System

Abstract

A system is provided.SOLUTION: This system is provided with a means for making data related with collected technical power, knowledge, experience and goodness per person into a database, a means for receiving and analyzing inquiry contents from a user, a means for recommending a proper person based on the analyzed result and presenting the contact destination information of the person and a means for generating a proper sentence based on the inquiry contents and presenting it to 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] When planning a new service or making inquiries to other departments within a company, there are problems such as not knowing who to consult, or the person you relied on being retired or transferred and no longer being available. Furthermore, it takes time to write an appropriate inquiry, and if the person you contact is not appropriate, communication may not go smoothly, resulting in a decrease in work efficiency. To solve these problems, the present invention provides a system that quickly finds the right person and enables smooth communication. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems with a system that includes a means for compiling collected data on technical ability, knowledge, experience, and affability into a database; a means for receiving and analyzing inquiries from users; a means for recommending appropriate individuals based on the analysis results and presenting the individual's contact information; and a means for generating appropriate text based on the inquiry content and presenting it to the user. Furthermore, the system includes a means for registering information entered by employees themselves and evaluation information from colleagues in the database, and a means for comprehensively evaluating technical ability, knowledge, experience, and affability, thereby including an algorithm for recommending the most appropriate individual, thereby achieving rapid and accurate recommendation. Furthermore, the system includes a display means for generating formal and specific inquiry text and presenting it to the user, supporting smooth communication.

[0006] "Technical ability" refers to the degree of knowledge, ability, and skill related to a particular technology.

[0007] "Knowledge" refers to the information, data, and understanding-based experience related to a particular field.

[0008] "Experience" refers to the actual experience and skills gained through previous tasks, projects, and activities.

[0009] "Affability" refers to traits that give a good impression, such as friendliness and a cooperative attitude, when communicating with others and in interpersonal relationships.

[0010] "Database creation" refers to the process of organizing collected information and managing it so that it can be easily searched and used.

[0011] "User" refers to an individual or department that uses the system to make an inquiry.

[0012] "Inquiry Content" refers to the specific problem or question that a user enters into the system.

[0013] "Analysis" refers to the process of breaking down the input inquiry and identifying relevant information and requirements.

[0014] The "right person" is the person with the most relevant knowledge and experience for the particular inquiry.

[0015] "Recommendation" refers to the act of suggesting a specific person or information based on the results of analysis.

[0016] "Contact Information" means information necessary to contact the Recommended Person (e.g., email address, telephone number, etc.).

[0017] "Inquiry text" refers to specific and formal text generated by the system based on the user's inquiry.

[0018] The term "system" refers to a device or software that includes a series of processes and functions provided by the present invention.

[0019] An "algorithm" refers to a procedure or calculation used to solve a problem or analyze data.

[0020] "Display means" refers to a method or device for presenting the generated query sentences and recommendation results to the user. [Brief explanation of the drawings]

[0021] [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

[0022] 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.

[0023] First, the terms used in the following description will be explained.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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."

[0029] [First embodiment]

[0030] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0031] 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.

[0032] 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).

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] 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.

[0039] 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.

[0040] 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.

[0041] 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."

[0042] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. Furthermore, it generates an appropriate sentence based on the content of the inquiry and presents it to the user.

[0043] Collecting internal data and creating a database

[0044] server

[0045] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues, and stores this information in a centralized database. This allows detailed information on all employees to be managed systematically.

[0046] Receiving and analyzing inquiries from users

[0047] User

[0048] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[0049] Terminal

[0050] The terminal transmits the inquiry entered by the user to the server.

[0051] server

[0052] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[0053] Recommending the best person

[0054] server

[0055] The server searches the database for employees with the specified related skills and knowledge, and recommends the most suitable person from among them based on a comprehensive evaluation of technical ability, experience, friendliness, etc. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0056] Terminal

[0057] Information about recommended people is sent from the server to the terminal and presented to the user.

[0058] Query generation

[0059] server

[0060] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0061] Terminal

[0062] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[0063] Specific examples

[0064] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The server then obtains employee B's contact information and provides that information to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0065] In this way, the present invention is a system that finds the appropriate person and generates an inquiry sentence, thereby improving the efficiency of communication and information sharing within the company and supporting the smooth execution of business operations.

[0066] The processing flow will be explained below.

[0067] Step 1:

[0068] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[0069] Step 2:

[0070] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0071] Step 3:

[0072] The terminal receives the inquiry entered by the user and transmits it to the server.

[0073] Step 4:

[0074] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[0075] Step 5:

[0076] The server searches the database to find someone with the skills and knowledge related to the inquiry. For example, it may determine that employee B, who is knowledgeable about security, is the best person to contact.

[0077] Step 6:

[0078] The server comprehensively evaluates candidate employees based on their technical skills, experience, and personality, and recommends the most suitable candidate. The recommendation includes the employee's contact information.

[0079] Step 7:

[0080] The terminal receives information about the recommended people from the server and presents it to the user.

[0081] Step 8:

[0082] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, employee B. I would like to ask you about the security of our new web service. Could you please help me?"

[0083] Step 9:

[0084] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[0085] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[0086] Example 1

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

[0088] When planning a new in-house service or making inquiries to other departments, it is difficult to quickly find the right person and achieve smooth communication. In addition, generating appropriate sentences based on the content of the inquiry is time-consuming, which hinders efficient information sharing.

[0089] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0090] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiries and presenting them to the user, means for analyzing the user's inquiries using a natural language processing algorithm, and means for generating formal and specific inquiry sentences using a generative AI model. This enables the appropriate person to be found quickly when planning a new service within the company or making inquiries to other departments, and enables efficient communication and information sharing.

[0091] "Database creation" is the process of systematically organizing collected data and storing it in a form that makes it easy to search and use.

[0092] "User" means an individual or group of people who use the System to make inquiries.

[0093] "Query" refers to the text of the specific problem or question that a user enters into the system.

[0094] "Analysis" refers to the process by which the system understands the content of the query it receives based on its meaning and context, using natural language processing algorithms, among other things.

[0095] The "right person" refers to the employee who is most relevant to the inquiry and has high technical skills, knowledge, experience, and a friendly personality.

[0096] "Contact Information" means information sufficient to contact the appropriate person, including, for example, an email address and telephone number.

[0097] "Text generation" is the process of automatically creating formal and specific text based on the user's query, using a generative AI model.

[0098] "Natural language processing algorithms" refer to algorithms that allow computers to understand human language and analyze its meaning, thereby extracting key keywords from the content of inquiries.

[0099] A "generative AI model" is a model that uses artificial intelligence and refers to technology for generating appropriate responses and sentences from input data.

[0100] The following system configuration and operating procedures are available as an embodiment of the present invention. This system finds the most suitable person and ensures smooth communication when planning a new service within a company or making inquiries to other departments. The system stores collected data on technical ability, knowledge, experience, and affability in a database, analyzes the content of inquiries from users, and recommends the appropriate person. Furthermore, it generates appropriate sentences based on the content of the inquiry and presents them to the user.

[0101] Collecting internal data and creating a database

[0102] server

[0103] The server collects data on self-reported technical skills, knowledge, and experience from employees. It also collects information on friendliness as assessed by colleagues, and stores this data in a centralized database. This allows detailed information on all employees to be managed systematically. Specifically, data is collected through data entry forms and evaluation systems, and is registered in the database through daily batch processing.

[0104] Receiving and analyzing inquiries from users

[0105] User

[0106] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[0107] Terminal

[0108] The terminal converts the inquiry content entered by the user into an HTTP request and sends it to the server. Specifically, when the user enters information into the text box and presses the send button, the content is sent to the server.

[0109] server

[0110] The server analyzes the content of the received inquiry and identifies the technologies and knowledge related to that content. Specifically, it uses a natural language processing (NLP) algorithm to extract keywords from the inquiry and compare them with information in the database. For example, the keyword "security" can be extracted from an inquiry such as "I would like to consult about the security of a new web service."

[0111] Recommending the best person

[0112] server

[0113] The server searches the database for employees with the identified relevant skills and knowledge, and recommends the most suitable candidate based on a comprehensive evaluation of their technical ability, experience, and personality. This process involves calculating a score for each employee using a machine learning model. For example, an employee with expertise in security would receive a score of 95 for technical ability, 90 for experience, and 80 for personality, and would be recommended as the most suitable candidate.

[0114] Terminal

[0115] The server sends the recommended person's information to the terminal and presents it to the user. For example, it will be displayed as "The best person to consult about security: Employee B."

[0116] Query generation

[0117] server

[0118] The server generates a formal and specific query based on the user's inquiry. This process uses a generative AI model. For example, it generates a sentence like, "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?"

[0119] Terminal

[0120] The generated query text is sent to the terminal and displayed to the user, who can then copy and paste it or send it as is to quickly make a query.

[0121] Specific examples

[0122] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds an employee who is knowledgeable about security. The server then obtains the employee's contact information and provides it to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0123] Prompt Sentence Examples

[0124] "Can you recommend an employee with expertise in the security measures required for our new web service?"

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1:

[0127] Data collection and database creation

[0128] Input: Data entered by employees regarding their technical skills, knowledge, experience, and personality.

[0129] Server: The server receives data from employees about their self-reported technical skills, knowledge, and experience through an input form, and also collects data about their friendliness through a peer rating system.

[0130] Output: A consolidated employee dataset.

[0131] (Specific operation) The server runs a daily batch process to scrape form input and evaluation data and add it to the database. For example, if an employee enters "security, 5 years experience," that information is saved in the database.

[0132] Step 2:

[0133] Receiving inquiries

[0134] Input: The specific inquiry entered by the user using the terminal.

[0135] User: The user enters the inquiry (e.g., "I would like to consult about the security of a new web service") into the text box on the terminal and presses the send button.

[0136] Terminal: The terminal receives the entered text and sends it to the server as an HTTP POST request.

[0137] Output: HTTP request containing the query.

[0138] (Specific operation) When the user enters "I would like to consult about the security of a new web service" and clicks "Submit," the device generates an HTTP request containing this content and sends it to the server.

[0139] Step 3:

[0140] Analysis of inquiry content

[0141] Input: An HTTP request containing the query sent from the device.

[0142] Server: The server receives the HTTP request and invokes an NLP (Natural Language Processing) engine to analyze the query. The NLP engine extracts key keywords from the query.

[0143] Output: Extracted keywords.

[0144] (Specific operation) The server receives the text "I would like to consult about the security of a new web service," and the NLP engine extracts the keyword "security."

[0145] Step 4:

[0146] Searching for relevant data and recommending the best people

[0147] Input: Keywords extracted by analysis (e.g. "security").

[0148] Server: The server searches the database for employees with skills and knowledge related to the extracted keywords. The list of employees obtained as a result of the search is scored using a machine learning model to recommend the most suitable candidate. The scoring takes into account factors such as technical ability, experience, and friendliness.

[0149] Output: Best fit information.

[0150] (Specific operation) The server generates a list of employees with skills related to "security." For example, employee B is recommended as the most suitable person with a score of 95 points for technical ability, 90 points for experience, and 80 points for per capita.

[0151] Step 5:

[0152] Presenting information to the most suitable person

[0153] Input: Recommended best person information.

[0154] Server: The server obtains the information of the recommended person and sends it to the terminal.

[0155] Terminal: The terminal receives the information of the most suitable person sent from the server and presents it to the user.

[0156] Output: The best match information presented to the user.

[0157] (Specific operation) Employee B's details are displayed in the user's browser, and the user is notified that "Employee B is the best person to consult about security issues."

[0158] Step 6:

[0159] Query generation

[0160] Input: The user's specific inquiry and the recommended best person information.

[0161] Server: The server uses a generative AI model to generate formal queries for the recommended people.

[0162] Output: The generated query text.

[0163] (Specific operation) The generative AI model generates the sentence, "Employee B, I would like to consult you about the security of a new web service. Could you assist me?"

[0164] Step 7:

[0165] Presentation of generated query sentences

[0166] Input: The generated query text.

[0167] Server: The server sends the generated query sentence to the terminal.

[0168] Terminal: The terminal receives the query text sent from the server and displays it to the user. The user uses this text to make a query.

[0169] Output: The query text presented to the user.

[0170] (Specific operation) The following message will be displayed on the user's screen: "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?" The user can quickly make an inquiry by copying and pasting this message or sending it as is.

[0171] (Application example 1)

[0172] 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."

[0173] Technical problems and business-related questions frequently arise in factories, requiring quick and appropriate responses. With conventional methods, it takes time to find someone with the appropriate technical skills and knowledge, making it difficult to solve problems efficiently. Furthermore, generating formal inquiry sentences based on the inquiry content is time-consuming, which hinders smooth communication.

