation information, and the output data is the notification displayed to the user.

[1891] Step 7:

[1892] The user reviews the notification and takes the appropriate action based on the information provided, such as contacting a designated escalation point or viewing the steps to resolve the problem. The input data is the displayed escalation information, and the user's actions are the output. This process ensures that equipment anomalies are handled quickly and accurately.

[1893] 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.

[1894] 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.

[1895] 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.

[1896] 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.

[1897] 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.

[1898] 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...

Claims

1. A means of storing information in tag form based on each employee's area of ​​expertise and experience; A means of recording each team's scope of responsibility and degree of responsibility in a database as a number, means for accepting input of consultation content by a user; A means to extract necessary tags and responsibility levels from the consultation content, A means for searching the database for the most appropriate escalation destination based on the extracted tags and degree of responsibility; a means for generating appropriate escalation information and notifying the user; A means to track and update the responsibilities of each team; A system including:

2. The system of claim 1 , wherein the escalation destination selection uses a tag matching algorithm.

3. 2. The system of claim 1, further comprising means for notifying a user of an updated responsibility level.

Images