[0174] 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.

[0175] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating formal inquiry sentences from the inquiry sentences using a generative model, and means for providing the generated inquiry sentences to users via display means. This enables quick and appropriate responses to technical problems and business questions that arise in the factory, enabling efficient problem solving and smooth communication.

[0176] "Collected data on technical skills, knowledge, experience, and personality" refers to information on technical skills, knowledge, and experience self-reported by employees, as well as information on personality as assessed by colleagues.

[0177] "Means for creating a database" refers to means for systematically storing and managing the above data.

[0178] "Means for receiving and analyzing inquiries from users" refers to means for receiving specific problems or inquiries entered by users and mechanically analyzing the contents of those inquiries.

[0179] "Means for recommending appropriate individuals based on the analysis results and presenting their contact information" refers to means for identifying employees with skills and knowledge related to the analyzed inquiry content and providing the user with the employee's contact information.

[0180] "Means for generating formal inquiry sentences from inquiry content using a generative model" refers to means for generating formal inquiry sentences based on the inquiry content from a user using a generative artificial intelligence model.

[0181] The "means for providing the generated query sentence to the user via the display means" refers to a means for visually presenting the generated query sentence to the user.

[0182] "Means for comprehensively evaluating technical ability, knowledge, experience, and personality" refers to a means for identifying the most suitable person by comprehensively evaluating technical ability, knowledge, experience, and personality when analyzing the content of an inquiry.

[0183] "Means for generating query sentences using prompt sentences based on a generative model" refers to means for generating formal and specific query sentences using prompt sentences provided by a generative AI model.

[0184] This invention is a system for facilitating communication by quickly and accurately responding to technical problems and business-related questions that arise in factories. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes user inquiries, and recommends appropriate personnel. It also uses a generative model to generate formal inquiry sentences from the inquiries and provides them to users.

[0185] Collecting internal data and creating a database

[0186] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing and storing this data in a database, detailed information on all employees can be managed systematically.

[0187] Receiving and analyzing inquiries from users

[0188] The user enters a specific problem or inquiry into the system through a terminal, for example, "Question about security settings on a new machine." This inquiry is then sent from the terminal to the server.

[0189] The server analyzes the content of the received inquiry, identifies the skills and knowledge related to that content, and then uses an analytical algorithm to search a database for employees with the relevant technical skills and knowledge.

[0190] Recommending the best person

[0191] The server then comprehensively evaluates the analyzed technical skills, knowledge, experience, and friendliness, and recommends the most suitable person from the database. For example, it may recommend someone who is knowledgeable about the security settings of a new machine. The recommended person's contact information is then sent to the user's device.

[0192] Query generation

[0193] The server uses a generative AI model to generate a formal query based on the user's query, such as a prompt: "Please generate a formal query based on questions about the security settings of a new machine."

[0194] The generated inquiry text will look something like this: "Hello, person in charge. I would like to ask about the security settings of a new machine. Could you please help me? I would appreciate your advice on the following points. Thank you."

[0195] The generated query sentences are presented to the user via the terminal, enabling the user to communicate appropriately and quickly.

[0196] These processes are primarily performed by a server using database management software (e.g., SQLite) and generative AI models (e.g., OpenAI GPT-3), covering a series of steps from data collection, analysis, recommendation, query generation, to final presentation.

[0197] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0198] Step 1:

[0199] The user enters specific problems or inquiries into the system through the terminal. For example, they enter "questions about security settings on a new machine." This input data is sent to the server in JSON format. In this step, it is important that the user's inquiries are entered into the terminal specifically and clearly.

[0200] Step 2:

[0201] The terminal sends the query to the server. The data sent includes the query entered by the user. The server receives the query and stores it in a database. The server then performs preprocessing to analyze the query.

[0202] Step 3:

[0203] The server analyzes the received query using a natural language processing (NLP) algorithm. The input for this analysis is the query entered by the user, and the output is generated as keywords for the identified technology or knowledge. For example, the keyword "security settings" is extracted. This step requires accurate analysis of the query.

[0204] Step 4:

[0205] The server searches the database for employees with the specified skills and knowledge. The input data are the keywords extracted in step 3, and the output data is a list of employees with the relevant technical skills, knowledge, experience, and personality. The server then executes an SQL query to find the relevant employees in the database.

[0206] Step 5:

[0207] The server recommends the most suitable candidate based on the search results. The input data is the employee list obtained in step 4, and the output data is the contact information of the recommended candidate. The server identifies the most suitable candidate using an algorithm that comprehensively evaluates technical ability, knowledge, experience, and friendliness.

[0208] Step 6:

[0209] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a formal query based on the user's query. The input data here is the user's query and information about the recommended person, and the output data is the generated query. For example, the generated query might be, "I'd like to ask about the security settings for my new machine. Could you help me with that?"

[0210] Step 7:

[0211] The server provides the generated query sentence to the user via the terminal. The input data is the query sentence generated in step 6, and the output data is the query sentence displayed on the terminal. The terminal visually presents this query sentence to the user, allowing the user to use this sentence directly to communicate appropriately.

[0212] Through these steps, a system will be created that enables smooth and efficient communication by quickly and appropriately responding to technical issues and business questions that arise within the factory.

[0213] 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.

[0214] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. It also generates appropriate sentences based on the content of the inquiry and presents them to the user.

[0215] Collecting internal data and creating a database

[0216] server

[0217] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing this information and storing it in a database, detailed information on all employees can be managed systematically.

[0218] Receiving and analyzing inquiries from users

[0219] User

[0220] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0221] Terminal

[0222] The terminal transmits the inquiry entered by the user to the server.

[0223] server

[0224] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[0225] Recommending the best person

[0226] server

[0227] The server searches the database to find people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0228] It also uses an emotion engine to analyze the user's emotions and adjust the recommendations to match them with the most suitable person, for example, if the user is feeling very anxious, it will recommend a particularly personable employee.

[0229] Query generation

[0230] server

[0231] The server generates a formal yet specific inquiry based on the user's inquiry. For example, it might generate a sentence like, "Hello, Employee B. I'd like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you." Furthermore, an emotion engine reflects the user's emotions and adjusts the sentence to an appropriate tone. For example, if the user is nervous, a gentler tone is added to the sentence.

[0232] Terminal

[0233] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[0234] Specific examples

[0235] For example, if a user is very concerned about the security of a new web service and wants to consult with someone, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The emotion engine then recognizes the user's anxiety and recommends employee B, who is more personable. The server then obtains employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence that takes into account the user's nervousness and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0236] In this way, by combining an emotion engine, the present invention is a system that not only finds the appropriate person and generates a query sentence, but also realizes communication that takes into consideration the user's emotions.

[0237] The processing flow will be explained below.

[0238] Step 1:

[0239] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[0240] Step 2:

[0241] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0242] Step 3:

[0243] The terminal receives the inquiry entered by the user and transmits it to the server.

[0244] Step 4:

[0245] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[0246] Step 5:

[0247] The server uses an emotion engine to recognize the user's emotions and analyzes the emotion data, for example, recognizing that the user is feeling stressed or anxious from their writing.

[0248] Step 6:

[0249] The server searches the database based on the emotion data and the inquiry content to find the number of people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0250] Step 7:

[0251] The server comprehensively evaluates candidate employees based on their technical skills, experience, friendliness, and emotional data, and recommends the most suitable candidate. The recommendation includes the employee's contact information. For example, if the user is feeling anxious, a friendly employee will be given priority.

[0252] Step 8:

[0253] The terminal receives information about the recommended people from the server and presents it to the user.

[0254] Step 9:

[0255] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0256] Step 10:

[0257] The server then adds appropriate tone and expressions to the generated query based on the user's emotional data. For example, if the user is nervous, it adds a gentle tone to the sentence.

[0258] Step 11:

[0259] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[0260] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[0261] Example 2

[0262] 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."

[0263] Current internal communication systems make it difficult for users to find the right person, and it takes a lot of time and effort to ensure smooth communication. Furthermore, systems act without considering the user's feelings, which can lead to low user satisfaction. In particular, there is a problem in that it is difficult to smoothly connect with the right person when planning a new service or making inquiries to other departments.

[0264] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0265] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiry contents and presenting them to the user, means for analyzing the user's emotions, means for adjusting the recommendation results based on the analyzed emotions, and means for generating inquiry sentences that reflect the emotions. This enables users to quickly find appropriate people and realize communication that takes the user's emotions into consideration.

[0266] A "database" is a system that centrally manages data and enables efficient search and access.

[0267] "Technical capabilities" refers to specialized technical skills and knowledge in a particular field.

[0268] "Knowledge" is a collection of information and understanding about a particular topic or field.

[0269] "Experience" refers to practical career and achievements in a particular activity or field.

[0270] "Agreeableness" is an individual characteristic that indicates ease and likeability in communicating and cooperating with others.

[0271] "User" refers to an individual who uses the System to make a specific inquiry.

[0272] An "emotion engine" is an algorithm or software that analyzes a user's emotions and understands and applies those emotions.

[0273] "Natural language processing tools" are software and algorithms used to analyze and understand natural language.

[0274] An "algorithm" is a set of procedures or computational methods for solving a particular problem.

[0275] "Inquiry content" refers to the specific questions or inquiries that users enter into the system.

[0276] A "query sentence" is a formal communication sentence generated by the system based on a user's query.

[0277] This invention is a system that finds the most appropriate person to contact when a user plans a new service or makes an inquiry to another department within the company, and ensures smooth communication. This system incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system operates by utilizing multiple hardware and software components.

[0278] First, the server collects data on employees' self-reported technical skills, knowledge, and experience, including details provided by employees through input forms. It also collects information on employee friendliness based on peer evaluations, and stores this information in a centralized database (e.g., MySQL or PostgreSQL). This allows for the systematic management of all employee details.

[0279] Next, users access a dedicated web page or application and enter their specific problem or inquiry, such as "I'd like to consult about the security of a new web service."

[0280] The device (e.g., the user's PC or smartphone) sends the query to the server, which first analyzes the query using natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords, then searches a database to identify employees with relevant skills and knowledge.

[0281] Furthermore, the server analyzes the user's emotions using an emotion engine (e.g., Hugging Face Transformers). This allows the system to adjust the recommendations accordingly, for example, if the user is feeling anxious or nervous. For example, a user who is feeling very anxious will be recommended a particularly personable employee.

[0282] The server generates an appropriate query based on the user's query and the selected person. It uses a generative AI model (e.g., OpenAI's GPT) to create specific and formal sentences, and adjusts the tone based on the analysis results of the emotion engine.

[0283] The generated query sentence is sent to the terminal and displayed to the user, who can use it to communicate quickly and accurately.

[0284] Specific examples

[0285] For example, if a user has strong concerns about the security of a new web service and wants to seek advice, the following process would take place:

[0286] 1. The user enters the following into the system's input form: "I have strong concerns about the security of a new web service. I would like to consult with you."

[0287] 2. The device sends this inquiry to the server.

[0288] 3. The server receives this information, extracts the keywords "web services," "security," and "anxiety," and searches for a suitable employee. In this case, it finds an employee who is knowledgeable about security and has a good personality.

[0289] 4. Based on the emotion engine, the server recognizes the user's "anxiety" and recommends employee B as someone who can alleviate that anxiety.

[0290] 5. The server generates a friendly inquiry such as, "Hello, Employee B. I would like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0291] 6. The terminal displays the generated text to the user, who can then use this text to start a conversation with employee B.

[0292] In this way, the system takes into consideration the user's feelings, efficiently finds the most suitable employee, and ensures smooth communication.

[0293] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0294] Step 1:

[0295] Collecting internal data and creating a database

[0296] The server collects self-reported data from employees and evaluation data from colleagues. This includes detailed information such as technical skills, knowledge, and experience provided by employees through an input form. The collected data is stored in a database (e.g., MySQL, PostgreSQL). The input is various data provided by employees, and the output is that this data is stored in the database. Specifically, the server receives data through an API and stores it in the corresponding fields in the database.

[0297] Step 2:

[0298] Receiving inquiries from users

[0299] A user accesses a dedicated web page or application and enters their inquiry. For example, they may enter specific information such as "I would like to consult about the security of a new web service." The input is the user's inquiry, and the output is the inquiry that is sent to the server. Specifically, the user enters data into an input form, and the form data is sent to the server as an HTTP request.

[0300] Step 3:

[0301] Analysis of inquiry content

[0302] The server analyzes the received query. To do this, it uses natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords from the input query. For example, a keyword such as "security" is extracted. The analyzed keywords are returned as output. Specifically, the server receives an HTTP request and uses a library with text analysis functions to extract keywords.

[0303] Step 4:

[0304] Recommending the best person

[0305] The server searches a database based on the analyzed keywords and lists employees with relevant skills and knowledge. It then uses an emotion engine (e.g., Hugging Face Transformers) to analyze the user's emotions and adjusts the recommendation results for the most suitable person taking this into account. The inputs are the analyzed keywords and the user's emotional data, and the output is a list of recommended employees. Specifically, it searches the database to list relevant employees and selects the most suitable employee based on the results of the emotion analysis.

[0306] Step 5:

[0307] Query generation

[0308] After selecting the most suitable person, the server generates an appropriate query sentence based on the user's inquiry. In this process, a generative AI model (e.g., OpenAI GPT) is used, and the tone is adjusted by also reflecting the results of the emotion engine. For example, a sentence such as "Hello, employee B. I would like to consult you about the security of our new web service. Could you assist me?" is generated. The input is the user's inquiry and information about the recommended employee, and the output is the generated query sentence. Specifically, the prompt sentence is input into the generative AI model, and the result is obtained and the tone is adjusted.

[0309] Step 6:

[0310] Suggestion of inquiry text

[0311] The terminal receives the generated query text from the server and displays it to the user. The input is the query text sent from the server, and the output is displayed on the user's terminal. Specifically, the generated text is received as an HTTP response and displayed on a web page or application.

[0312] As described above, this system achieves efficient communication that takes into consideration the user's feelings through a series of processing steps, and helps direct inquiries to the appropriate person.

[0313] (Application example 2)

[0314] 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."

[0315] The challenge is to provide a system that effectively utilizes the technical skills, knowledge, and experience of employees to achieve fast and accurate communication when designing new manufacturing processes or solving machine problems within a factory. Another important challenge is to consider the feelings of the user making an inquiry, recommend the most appropriate person, and support communication that alleviates the user's anxiety and tension.

[0316] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0317] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate text based on the inquiry content and presenting it to the user, and means for analyzing the user's emotions and adjusting the tone of the recommendation of appropriate people and the text of the inquiry based on the analysis results, thereby enabling users to communicate quickly and smoothly with appropriate personnel within the factory.

[0318] "Technical ability" refers to the ability based on technical knowledge and skills, and is an important element in carrying out business.

[0319] "Knowledge" refers to information and understanding about a particular field or specialty that enables one to make decisions and take action based on this information.

[0320] "Experience" refers to knowledge and acquired skills based on actual work or projects undertaken in the past, and indicates a person's track record and level of expertise.

[0321] "Agreeableness" refers to the ability to communicate smoothly with others and build cooperative relationships, and is an important element in forming good interpersonal relationships within an organization.

[0322] "Database creation" refers to the process of centralizing collected information and registering it in a database for systematic management.

[0323] A "user" is someone who uses the system to make inquiries or search for information.

[0324] "Inquiry content" refers to questions or inquiries that users input into the system.

[0325] "Analysis means" refers to the methods and techniques used to analyze received data or information and make sense of it.

[0326] "Recommendation" refers to presenting the best options based on specific criteria.

[0327] "Analyzing emotions" refers to the process of assessing and understanding a user's psychological state from their facial expressions and voice.

[0328] "Inquiry text" refers to formal and specific text generated based on a user's question or inquiry.

[0329] "Adjusting tone" refers to changing the way you write or express words to suit the recipient's emotions and the situation.

[0330] The present invention is implemented as a "smart factory communication assistant," a system that efficiently responds to inquiries related to designing new manufacturing processes and solving machine problems within a factory.

[0331] Server configuration and operation

[0332] The server is implemented using the following hardware and software.

[0333] Hardware: Central Processing Unit (CPU), memory, storage devices, network interfaces

[0334] Software: Database management systems (e.g., MySQL), emotion engines (e.g., EmotionEngine)

[0335] The server stores and manages data collected from the factory's robots on employees' technical skills, knowledge, experience, and friendliness in a database. For example, information such as employee A's expertise in security and his track record in the manufacturing process is managed.

[0336] Users (i.e., factory employees) can input their inquiries through the robots in the factory. For example, they can input a specific problem such as "I would like to ask about improving the efficiency of the manufacturing process." This inquiry is then sent to the server via the factory network.

[0337] The server analyzes the content of the received inquiry and identifies the "technical capabilities" and "knowledge" related to that content. For example, if the inquiry is about the "manufacturing process," it will identify employees with related expertise. It also uses an emotion engine to analyze the user's emotions. For example, if the user is feeling "anxious," it will take that emotion into consideration and recommend the most suitable person.

[0338] Based on the analysis results, the server searches the database for an appropriate person (e.g., employee B, who is knowledgeable about the manufacturing process) and presents that person's contact information to the user. At the same time, the server generates a specific and formal inquiry sentence based on the inquiry content. The emotion engine reflects the user's emotions; for example, if the user has "low self-esteem," a gentle tone of sentence is generated. The generated sentence is displayed to the user through the robot's terminal.

[0339] Specific examples

[0340] For example, if an employee in a factory is feeling very anxious and wants to consult about improving the efficiency of the manufacturing process, the user inputs this inquiry into a robot in the factory. The robot sends the inquiry to a server, which analyzes the inquiry and finds Employee B, who is knowledgeable about the manufacturing process. The emotion engine also recognizes the user's anxiety and recommends Employee B, who is more personable. The server then obtains Employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0341] Prompt Sentence Examples

[0342] Specific examples of prompt sentences to be input to the generative AI model are as follows:

[0343] For anxious users who want to consult about improving the efficiency of their manufacturing processes, recommend a person who is knowledgeable about the manufacturing process and has a friendly personality, and generate an inquiry message in an appropriate tone.

[0344] In this way, the present invention allows factory employees to quickly and smoothly communicate with the most suitable person based on technical ability, knowledge, experience, and friendliness, while also taking into consideration the user's feelings.

[0345] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0346] Step 1:

[0347] The user inputs the inquiry content by voice to the robot in the factory.

[0348] Input: The user speaks to the robot, "I would like to consult with you about improving the efficiency of our manufacturing process."

[0349] Output: The voice data is converted into text format for the terminal. This is a data processing process to understand the user's intent.

[0350] Step 2:

[0351] The terminal transmits the converted text data to the server.

[0352] Input: Inquiry in text format

[0353] Output: Text data sent to the server

[0354] The device uses voice recognition software to convert the voice data into text format and transmits it over the network to a server.

[0355] Step 3:

[0356] The server analyzes the received text data to identify related technologies and knowledge.

[0357] Input: Inquiry in text format

[0358] Output: Related technology and knowledge (e.g., "manufacturing process")

[0359] The server uses a natural language processing (NLP) model to analyze the text data and identify content related to "manufacturing processes."

[0360] Step 4:

[0361] The server uses an emotion engine to analyze the user's emotions.

[0362] Input: Inquiry in text format

[0363] Output: User's emotional state (e.g., "anxiety")

[0364] The server uses a sentiment analysis model to identify the user's emotions based on the user's text data and, if necessary, voice and facial expression data.

[0365] Step 5:

[0366] The server searches the database to identify the best person with the relevant skills and knowledge and retrieves that person's contact information.

[0367] Input: Related skills and knowledge, user's emotional state

[0368] Output: Contact information for the best person (e.g., Employee B, who is knowledgeable about the manufacturing process)

[0369] The server uses a database management system (DBMS) to search for the most suitable person who has the relevant skills and knowledge and who also corresponds to the emotional state, such as "friendliness."

[0370] Step 6:

[0371] The server generates a specific and formal query sentence based on the query content.

[0372] Input: Text inquiry, information on the best available agent, and the user's emotional state

[0373] Output: Formal query text

[0374] The server uses a generative AI model (such as GPT-3) to generate sentences with an appropriate tone based on the query content and create sentences to present to the user.

[0375] Step 7:

[0376] The terminal displays the generated query sentence to the user.

[0377] Input: Formal query text

[0378] Output: Text displayed to the user

[0379] The terminal displays the generated inquiry sentence in an easy-to-understand manner to the user, and supports the user in using the sentence to carry out appropriate communication.

[0380] This series of processing steps enables users to receive prompt and accurate support regarding the design of new manufacturing processes in factories and the resolution of machine problems.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Second embodiment]

[0385] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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."

[0397] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. Furthermore, it generates an appropriate sentence based on the content of the inquiry and presents it to the user.

[0398] Collecting internal data and creating a database

[0399] server

[0400] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues, and stores this information in a centralized database. This allows detailed information on all employees to be managed systematically.

[0401] Receiving and analyzing inquiries from users

[0402] User

[0403] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[0404] Terminal

[0405] The terminal transmits the inquiry entered by the user to the server.

[0406] server

[0407] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[0408] Recommending the best person

[0409] server

[0410] The server searches the database for employees with the specified related skills and knowledge, and recommends the most suitable person from among them based on a comprehensive evaluation of technical ability, experience, friendliness, etc. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0411] Terminal

[0412] Information about recommended people is sent from the server to the terminal and presented to the user.

[0413] Query generation

[0414] server

[0415] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0416] Terminal

[0417] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[0418] Specific examples

[0419] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The server then obtains employee B's contact information and provides that information to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0420] In this way, the present invention is a system that finds the appropriate person and generates an inquiry sentence, thereby improving the efficiency of communication and information sharing within the company and supporting the smooth execution of business operations.

[0421] The processing flow will be explained below.

[0422] Step 1:

[0423] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[0424] Step 2:

[0425] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0426] Step 3:

[0427] The terminal receives the inquiry entered by the user and transmits it to the server.

[0428] Step 4:

[0429] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[0430] Step 5:

[0431] The server searches the database to find someone with the skills and knowledge related to the inquiry. For example, it may determine that employee B, who is knowledgeable about security, is the best person to contact.

[0432] Step 6:

[0433] The server comprehensively evaluates candidate employees based on their technical skills, experience, and personality, and recommends the most suitable candidate. The recommendation includes the employee's contact information.

[0434] Step 7:

[0435] The terminal receives information about the recommended people from the server and presents it to the user.

[0436] Step 8:

[0437] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, employee B. I would like to ask you about the security of our new web service. Could you please help me?"

[0438] Step 9:

[0439] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[0440] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[0441] Example 1

[0442] 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."

[0443] When planning a new in-house service or making inquiries to other departments, it is difficult to quickly find the right person and achieve smooth communication. In addition, generating appropriate sentences based on the content of the inquiry is time-consuming, which hinders efficient information sharing.

[0444] 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.

[0445] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiries and presenting them to the user, means for analyzing the user's inquiries using a natural language processing algorithm, and means for generating formal and specific inquiry sentences using a generative AI model. This enables the appropriate person to be found quickly when planning a new service within the company or making inquiries to other departments, and enables efficient communication and information sharing.

[0446] "Database creation" is the process of systematically organizing collected data and storing it in a form that makes it easy to search and use.

[0447] "User" means an individual or group of people who use the System to make inquiries.

[0448] "Query" refers to the text of the specific problem or question that a user enters into the system.

[0449] "Analysis" refers to the process by which the system understands the content of the query it receives based on its meaning and context, using natural language processing algorithms, among other things.

[0450] The "right person" refers to the employee who is most relevant to the inquiry and has high technical skills, knowledge, experience, and a friendly personality.

[0451] "Contact Information" means information sufficient to contact the appropriate person, including, for example, an email address and telephone number.

[0452] "Text generation" is the process of automatically creating formal and specific text based on the user's query, using a generative AI model.

[0453] "Natural language processing algorithms" refer to algorithms that allow computers to understand human language and analyze its meaning, thereby extracting key keywords from the content of inquiries.

[0454] A "generative AI model" is a model that uses artificial intelligence and refers to technology for generating appropriate responses and sentences from input data.

[0455] The following system configuration and operating procedures are available as an embodiment of the present invention. This system finds the most suitable person and ensures smooth communication when planning a new service within a company or making inquiries to other departments. The system stores collected data on technical ability, knowledge, experience, and affability in a database, analyzes the content of inquiries from users, and recommends the appropriate person. Furthermore, it generates appropriate sentences based on the content of the inquiry and presents them to the user.

[0456] Collecting internal data and creating a database

[0457] server

[0458] The server collects data on self-reported technical skills, knowledge, and experience from employees. It also collects information on friendliness as assessed by colleagues, and stores this data in a centralized database. This allows detailed information on all employees to be managed systematically. Specifically, data is collected through data entry forms and evaluation systems, and is registered in the database through daily batch processing.

[0459] Receiving and analyzing inquiries from users

[0460] User

[0461] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[0462] Terminal

[0463] The terminal converts the inquiry content entered by the user into an HTTP request and sends it to the server. Specifically, when the user enters information into the text box and presses the send button, the content is sent to the server.

[0464] server

[0465] The server analyzes the content of the received inquiry and identifies the technologies and knowledge related to that content. Specifically, it uses a natural language processing (NLP) algorithm to extract keywords from the inquiry and compare them with information in the database. For example, the keyword "security" can be extracted from an inquiry such as "I would like to consult about the security of a new web service."

[0466] Recommending the best person

[0467] server

[0468] The server searches the database for employees with the identified relevant skills and knowledge, and recommends the most suitable candidate based on a comprehensive evaluation of their technical ability, experience, and personality. This process involves calculating a score for each employee using a machine learning model. For example, an employee with expertise in security would receive a score of 95 for technical ability, 90 for experience, and 80 for personality, and would be recommended as the most suitable candidate.

[0469] Terminal

[0470] The server sends the recommended person's information to the terminal and presents it to the user. For example, it will be displayed as "The best person to consult about security: Employee B."

[0471] Query generation

[0472] server

[0473] The server generates a formal and specific query based on the user's inquiry. This process uses a generative AI model. For example, it generates a sentence like, "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?"

[0474] Terminal

[0475] The generated query text is sent to the terminal and displayed to the user, who can then copy and paste it or send it as is to quickly make a query.

[0476] Specific examples

[0477] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds an employee who is knowledgeable about security. The server then obtains the employee's contact information and provides it to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0478] Prompt Sentence Examples

[0479] "Can you recommend an employee with expertise in the security measures required for our new web service?"

[0480] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0481] Step 1:

[0482] Data collection and database creation

[0483] Input: Data entered by employees regarding their technical skills, knowledge, experience, and personality.

[0484] Server: The server receives data from employees about their self-reported technical skills, knowledge, and experience through an input form, and also collects data about their friendliness through a peer rating system.

[0485] Output: A consolidated employee dataset.

[0486] (Specific operation) The server runs a daily batch process to scrape form input and evaluation data and add it to the database. For example, if an employee enters "security, 5 years experience," that information is saved in the database.

[0487] Step 2:

[0488] Receiving inquiries

[0489] Input: The specific inquiry entered by the user using the terminal.

[0490] User: The user enters the inquiry (e.g., "I would like to consult about the security of a new web service") into the text box on the terminal and presses the send button.

[0491] Terminal: The terminal receives the entered text and sends it to the server as an HTTP POST request.

[0492] Output: HTTP request containing the query.

[0493] (Specific operation) When the user enters "I would like to consult about the security of a new web service" and clicks "Submit," the device generates an HTTP request containing this content and sends it to the server.

[0494] Step 3:

[0495] Analysis of inquiry content

[0496] Input: An HTTP request containing the query sent from the device.

[0497] Server: The server receives the HTTP request and invokes an NLP (Natural Language Processing) engine to analyze the query. The NLP engine extracts key keywords from the query.

[0498] Output: Extracted keywords.

[0499] (Specific operation) The server receives the text "I would like to consult about the security of a new web service," and the NLP engine extracts the keyword "security."

[0500] Step 4:

[0501] Searching for relevant data and recommending the best people

[0502] Input: Keywords extracted by analysis (e.g. "security").

[0503] Server: The server searches the database for employees with skills and knowledge related to the extracted keywords. The list of employees obtained as a result of the search is scored using a machine learning model to recommend the most suitable candidate. The scoring takes into account factors such as technical ability, experience, and friendliness.

[0504] Output: Best fit information.

[0505] (Specific operation) The server generates a list of employees with skills related to "security." For example, employee B is recommended as the most suitable person with a score of 95 points for technical ability, 90 points for experience, and 80 points for per capita.

[0506] Step 5:

[0507] Presenting information to the most suitable person

[0508] Input: Recommended best person information.

[0509] Server: The server obtains the information of the recommended person and sends it to the terminal.

[0510] Terminal: The terminal receives the information of the most suitable person sent from the server and presents it to the user.

[0511] Output: The best match information presented to the user.

[0512] (Specific operation) Employee B's details are displayed in the user's browser, and the user is notified that "Employee B is the best person to consult about security issues."

[0513] Step 6:

[0514] Query generation

[0515] Input: The user's specific inquiry and the recommended best person information.

[0516] Server: The server uses a generative AI model to generate formal queries for the recommended people.

[0517] Output: The generated query text.

[0518] (Specific operation) The generative AI model generates the sentence, "Employee B, I would like to consult you about the security of a new web service. Could you assist me?"

[0519] Step 7:

[0520] Presentation of generated query sentences

[0521] Input: The generated query text.

[0522] Server: The server sends the generated query sentence to the terminal.

[0523] Terminal: The terminal receives the query text sent from the server and displays it to the user. The user uses this text to make a query.

[0524] Output: The query text presented to the user.

[0525] (Specific operation) The following message will be displayed on the user's screen: "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?" The user can quickly make an inquiry by copying and pasting this message or sending it as is.

[0526] (Application example 1)

[0527] 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."

[0528] Technical problems and business-related questions frequently arise in factories, requiring quick and appropriate responses. With conventional methods, it takes time to find someone with the appropriate technical skills and knowledge, making it difficult to solve problems efficiently. Furthermore, generating formal inquiry sentences based on the inquiry content is time-consuming, which hinders smooth communication.

[0529] 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.

[0530] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating formal inquiry sentences from the inquiry sentences using a generative model, and means for providing the generated inquiry sentences to users via display means. This enables quick and appropriate responses to technical problems and business questions that arise in the factory, enabling efficient problem solving and smooth communication.

[0531] "Collected data on technical skills, knowledge, experience, and personality" refers to information on technical skills, knowledge, and experience self-reported by employees, as well as information on personality as assessed by colleagues.

[0532] "Means for creating a database" refers to means for systematically storing and managing the above data.

[0533] "Means for receiving and analyzing inquiries from users" refers to means for receiving specific problems or inquiries entered by users and mechanically analyzing the contents of those inquiries.

[0534] "Means for recommending appropriate individuals based on the analysis results and presenting their contact information" refers to means for identifying employees with skills and knowledge related to the analyzed inquiry content and providing the user with the employee's contact information.

[0535] "Means for generating formal inquiry sentences from inquiry content using a generative model" refers to means for generating formal inquiry sentences based on the inquiry content from a user using a generative artificial intelligence model.

[0536] The "means for providing the generated query sentence to the user via the display means" refers to a means for visually presenting the generated query sentence to the user.

[0537] "Means for comprehensively evaluating technical ability, knowledge, experience, and personality" refers to a means for identifying the most suitable person by comprehensively evaluating technical ability, knowledge, experience, and personality when analyzing the content of an inquiry.

[0538] "Means for generating query sentences using prompt sentences based on a generative model" refers to means for generating formal and specific query sentences using prompt sentences provided by a generative AI model.

[0539] This invention is a system for facilitating communication by quickly and accurately responding to technical problems and business-related questions that arise in factories. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes user inquiries, and recommends appropriate personnel. It also uses a generative model to generate formal inquiry sentences from the inquiries and provides them to users.

[0540] Collecting internal data and creating a database

[0541] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing and storing this data in a database, detailed information on all employees can be managed systematically.

[0542] Receiving and analyzing inquiries from users

[0543] The user enters a specific problem or inquiry into the system through a terminal, for example, "Question about security settings on a new machine." This inquiry is then sent from the terminal to the server.

[0544] The server analyzes the content of the received inquiry, identifies the skills and knowledge related to that content, and then uses an analytical algorithm to search a database for employees with the relevant technical skills and knowledge.

[0545] Recommending the best person

[0546] The server then comprehensively evaluates the analyzed technical skills, knowledge, experience, and friendliness, and recommends the most suitable person from the database. For example, it may recommend someone who is knowledgeable about the security settings of a new machine. The recommended person's contact information is then sent to the user's device.

[0547] Query generation

[0548] The server uses a generative AI model to generate a formal query based on the user's query, such as a prompt: "Please generate a formal query based on questions about the security settings of a new machine."

[0549] The generated inquiry text will look something like this: "Hello, person in charge. I would like to ask about the security settings of a new machine. Could you please help me? I would appreciate your advice on the following points. Thank you."

[0550] The generated query sentences are presented to the user via the terminal, enabling the user to communicate appropriately and quickly.

[0551] These processes are primarily performed by a server using database management software (e.g., SQLite) and generative AI models (e.g., OpenAI GPT-3), covering a series of steps from data collection, analysis, recommendation, query generation, to final presentation.

[0552] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0553] Step 1:

[0554] The user enters specific problems or inquiries into the system through the terminal. For example, they enter "questions about security settings on a new machine." This input data is sent to the server in JSON format. In this step, it is important that the user's inquiries are entered into the terminal specifically and clearly.

[0555] Step 2:

[0556] The terminal sends the query to the server. The data sent includes the query entered by the user. The server receives the query and stores it in a database. The server then performs preprocessing to analyze the query.

[0557] Step 3:

[0558] The server analyzes the received query using a natural language processing (NLP) algorithm. The input for this analysis is the query entered by the user, and the output is generated as keywords for the identified technology or knowledge. For example, the keyword "security settings" is extracted. This step requires accurate analysis of the query.

[0559] Step 4:

[0560] The server searches the database for employees with the specified skills and knowledge. The input data are the keywords extracted in step 3, and the output data is a list of employees with the relevant technical skills, knowledge, experience, and personality. The server then executes an SQL query to find the relevant employees in the database.

[0561] Step 5:

[0562] The server recommends the most suitable candidate based on the search results. The input data is the employee list obtained in step 4, and the output data is the contact information of the recommended candidate. The server identifies the most suitable candidate using an algorithm that comprehensively evaluates technical ability, knowledge, experience, and friendliness.

[0563] Step 6:

[0564] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a formal query based on the user's query. The input data here is the user's query and information about the recommended person, and the output data is the generated query. For example, the generated query might be, "I'd like to ask about the security settings for my new machine. Could you help me with that?"

[0565] Step 7:

[0566] The server provides the generated query sentence to the user via the terminal. The input data is the query sentence generated in step 6, and the output data is the query sentence displayed on the terminal. The terminal visually presents this query sentence to the user, allowing the user to use this sentence directly to communicate appropriately.

[0567] Through these steps, a system will be created that enables smooth and efficient communication by quickly and appropriately responding to technical issues and business questions that arise within the factory.

[0568] 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.

[0569] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. It also generates appropriate sentences based on the content of the inquiry and presents them to the user.

[0570] Collecting internal data and creating a database

[0571] server

[0572] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing this information and storing it in a database, detailed information on all employees can be managed systematically.

[0573] Receiving and analyzing inquiries from users

[0574] User

[0575] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0576] Terminal

[0577] The terminal transmits the inquiry entered by the user to the server.

[0578] server

[0579] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[0580] Recommending the best person

[0581] server

[0582] The server searches the database to find people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0583] It also uses an emotion engine to analyze the user's emotions and adjust the recommendations to match them with the most suitable person, for example, if the user is feeling very anxious, it will recommend a particularly personable employee.

[0584] Query generation

[0585] server

[0586] The server generates a formal yet specific inquiry based on the user's inquiry. For example, it might generate a sentence like, "Hello, Employee B. I'd like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you." Furthermore, an emotion engine reflects the user's emotions and adjusts the sentence to an appropriate tone. For example, if the user is nervous, a gentler tone is added to the sentence.

[0587] Terminal

[0588] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[0589] Specific examples

[0590] For example, if a user is very concerned about the security of a new web service and wants to consult with someone, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The emotion engine then recognizes the user's anxiety and recommends employee B, who is more personable. The server then obtains employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence that takes into account the user's nervousness and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0591] In this way, by combining an emotion engine, the present invention is a system that not only finds the appropriate person and generates a query sentence, but also realizes communication that takes into consideration the user's emotions.

[0592] The processing flow will be explained below.

[0593] Step 1:

[0594] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[0595] Step 2:

[0596] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0597] Step 3:

[0598] The terminal receives the inquiry entered by the user and transmits it to the server.

[0599] Step 4:

[0600] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[0601] Step 5:

[0602] The server uses an emotion engine to recognize the user's emotions and analyzes the emotion data, for example, recognizing that the user is feeling stressed or anxious from their writing.

[0603] Step 6:

[0604] The server searches the database based on the emotion data and the inquiry content to find the number of people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0605] Step 7:

[0606] The server comprehensively evaluates candidate employees based on their technical skills, experience, friendliness, and emotional data, and recommends the most suitable candidate. The recommendation includes the employee's contact information. For example, if the user is feeling anxious, a friendly employee will be given priority.

[0607] Step 8:

[0608] The terminal receives information about the recommended people from the server and presents it to the user.

[0609] Step 9:

[0610] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0611] Step 10:

[0612] The server then adds appropriate tone and expressions to the generated query based on the user's emotional data. For example, if the user is nervous, it adds a gentle tone to the sentence.

[0613] Step 11:

[0614] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[0615] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[0616] Example 2

[0617] 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."

[0618] Current internal communication systems make it difficult for users to find the right person, and it takes a lot of time and effort to ensure smooth communication. Furthermore, systems act without considering the user's feelings, which can lead to low user satisfaction. In particular, there is a problem in that it is difficult to smoothly connect with the right person when planning a new service or making inquiries to other departments.

[0619] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0620] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiry contents and presenting them to the user, means for analyzing the user's emotions, means for adjusting the recommendation results based on the analyzed emotions, and means for generating inquiry sentences that reflect the emotions. This enables users to quickly find appropriate people and realize communication that takes the user's emotions into consideration.

[0621] A "database" is a system that centrally manages data and enables efficient search and access.

[0622] "Technical capabilities" refers to specialized technical skills and knowledge in a particular field.

[0623] "Knowledge" is a collection of information and understanding about a particular topic or field.

[0624] "Experience" refers to practical career and achievements in a particular activity or field.

[0625] "Agreeableness" is an individual characteristic that indicates ease and likeability in communicating and cooperating with others.

[0626] "User" refers to an individual who uses the System to make a specific inquiry.

[0627] An "emotion engine" is an algorithm or software that analyzes a user's emotions and understands and applies those emotions.

[0628] "Natural language processing tools" are software and algorithms used to analyze and understand natural language.

[0629] An "algorithm" is a set of procedures or computational methods for solving a particular problem.

[0630] "Inquiry content" refers to the specific questions or inquiries that users enter into the system.

[0631] A "query sentence" is a formal communication sentence generated by the system based on a user's query.

[0632] This invention is a system that finds the most appropriate person to contact when a user plans a new service or makes an inquiry to another department within the company, and ensures smooth communication. This system incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system operates by utilizing multiple hardware and software components.

[0633] First, the server collects data on employees' self-reported technical skills, knowledge, and experience, including details provided by employees through input forms. It also collects information on employee friendliness based on peer evaluations, and stores this information in a centralized database (e.g., MySQL or PostgreSQL). This allows for the systematic management of all employee details.

[0634] Next, users access a dedicated web page or application and enter their specific problem or inquiry, such as "I'd like to consult about the security of a new web service."

[0635] The device (e.g., the user's PC or smartphone) sends the query to the server, which first analyzes the query using natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords, then searches a database to identify employees with relevant skills and knowledge.

[0636] Furthermore, the server analyzes the user's emotions using an emotion engine (e.g., Hugging Face Transformers). This allows the system to adjust the recommendations accordingly, for example, if the user is feeling anxious or nervous. For example, a user who is feeling very anxious will be recommended a particularly personable employee.

[0637] The server generates an appropriate query based on the user's query and the selected person. It uses a generative AI model (e.g., OpenAI's GPT) to create specific and formal sentences, and adjusts the tone based on the analysis results of the emotion engine.

[0638] The generated query sentence is sent to the terminal and displayed to the user, who can use it to communicate quickly and accurately.

[0639] Specific examples

[0640] For example, if a user has strong concerns about the security of a new web service and wants to seek advice, the following process would take place:

[0641] 1. The user enters the following into the system's input form: "I have strong concerns about the security of a new web service. I would like to consult with you."

[0642] 2. The device sends this inquiry to the server.

[0643] 3. The server receives this information, extracts the keywords "web services," "security," and "anxiety," and searches for a suitable employee. In this case, it finds an employee who is knowledgeable about security and has a good personality.

[0644] 4. Based on the emotion engine, the server recognizes the user's "anxiety" and recommends employee B as someone who can alleviate that anxiety.

[0645] 5. The server generates a friendly inquiry such as, "Hello, Employee B. I would like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0646] 6. The terminal displays the generated text to the user, who can then use this text to start a conversation with employee B.

[0647] In this way, the system takes into consideration the user's feelings, efficiently finds the most suitable employee, and ensures smooth communication.

[0648] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0649] Step 1:

[0650] Collecting internal data and creating a database

[0651] The server collects self-reported data from employees and evaluation data from colleagues. This includes detailed information such as technical skills, knowledge, and experience provided by employees through an input form. The collected data is stored in a database (e.g., MySQL, PostgreSQL). The input is various data provided by employees, and the output is that this data is stored in the database. Specifically, the server receives data through an API and stores it in the corresponding fields in the database.

[0652] Step 2:

[0653] Receiving inquiries from users

[0654] A user accesses a dedicated web page or application and enters their inquiry. For example, they may enter specific information such as "I would like to consult about the security of a new web service." The input is the user's inquiry, and the output is the inquiry that is sent to the server. Specifically, the user enters data into an input form, and the form data is sent to the server as an HTTP request.

[0655] Step 3:

[0656] Analysis of inquiry content

[0657] The server analyzes the received query. To do this, it uses natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords from the input query. For example, a keyword such as "security" is extracted. The analyzed keywords are returned as output. Specifically, the server receives an HTTP request and uses a library with text analysis functions to extract keywords.

[0658] Step 4:

[0659] Recommending the best person

[0660] The server searches a database based on the analyzed keywords and lists employees with relevant skills and knowledge. It then uses an emotion engine (e.g., Hugging Face Transformers) to analyze the user's emotions and adjusts the recommendation results for the most suitable person taking this into account. The inputs are the analyzed keywords and the user's emotional data, and the output is a list of recommended employees. Specifically, it searches the database to list relevant employees and selects the most suitable employee based on the results of the emotion analysis.

[0661] Step 5:

[0662] Query generation

[0663] After selecting the most suitable person, the server generates an appropriate query sentence based on the user's inquiry. In this process, a generative AI model (e.g., OpenAI GPT) is used, and the tone is adjusted by also reflecting the results of the emotion engine. For example, a sentence such as "Hello, employee B. I would like to consult you about the security of our new web service. Could you assist me?" is generated. The input is the user's inquiry and information about the recommended employee, and the output is the generated query sentence. Specifically, the prompt sentence is input into the generative AI model, and the result is obtained and the tone is adjusted.

[0664] Step 6:

[0665] Suggestion of inquiry text

[0666] The terminal receives the generated query text from the server and displays it to the user. The input is the query text sent from the server, and the output is displayed on the user's terminal. Specifically, the generated text is received as an HTTP response and displayed on a web page or application.

[0667] As described above, this system achieves efficient communication that takes into consideration the user's feelings through a series of processing steps, and helps direct inquiries to the appropriate person.

[0668] (Application example 2)

[0669] 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."

[0670] The challenge is to provide a system that effectively utilizes the technical skills, knowledge, and experience of employees to achieve fast and accurate communication when designing new manufacturing processes or solving machine problems within a factory. Another important challenge is to consider the feelings of the user making an inquiry, recommend the most appropriate person, and support communication that alleviates the user's anxiety and tension.

[0671] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0672] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate text based on the inquiry content and presenting it to the user, and means for analyzing the user's emotions and adjusting the tone of the recommendation of appropriate people and the text of the inquiry based on the analysis results, thereby enabling users to communicate quickly and smoothly with appropriate personnel within the factory.

[0673] "Technical ability" refers to the ability based on technical knowledge and skills, and is an important element in carrying out business.

[0674] "Knowledge" refers to information and understanding about a particular field or specialty that enables one to make decisions and take action based on this information.

[0675] "Experience" refers to knowledge and acquired skills based on actual work or projects undertaken in the past, and indicates a person's track record and level of expertise.

[0676] "Agreeableness" refers to the ability to communicate smoothly with others and build cooperative relationships, and is an important element in forming good interpersonal relationships within an organization.

[0677] "Database creation" refers to the process of centralizing collected information and registering it in a database for systematic management.

[0678] A "user" is someone who uses the system to make inquiries or search for information.

[0679] "Inquiry content" refers to questions or inquiries that users input into the system.

[0680] "Analysis means" refers to the methods and techniques used to analyze received data or information and make sense of it.

[0681] "Recommendation" refers to presenting the best options based on specific criteria.

[0682] "Analyzing emotions" refers to the process of assessing and understanding a user's psychological state from their facial expressions and voice.

[0683] "Inquiry text" refers to formal and specific text generated based on a user's question or inquiry.

[0684] "Adjusting tone" refers to changing the way you write or express words to suit the recipient's emotions and the situation.

[0685] The present invention is implemented as a "smart factory communication assistant," a system that efficiently responds to inquiries related to designing new manufacturing processes and solving machine problems within a factory.

[0686] Server configuration and operation

[0687] The server is implemented using the following hardware and software.

[0688] Hardware: Central Processing Unit (CPU), memory, storage devices, network interfaces

[0689] Software: Database management systems (e.g., MySQL), emotion engines (e.g., EmotionEngine)

[0690] The server stores and manages data collected from the factory's robots on employees' technical skills, knowledge, experience, and friendliness in a database. For example, information such as employee A's expertise in security and his track record in the manufacturing process is managed.

[0691] Users (i.e., factory employees) can input their inquiries through the robots in the factory. For example, they can input a specific problem such as "I would like to ask about improving the efficiency of the manufacturing process." This inquiry is then sent to the server via the factory network.

[0692] The server analyzes the content of the received inquiry and identifies the "technical capabilities" and "knowledge" related to that content. For example, if the inquiry is about the "manufacturing process," it will identify employees with related expertise. It also uses an emotion engine to analyze the user's emotions. For example, if the user is feeling "anxious," it will take that emotion into consideration and recommend the most suitable person.

[0693] Based on the analysis results, the server searches the database for an appropriate person (e.g., employee B, who is knowledgeable about the manufacturing process) and presents that person's contact information to the user. At the same time, the server generates a specific and formal inquiry sentence based on the inquiry content. The emotion engine reflects the user's emotions; for example, if the user has "low self-esteem," a gentle tone of sentence is generated. The generated sentence is displayed to the user through the robot's terminal.

[0694] Specific examples

[0695] For example, if an employee in a factory is feeling very anxious and wants to consult about improving the efficiency of the manufacturing process, the user inputs this inquiry into a robot in the factory. The robot sends the inquiry to a server, which analyzes the inquiry and finds Employee B, who is knowledgeable about the manufacturing process. The emotion engine also recognizes the user's anxiety and recommends Employee B, who is more personable. The server then obtains Employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0696] Prompt Sentence Examples

[0697] Specific examples of prompt sentences to be input to the generative AI model are as follows:

[0698] For anxious users who want to consult about improving the efficiency of their manufacturing processes, recommend a person who is knowledgeable about the manufacturing process and has a friendly personality, and generate an inquiry message in an appropriate tone.

[0699] In this way, the present invention allows factory employees to quickly and smoothly communicate with the most suitable person based on technical ability, knowledge, experience, and friendliness, while also taking into consideration the user's feelings.

[0700] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0701] Step 1:

[0702] The user inputs the inquiry content by voice to the robot in the factory.

[0703] Input: The user speaks to the robot, "I would like to consult with you about improving the efficiency of our manufacturing process."

[0704] Output: The voice data is converted into text format for the terminal. This is a data processing process to understand the user's intent.

[0705] Step 2:

[0706] The terminal transmits the converted text data to the server.

[0707] Input: Inquiry in text format

[0708] Output: Text data sent to the server

[0709] The device uses voice recognition software to convert the voice data into text format and transmits it over the network to a server.

[0710] Step 3:

[0711] The server analyzes the received text data to identify related technologies and knowledge.

[0712] Input: Inquiry in text format

[0713] Output: Related technology and knowledge (e.g., "manufacturing process")

[0714] The server uses a natural language processing (NLP) model to analyze the text data and identify content related to "manufacturing processes."

[0715] Step 4:

[0716] The server uses an emotion engine to analyze the user's emotions.

[0717] Input: Inquiry in text format

[0718] Output: User's emotional state (e.g., "anxiety")

[0719] The server uses a sentiment analysis model to identify the user's emotions based on the user's text data and, if necessary, voice and facial expression data.

[0720] Step 5:

[0721] The server searches the database to identify the best person with the relevant skills and knowledge and retrieves that person's contact information.

[0722] Input: Related skills and knowledge, user's emotional state

[0723] Output: Contact information for the best person (e.g., Employee B, who is knowledgeable about the manufacturing process)

[0724] The server uses a database management system (DBMS) to search for the most suitable person who has the relevant skills and knowledge and who also corresponds to the emotional state, such as "friendliness."

[0725] Step 6:

[0726] The server generates a specific and formal query sentence based on the query content.

[0727] Input: Text inquiry, information on the best available agent, and the user's emotional state

[0728] Output: Formal query text

[0729] The server uses a generative AI model (such as GPT-3) to generate sentences with an appropriate tone based on the query content and create sentences to present to the user.

[0730] Step 7:

[0731] The terminal displays the generated query sentence to the user.

[0732] Input: Formal query text

[0733] Output: Text displayed to the user

[0734] The terminal displays the generated inquiry sentence in an easy-to-understand manner to the user, and supports the user in using the sentence to carry out appropriate communication.

[0735] This series of processing steps enables users to receive prompt and accurate support regarding the design of new manufacturing processes in factories and the resolution of machine problems.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] [Third embodiment]

[0740] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0741] 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.

[0742] 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).

[0743] 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.

[0744] 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.

[0745] 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).

[0746] 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.

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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."

[0752] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. Furthermore, it generates an appropriate sentence based on the content of the inquiry and presents it to the user.

[0753] Collecting internal data and creating a database

[0754] server

[0755] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues, and stores this information in a centralized database. This allows detailed information on all employees to be managed systematically.

[0756] Receiving and analyzing inquiries from users

[0757] User

[0758] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[0759] Terminal

[0760] The terminal transmits the inquiry entered by the user to the server.

[0761] server

[0762] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[0763] Recommending the best person

[0764] server

[0765] The server searches the database for employees with the specified related skills and knowledge, and recommends the most suitable person from among them based on a comprehensive evaluation of technical ability, experience, friendliness, etc. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0766] Terminal

[0767] Information about recommended people is sent from the server to the terminal and presented to the user.

[0768] Query generation

[0769] server

[0770] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0771] Terminal

[0772] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[0773] Specific examples

[0774] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The server then obtains employee B's contact information and provides that information to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0775] In this way, the present invention is a system that finds the appropriate person and generates an inquiry sentence, thereby improving the efficiency of communication and information sharing within the company and supporting the smooth execution of business operations.

[0776] The processing flow will be explained below.

[0777] Step 1:

[0778] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[0779] Step 2:

[0780] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0781] Step 3:

[0782] The terminal receives the inquiry entered by the user and transmits it to the server.

[0783] Step 4:

[0784] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[0785] Step 5:

[0786] The server searches the database to find someone with the skills and knowledge related to the inquiry. For example, it may determine that employee B, who is knowledgeable about security, is the best person to contact.

[0787] Step 6:

[0788] The server comprehensively evaluates candidate employees based on their technical skills, experience, and personality, and recommends the most suitable candidate. The recommendation includes the employee's contact information.

[0789] Step 7:

[0790] The terminal receives information about the recommended people from the server and presents it to the user.

[0791] Step 8:

[0792] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, employee B. I would like to ask you about the security of our new web service. Could you please help me?"

[0793] Step 9:

[0794] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[0795] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[0796] Example 1

[0797] 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."

[0798] When planning a new in-house service or making inquiries to other departments, it is difficult to quickly find the right person and achieve smooth communication. In addition, generating appropriate sentences based on the content of the inquiry is time-consuming, which hinders efficient information sharing.

[0799] 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.

[0800] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiries and presenting them to the user, means for analyzing the user's inquiries using a natural language processing algorithm, and means for generating formal and specific inquiry sentences using a generative AI model. This enables the appropriate person to be found quickly when planning a new service within the company or making inquiries to other departments, and enables efficient communication and information sharing.

[0801] "Database creation" is the process of systematically organizing collected data and storing it in a form that makes it easy to search and use.

[0802] "User" means an individual or group of people who use the System to make inquiries.

[0803] "Query" refers to the text of the specific problem or question that a user enters into the system.

[0804] "Analysis" refers to the process by which the system understands the content of the query it receives based on its meaning and context, using natural language processing algorithms, among other things.

[0805] The "right person" refers to the employee who is most relevant to the inquiry and has high technical skills, knowledge, experience, and a friendly personality.

[0806] "Contact Information" means information sufficient to contact the appropriate person, including, for example, an email address and telephone number.

[0807] "Text generation" is the process of automatically creating formal and specific text based on the user's query, using a generative AI model.

[0808] "Natural language processing algorithms" refer to algorithms that allow computers to understand human language and analyze its meaning, thereby extracting key keywords from the content of inquiries.

[0809] A "generative AI model" is a model that uses artificial intelligence and refers to technology for generating appropriate responses and sentences from input data.

[0810] The following system configuration and operating procedures are available as an embodiment of the present invention. This system finds the most suitable person and ensures smooth communication when planning a new service within a company or making inquiries to other departments. The system stores collected data on technical ability, knowledge, experience, and affability in a database, analyzes the content of inquiries from users, and recommends the appropriate person. Furthermore, it generates appropriate sentences based on the content of the inquiry and presents them to the user.

[0811] Collecting internal data and creating a database

[0812] server

[0813] The server collects data on self-reported technical skills, knowledge, and experience from employees. It also collects information on friendliness as assessed by colleagues, and stores this data in a centralized database. This allows detailed information on all employees to be managed systematically. Specifically, data is collected through data entry forms and evaluation systems, and is registered in the database through daily batch processing.

[0814] Receiving and analyzing inquiries from users

[0815] User

[0816] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[0817] Terminal

[0818] The terminal converts the inquiry content entered by the user into an HTTP request and sends it to the server. Specifically, when the user enters information into the text box and presses the send button, the content is sent to the server.

[0819] server

[0820] The server analyzes the content of the received inquiry and identifies the technologies and knowledge related to that content. Specifically, it uses a natural language processing (NLP) algorithm to extract keywords from the inquiry and compare them with information in the database. For example, the keyword "security" can be extracted from an inquiry such as "I would like to consult about the security of a new web service."

[0821] Recommending the best person

[0822] server

[0823] The server searches the database for employees with the identified relevant skills and knowledge, and recommends the most suitable candidate based on a comprehensive evaluation of their technical ability, experience, and personality. This process involves calculating a score for each employee using a machine learning model. For example, an employee with expertise in security would receive a score of 95 for technical ability, 90 for experience, and 80 for personality, and would be recommended as the most suitable candidate.

[0824] Terminal

[0825] The server sends the recommended person's information to the terminal and presents it to the user. For example, it will be displayed as "The best person to consult about security: Employee B."

[0826] Query generation

[0827] server

[0828] The server generates a formal and specific query based on the user's inquiry. This process uses a generative AI model. For example, it generates a sentence like, "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?"

[0829] Terminal

[0830] The generated query text is sent to the terminal and displayed to the user, who can then copy and paste it or send it as is to quickly make a query.

[0831] Specific examples

[0832] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds an employee who is knowledgeable about security. The server then obtains the employee's contact information and provides it to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0833] Prompt Sentence Examples

[0834] "Can you recommend an employee with expertise in the security measures required for our new web service?"

[0835] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0836] Step 1:

[0837] Data collection and database creation

[0838] Input: Data entered by employees regarding their technical skills, knowledge, experience, and personality.

[0839] Server: The server receives data from employees about their self-reported technical skills, knowledge, and experience through an input form, and also collects data about their friendliness through a peer rating system.

[0840] Output: A consolidated employee dataset.

[0841] (Specific operation) The server runs a daily batch process to scrape form input and evaluation data and add it to the database. For example, if an employee enters "security, 5 years experience," that information is saved in the database.

[0842] Step 2:

[0843] Receiving inquiries

[0844] Input: The specific inquiry entered by the user using the terminal.

[0845] User: The user enters the inquiry (e.g., "I would like to consult about the security of a new web service") into the text box on the terminal and presses the send button.

[0846] Terminal: The terminal receives the entered text and sends it to the server as an HTTP POST request.

[0847] Output: HTTP request containing the query.

[0848] (Specific operation) When the user enters "I would like to consult about the security of a new web service" and clicks "Submit," the device generates an HTTP request containing this content and sends it to the server.

[0849] Step 3:

[0850] Analysis of inquiry content

[0851] Input: An HTTP request containing the query sent from the device.

[0852] Server: The server receives the HTTP request and invokes an NLP (Natural Language Processing) engine to analyze the query. The NLP engine extracts key keywords from the query.

[0853] Output: Extracted keywords.

[0854] (Specific operation) The server receives the text "I would like to consult about the security of a new web service," and the NLP engine extracts the keyword "security."

[0855] Step 4:

[0856] Searching for relevant data and recommending the best people

[0857] Input: Keywords extracted by analysis (e.g. "security").

[0858] Server: The server searches the database for employees with skills and knowledge related to the extracted keywords. The list of employees obtained as a result of the search is scored using a machine learning model to recommend the most suitable candidate. The scoring takes into account factors such as technical ability, experience, and friendliness.

[0859] Output: Best fit information.

[0860] (Specific operation) The server generates a list of employees with skills related to "security." For example, employee B is recommended as the most suitable person with a score of 95 points for technical ability, 90 points for experience, and 80 points for per capita.

[0861] Step 5:

[0862] Presenting information to the most suitable person

[0863] Input: Recommended best person information.

[0864] Server: The server obtains the information of the recommended person and sends it to the terminal.

[0865] Terminal: The terminal receives the information of the most suitable person sent from the server and presents it to the user.

[0866] Output: The best match information presented to the user.

[0867] (Specific operation) Employee B's details are displayed in the user's browser, and the user is notified that "Employee B is the best person to consult about security issues."

[0868] Step 6:

[0869] Query generation

[0870] Input: The user's specific inquiry and the recommended best person information.

[0871] Server: The server uses a generative AI model to generate formal queries for the recommended people.

[0872] Output: The generated query text.

[0873] (Specific operation) The generative AI model generates the sentence, "Employee B, I would like to consult you about the security of a new web service. Could you assist me?"

[0874] Step 7:

[0875] Presentation of generated query sentences

[0876] Input: The generated query text.

[0877] Server: The server sends the generated query sentence to the terminal.

[0878] Terminal: The terminal receives the query text sent from the server and displays it to the user. The user uses this text to make a query.

[0879] Output: The query text presented to the user.

[0880] (Specific operation) The following message will be displayed on the user's screen: "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?" The user can quickly make an inquiry by copying and pasting this message or sending it as is.

[0881] (Application example 1)

[0882] 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."

[0883] Technical problems and business-related questions frequently arise in factories, requiring quick and appropriate responses. With conventional methods, it takes time to find someone with the appropriate technical skills and knowledge, making it difficult to solve problems efficiently. Furthermore, generating formal inquiry sentences based on the inquiry content is time-consuming, which hinders smooth communication.

[0884] 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.

[0885] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating formal inquiry sentences from the inquiry sentences using a generative model, and means for providing the generated inquiry sentences to users via display means. This enables quick and appropriate responses to technical problems and business questions that arise in the factory, enabling efficient problem solving and smooth communication.

[0886] "Collected data on technical skills, knowledge, experience, and personality" refers to information on technical skills, knowledge, and experience self-reported by employees, as well as information on personality as assessed by colleagues.

[0887] "Means for creating a database" refers to means for systematically storing and managing the above data.

[0888] "Means for receiving and analyzing inquiries from users" refers to means for receiving specific problems or inquiries entered by users and mechanically analyzing the contents of those inquiries.

[0889] "Means for recommending appropriate individuals based on the analysis results and presenting their contact information" refers to means for identifying employees with skills and knowledge related to the analyzed inquiry content and providing the user with the employee's contact information.

[0890] "Means for generating formal inquiry sentences from inquiry content using a generative model" refers to means for generating formal inquiry sentences based on the inquiry content from a user using a generative artificial intelligence model.

[0891] The "means for providing the generated query sentence to the user via the display means" refers to a means for visually presenting the generated query sentence to the user.

[0892] "Means for comprehensively evaluating technical ability, knowledge, experience, and personality" refers to a means for identifying the most suitable person by comprehensively evaluating technical ability, knowledge, experience, and personality when analyzing the content of an inquiry.

[0893] "Means for generating query sentences using prompt sentences based on a generative model" refers to means for generating formal and specific query sentences using prompt sentences provided by a generative AI model.

[0894] This invention is a system for facilitating communication by quickly and accurately responding to technical problems and business-related questions that arise in factories. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes user inquiries, and recommends appropriate personnel. It also uses a generative model to generate formal inquiry sentences from the inquiries and provides them to users.

[0895] Collecting internal data and creating a database

[0896] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing and storing this data in a database, detailed information on all employees can be managed systematically.

[0897] Receiving and analyzing inquiries from users

[0898] The user enters a specific problem or inquiry into the system through a terminal, for example, "Question about security settings on a new machine." This inquiry is then sent from the terminal to the server.

[0899] The server analyzes the content of the received inquiry, identifies the skills and knowledge related to that content, and then uses an analytical algorithm to search a database for employees with the relevant technical skills and knowledge.

[0900] Recommending the best person

[0901] The server then comprehensively evaluates the analyzed technical skills, knowledge, experience, and friendliness, and recommends the most suitable person from the database. For example, it may recommend someone who is knowledgeable about the security settings of a new machine. The recommended person's contact information is then sent to the user's device.

[0902] Query generation

[0903] The server uses a generative AI model to generate a formal query based on the user's query, such as a prompt: "Please generate a formal query based on questions about the security settings of a new machine."

[0904] The generated inquiry text will look something like this: "Hello, person in charge. I would like to ask about the security settings of a new machine. Could you please help me? I would appreciate your advice on the following points. Thank you."

[0905] The generated query sentences are presented to the user via the terminal, enabling the user to communicate appropriately and quickly.

[0906] These processes are primarily performed by a server using database management software (e.g., SQLite) and generative AI models (e.g., OpenAI GPT-3), covering a series of steps from data collection, analysis, recommendation, query generation, to final presentation.

[0907] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0908] Step 1:

[0909] The user enters specific problems or inquiries into the system through the terminal. For example, they enter "questions about security settings on a new machine." This input data is sent to the server in JSON format. In this step, it is important that the user's inquiries are entered into the terminal specifically and clearly.

[0910] Step 2:

[0911] The terminal sends the query to the server. The data sent includes the query entered by the user. The server receives the query and stores it in a database. The server then performs preprocessing to analyze the query.

[0912] Step 3:

[0913] The server analyzes the received query using a natural language processing (NLP) algorithm. The input for this analysis is the query entered by the user, and the output is generated as keywords for the identified technology or knowledge. For example, the keyword "security settings" is extracted. This step requires accurate analysis of the query.

[0914] Step 4:

[0915] The server searches the database for employees with the specified skills and knowledge. The input data are the keywords extracted in step 3, and the output data is a list of employees with the relevant technical skills, knowledge, experience, and personality. The server then executes an SQL query to find the relevant employees in the database.

[0916] Step 5:

[0917] The server recommends the most suitable candidate based on the search results. The input data is the employee list obtained in step 4, and the output data is the contact information of the recommended candidate. The server identifies the most suitable candidate using an algorithm that comprehensively evaluates technical ability, knowledge, experience, and friendliness.

[0918] Step 6:

[0919] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a formal query based on the user's query. The input data here is the user's query and information about the recommended person, and the output data is the generated query. For example, the generated query might be, "I'd like to ask about the security settings for my new machine. Could you help me with that?"

[0920] Step 7:

[0921] The server provides the generated query sentence to the user via the terminal. The input data is the query sentence generated in step 6, and the output data is the query sentence displayed on the terminal. The terminal visually presents this query sentence to the user, allowing the user to use this sentence directly to communicate appropriately.

[0922] Through these steps, a system will be created that enables smooth and efficient communication by quickly and appropriately responding to technical issues and business questions that arise within the factory.

[0923] 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.

[0924] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. It also generates appropriate sentences based on the content of the inquiry and presents them to the user.

[0925] Collecting internal data and creating a database

[0926] server

[0927] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing this information and storing it in a database, detailed information on all employees can be managed systematically.

[0928] Receiving and analyzing inquiries from users

[0929] User

[0930] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0931] Terminal

[0932] The terminal transmits the inquiry entered by the user to the server.

[0933] server

[0934] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[0935] Recommending the best person

[0936] server

[0937] The server searches the database to find people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0938] It also uses an emotion engine to analyze the user's emotions and adjust the recommendations to match them with the most suitable person, for example, if the user is feeling very anxious, it will recommend a particularly personable employee.

[0939] Query generation

[0940] server

[0941] The server generates a formal yet specific inquiry based on the user's inquiry. For example, it might generate a sentence like, "Hello, Employee B. I'd like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you." Furthermore, an emotion engine reflects the user's emotions and adjusts the sentence to an appropriate tone. For example, if the user is nervous, a gentler tone is added to the sentence.

[0942] Terminal

[0943] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[0944] Specific examples

[0945] For example, if a user is very concerned about the security of a new web service and wants to consult with someone, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The emotion engine then recognizes the user's anxiety and recommends employee B, who is more personable. The server then obtains employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence that takes into account the user's nervousness and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[0946] In this way, by combining an emotion engine, the present invention is a system that not only finds the appropriate person and generates a query sentence, but also realizes communication that takes into consideration the user's emotions.

[0947] The processing flow will be explained below.

[0948] Step 1:

[0949] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[0950] Step 2:

[0951] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[0952] Step 3:

[0953] The terminal receives the inquiry entered by the user and transmits it to the server.

[0954] Step 4:

[0955] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[0956] Step 5:

[0957] The server uses an emotion engine to recognize the user's emotions and analyzes the emotion data, for example, recognizing that the user is feeling stressed or anxious from their writing.

[0958] Step 6:

[0959] The server searches the database based on the emotion data and the inquiry content to find the number of people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[0960] Step 7:

[0961] The server comprehensively evaluates candidate employees based on their technical skills, experience, friendliness, and emotional data, and recommends the most suitable candidate. The recommendation includes the employee's contact information. For example, if the user is feeling anxious, a friendly employee will be given priority.

[0962] Step 8:

[0963] The terminal receives information about the recommended people from the server and presents it to the user.

[0964] Step 9:

[0965] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[0966] Step 10:

[0967] The server then adds appropriate tone and expressions to the generated query based on the user's emotional data. For example, if the user is nervous, it adds a gentle tone to the sentence.

[0968] Step 11:

[0969] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[0970] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[0971] Example 2

[0972] 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."

[0973] Current internal communication systems make it difficult for users to find the right person, and it takes a lot of time and effort to ensure smooth communication. Furthermore, systems act without considering the user's feelings, which can lead to low user satisfaction. In particular, there is a problem in that it is difficult to smoothly connect with the right person when planning a new service or making inquiries to other departments.

[0974] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0975] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiry contents and presenting them to the user, means for analyzing the user's emotions, means for adjusting the recommendation results based on the analyzed emotions, and means for generating inquiry sentences that reflect the emotions. This enables users to quickly find appropriate people and realize communication that takes the user's emotions into consideration.

[0976] A "database" is a system that centrally manages data and enables efficient search and access.

[0977] "Technical capabilities" refers to specialized technical skills and knowledge in a particular field.

[0978] "Knowledge" is a collection of information and understanding about a particular topic or field.

[0979] "Experience" refers to practical career and achievements in a particular activity or field.

[0980] "Agreeableness" is an individual characteristic that indicates ease and likeability in communicating and cooperating with others.

[0981] "User" refers to an individual who uses the System to make a specific inquiry.

[0982] An "emotion engine" is an algorithm or software that analyzes a user's emotions and understands and applies those emotions.

[0983] "Natural language processing tools" are software and algorithms used to analyze and understand natural language.

[0984] An "algorithm" is a set of procedures or computational methods for solving a particular problem.

[0985] "Inquiry content" refers to the specific questions or inquiries that users enter into the system.

[0986] A "query sentence" is a formal communication sentence generated by the system based on a user's query.

[0987] This invention is a system that finds the most appropriate person to contact when a user plans a new service or makes an inquiry to another department within the company, and ensures smooth communication. This system incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system operates by utilizing multiple hardware and software components.

[0988] First, the server collects data on employees' self-reported technical skills, knowledge, and experience, including details provided by employees through input forms. It also collects information on employee friendliness based on peer evaluations, and stores this information in a centralized database (e.g., MySQL or PostgreSQL). This allows for the systematic management of all employee details.

[0989] Next, users access a dedicated web page or application and enter their specific problem or inquiry, such as "I'd like to consult about the security of a new web service."

[0990] The device (e.g., the user's PC or smartphone) sends the query to the server, which first analyzes the query using natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords, then searches a database to identify employees with relevant skills and knowledge.

[0991] Furthermore, the server analyzes the user's emotions using an emotion engine (e.g., Hugging Face Transformers). This allows the system to adjust the recommendations accordingly, for example, if the user is feeling anxious or nervous. For example, a user who is feeling very anxious will be recommended a particularly personable employee.

[0992] The server generates an appropriate query based on the user's query and the selected person. It uses a generative AI model (e.g., OpenAI's GPT) to create specific and formal sentences, and adjusts the tone based on the analysis results of the emotion engine.

[0993] The generated query sentence is sent to the terminal and displayed to the user, who can use it to communicate quickly and accurately.

[0994] Specific examples

[0995] For example, if a user has strong concerns about the security of a new web service and wants to seek advice, the following process would take place:

[0996] 1. The user enters the following into the system's input form: "I have strong concerns about the security of a new web service. I would like to consult with you."

[0997] 2. The device sends this inquiry to the server.

[0998] 3. The server receives this information, extracts the keywords "web services," "security," and "anxiety," and searches for a suitable employee. In this case, it finds an employee who is knowledgeable about security and has a good personality.

[0999] 4. Based on the emotion engine, the server recognizes the user's "anxiety" and recommends employee B as someone who can alleviate that anxiety.

[1000] 5. The server generates a friendly inquiry such as, "Hello, Employee B. I would like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[1001] 6. The terminal displays the generated text to the user, who can then use this text to start a conversation with employee B.

[1002] In this way, the system takes into consideration the user's feelings, efficiently finds the most suitable employee, and ensures smooth communication.

[1003] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1004] Step 1:

[1005] Collecting internal data and creating a database

[1006] The server collects self-reported data from employees and evaluation data from colleagues. This includes detailed information such as technical skills, knowledge, and experience provided by employees through an input form. The collected data is stored in a database (e.g., MySQL, PostgreSQL). The input is various data provided by employees, and the output is that this data is stored in the database. Specifically, the server receives data through an API and stores it in the corresponding fields in the database.

[1007] Step 2:

[1008] Receiving inquiries from users

[1009] A user accesses a dedicated web page or application and enters their inquiry. For example, they may enter specific information such as "I would like to consult about the security of a new web service." The input is the user's inquiry, and the output is the inquiry that is sent to the server. Specifically, the user enters data into an input form, and the form data is sent to the server as an HTTP request.

[1010] Step 3:

[1011] Analysis of inquiry content

[1012] The server analyzes the received query. To do this, it uses natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords from the input query. For example, a keyword such as "security" is extracted. The analyzed keywords are returned as output. Specifically, the server receives an HTTP request and uses a library with text analysis functions to extract keywords.

[1013] Step 4:

[1014] Recommending the best person

[1015] The server searches a database based on the analyzed keywords and lists employees with relevant skills and knowledge. It then uses an emotion engine (e.g., Hugging Face Transformers) to analyze the user's emotions and adjusts the recommendation results for the most suitable person taking this into account. The inputs are the analyzed keywords and the user's emotional data, and the output is a list of recommended employees. Specifically, it searches the database to list relevant employees and selects the most suitable employee based on the results of the emotion analysis.

[1016] Step 5:

[1017] Query generation

[1018] After selecting the most suitable person, the server generates an appropriate query sentence based on the user's inquiry. In this process, a generative AI model (e.g., OpenAI GPT) is used, and the tone is adjusted by also reflecting the results of the emotion engine. For example, a sentence such as "Hello, employee B. I would like to consult you about the security of our new web service. Could you assist me?" is generated. The input is the user's inquiry and information about the recommended employee, and the output is the generated query sentence. Specifically, the prompt sentence is input into the generative AI model, and the result is obtained and the tone is adjusted.

[1019] Step 6:

[1020] Suggestion of inquiry text

[1021] The terminal receives the generated query text from the server and displays it to the user. The input is the query text sent from the server, and the output is displayed on the user's terminal. Specifically, the generated text is received as an HTTP response and displayed on a web page or application.

[1022] As described above, this system achieves efficient communication that takes into consideration the user's feelings through a series of processing steps, and helps direct inquiries to the appropriate person.

[1023] (Application example 2)

[1024] 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."

[1025] The challenge is to provide a system that effectively utilizes the technical skills, knowledge, and experience of employees to achieve fast and accurate communication when designing new manufacturing processes or solving machine problems within a factory. Another important challenge is to consider the feelings of the user making an inquiry, recommend the most appropriate person, and support communication that alleviates the user's anxiety and tension.

[1026] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1027] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate text based on the inquiry content and presenting it to the user, and means for analyzing the user's emotions and adjusting the tone of the recommendation of appropriate people and the text of the inquiry based on the analysis results, thereby enabling users to communicate quickly and smoothly with appropriate personnel within the factory.

[1028] "Technical ability" refers to the ability based on technical knowledge and skills, and is an important element in carrying out business.

[1029] "Knowledge" refers to information and understanding about a particular field or specialty that enables one to make decisions and take action based on this information.

[1030] "Experience" refers to knowledge and acquired skills based on actual work or projects undertaken in the past, and indicates a person's track record and level of expertise.

[1031] "Agreeableness" refers to the ability to communicate smoothly with others and build cooperative relationships, and is an important element in forming good interpersonal relationships within an organization.

[1032] "Database creation" refers to the process of centralizing collected information and registering it in a database for systematic management.

[1033] A "user" is someone who uses the system to make inquiries or search for information.

[1034] "Inquiry content" refers to questions or inquiries that users input into the system.

[1035] "Analysis means" refers to the methods and techniques used to analyze received data or information and make sense of it.

[1036] "Recommendation" refers to presenting the best options based on specific criteria.

[1037] "Analyzing emotions" refers to the process of assessing and understanding a user's psychological state from their facial expressions and voice.

[1038] "Inquiry text" refers to formal and specific text generated based on a user's question or inquiry.

[1039] "Adjusting tone" refers to changing the way you write or express words to suit the recipient's emotions and the situation.

[1040] The present invention is implemented as a "smart factory communication assistant," a system that efficiently responds to inquiries related to designing new manufacturing processes and solving machine problems within a factory.

[1041] Server configuration and operation

[1042] The server is implemented using the following hardware and software.

[1043] Hardware: Central Processing Unit (CPU), memory, storage devices, network interfaces

[1044] Software: Database management systems (e.g., MySQL), emotion engines (e.g., EmotionEngine)

[1045] The server stores and manages data collected from the factory's robots on employees' technical skills, knowledge, experience, and friendliness in a database. For example, information such as employee A's expertise in security and his track record in the manufacturing process is managed.

[1046] Users (i.e., factory employees) can input their inquiries through the robots in the factory. For example, they can input a specific problem such as "I would like to ask about improving the efficiency of the manufacturing process." This inquiry is then sent to the server via the factory network.

[1047] The server analyzes the content of the received inquiry and identifies the "technical capabilities" and "knowledge" related to that content. For example, if the inquiry is about the "manufacturing process," it will identify employees with related expertise. It also uses an emotion engine to analyze the user's emotions. For example, if the user is feeling "anxious," it will take that emotion into consideration and recommend the most suitable person.

[1048] Based on the analysis results, the server searches the database for an appropriate person (e.g., employee B, who is knowledgeable about the manufacturing process) and presents that person's contact information to the user. At the same time, the server generates a specific and formal inquiry sentence based on the inquiry content. The emotion engine reflects the user's emotions; for example, if the user has "low self-esteem," a gentle tone of sentence is generated. The generated sentence is displayed to the user through the robot's terminal.

[1049] Specific examples

[1050] For example, if an employee in a factory is feeling very anxious and wants to consult about improving the efficiency of the manufacturing process, the user inputs this inquiry into a robot in the factory. The robot sends the inquiry to a server, which analyzes the inquiry and finds Employee B, who is knowledgeable about the manufacturing process. The emotion engine also recognizes the user's anxiety and recommends Employee B, who is more personable. The server then obtains Employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[1051] Prompt Sentence Examples

[1052] Specific examples of prompt sentences to be input to the generative AI model are as follows:

[1053] For anxious users who want to consult about improving the efficiency of their manufacturing processes, recommend a person who is knowledgeable about the manufacturing process and has a friendly personality, and generate an inquiry message in an appropriate tone.

[1054] In this way, the present invention allows factory employees to quickly and smoothly communicate with the most suitable person based on technical ability, knowledge, experience, and friendliness, while also taking into consideration the user's feelings.

[1055] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1056] Step 1:

[1057] The user inputs the inquiry content by voice to the robot in the factory.

[1058] Input: The user speaks to the robot, "I would like to consult with you about improving the efficiency of our manufacturing process."

[1059] Output: The voice data is converted into text format for the terminal. This is a data processing process to understand the user's intent.

[1060] Step 2:

[1061] The terminal transmits the converted text data to the server.

[1062] Input: Inquiry in text format

[1063] Output: Text data sent to the server

[1064] The device uses voice recognition software to convert the voice data into text format and transmits it over the network to a server.

[1065] Step 3:

[1066] The server analyzes the received text data to identify related technologies and knowledge.

[1067] Input: Inquiry in text format

[1068] Output: Related technology and knowledge (e.g., "manufacturing process")

[1069] The server uses a natural language processing (NLP) model to analyze the text data and identify content related to "manufacturing processes."

[1070] Step 4:

[1071] The server uses an emotion engine to analyze the user's emotions.

[1072] Input: Inquiry in text format

[1073] Output: User's emotional state (e.g., "anxiety")

[1074] The server uses a sentiment analysis model to identify the user's emotions based on the user's text data and, if necessary, voice and facial expression data.

[1075] Step 5:

[1076] The server searches the database to identify the best person with the relevant skills and knowledge and retrieves that person's contact information.

[1077] Input: Related skills and knowledge, user's emotional state

[1078] Output: Contact information for the best person (e.g., Employee B, who is knowledgeable about the manufacturing process)

[1079] The server uses a database management system (DBMS) to search for the most suitable person who has the relevant skills and knowledge and who also corresponds to the emotional state, such as "friendliness."

[1080] Step 6:

[1081] The server generates a specific and formal query sentence based on the query content.

[1082] Input: Text inquiry, information on the best available agent, and the user's emotional state

[1083] Output: Formal query text

[1084] The server uses a generative AI model (such as GPT-3) to generate sentences with an appropriate tone based on the query content and create sentences to present to the user.

[1085] Step 7:

[1086] The terminal displays the generated query sentence to the user.

[1087] Input: Formal query text

[1088] Output: Text displayed to the user

[1089] The terminal displays the generated inquiry sentence in an easy-to-understand manner to the user, and supports the user in using the sentence to carry out appropriate communication.

[1090] This series of processing steps enables users to receive prompt and accurate support regarding the design of new manufacturing processes in factories and the resolution of machine problems.

[1091] 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.

[1092] 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.

[1093] 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.

[1094] [Fourth embodiment]

[1095] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1096] 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.

[1097] 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).

[1098] 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.

[1099] 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.

[1100] 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).

[1101] 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.

[1102] 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.

[1103] 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.

[1104] 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.

[1105] 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.

[1106] 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.

[1107] 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."

[1108] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. Furthermore, it generates an appropriate sentence based on the content of the inquiry and presents it to the user.

[1109] Collecting internal data and creating a database

[1110] server

[1111] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues, and stores this information in a centralized database. This allows detailed information on all employees to be managed systematically.

[1112] Receiving and analyzing inquiries from users

[1113] User

[1114] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[1115] Terminal

[1116] The terminal transmits the inquiry entered by the user to the server.

[1117] server

[1118] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[1119] Recommending the best person

[1120] server

[1121] The server searches the database for employees with the specified related skills and knowledge, and recommends the most suitable person from among them based on a comprehensive evaluation of technical ability, experience, friendliness, etc. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[1122] Terminal

[1123] Information about recommended people is sent from the server to the terminal and presented to the user.

[1124] Query generation

[1125] server

[1126] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[1127] Terminal

[1128] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[1129] Specific examples

[1130] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The server then obtains employee B's contact information and provides that information to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[1131] In this way, the present invention is a system that finds the appropriate person and generates an inquiry sentence, thereby improving the efficiency of communication and information sharing within the company and supporting the smooth execution of business operations.

[1132] The processing flow will be explained below.

[1133] Step 1:

[1134] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[1135] Step 2:

[1136] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[1137] Step 3:

[1138] The terminal receives the inquiry entered by the user and transmits it to the server.

[1139] Step 4:

[1140] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[1141] Step 5:

[1142] The server searches the database to find someone with the skills and knowledge related to the inquiry. For example, it may determine that employee B, who is knowledgeable about security, is the best person to contact.

[1143] Step 6:

[1144] The server comprehensively evaluates candidate employees based on their technical skills, experience, and personality, and recommends the most suitable candidate. The recommendation includes the employee's contact information.

[1145] Step 7:

[1146] The terminal receives information about the recommended people from the server and presents it to the user.

[1147] Step 8:

[1148] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, employee B. I would like to ask you about the security of our new web service. Could you please help me?"

[1149] Step 9:

[1150] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[1151] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[1152] Example 1

[1153] 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."

[1154] When planning a new in-house service or making inquiries to other departments, it is difficult to quickly find the right person and achieve smooth communication. In addition, generating appropriate sentences based on the content of the inquiry is time-consuming, which hinders efficient information sharing.

[1155] 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.

[1156] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiries and presenting them to the user, means for analyzing the user's inquiries using a natural language processing algorithm, and means for generating formal and specific inquiry sentences using a generative AI model. This enables the appropriate person to be found quickly when planning a new service within the company or making inquiries to other departments, and enables efficient communication and information sharing.

[1157] "Database creation" is the process of systematically organizing collected data and storing it in a form that makes it easy to search and use.

[1158] "User" means an individual or group of people who use the System to make inquiries.

[1159] "Query" refers to the text of the specific problem or question that a user enters into the system.

[1160] "Analysis" refers to the process by which the system understands the content of the query it receives based on its meaning and context, using natural language processing algorithms, among other things.

[1161] The "right person" refers to the employee who is most relevant to the inquiry and has high technical skills, knowledge, experience, and a friendly personality.

[1162] "Contact Information" means information sufficient to contact the appropriate person, including, for example, an email address and telephone number.

[1163] "Text generation" is the process of automatically creating formal and specific text based on the user's query, using a generative AI model.

[1164] "Natural language processing algorithms" refer to algorithms that allow computers to understand human language and analyze its meaning, thereby extracting key keywords from the content of inquiries.

[1165] A "generative AI model" is a model that uses artificial intelligence and refers to technology for generating appropriate responses and sentences from input data.

[1166] The following system configuration and operating procedures are available as an embodiment of the present invention. This system finds the most suitable person and ensures smooth communication when planning a new service within a company or making inquiries to other departments. The system stores collected data on technical ability, knowledge, experience, and affability in a database, analyzes the content of inquiries from users, and recommends the appropriate person. Furthermore, it generates appropriate sentences based on the content of the inquiry and presents them to the user.

[1167] Collecting internal data and creating a database

[1168] server

[1169] The server collects data on self-reported technical skills, knowledge, and experience from employees. It also collects information on friendliness as assessed by colleagues, and stores this data in a centralized database. This allows detailed information on all employees to be managed systematically. Specifically, data is collected through data entry forms and evaluation systems, and is registered in the database through daily batch processing.

[1170] Receiving and analyzing inquiries from users

[1171] User

[1172] Users enter specific problems or inquiries into the system via their terminal, such as "I'd like to ask about the security of a new web service."

[1173] Terminal

[1174] The terminal converts the inquiry content entered by the user into an HTTP request and sends it to the server. Specifically, when the user enters information into the text box and presses the send button, the content is sent to the server.

[1175] server

[1176] The server analyzes the content of the received inquiry and identifies the technologies and knowledge related to that content. Specifically, it uses a natural language processing (NLP) algorithm to extract keywords from the inquiry and compare them with information in the database. For example, the keyword "security" can be extracted from an inquiry such as "I would like to consult about the security of a new web service."

[1177] Recommending the best person

[1178] server

[1179] The server searches the database for employees with the identified relevant skills and knowledge, and recommends the most suitable candidate based on a comprehensive evaluation of their technical ability, experience, and personality. This process involves calculating a score for each employee using a machine learning model. For example, an employee with expertise in security would receive a score of 95 for technical ability, 90 for experience, and 80 for personality, and would be recommended as the most suitable candidate.

[1180] Terminal

[1181] The server sends the recommended person's information to the terminal and presents it to the user. For example, it will be displayed as "The best person to consult about security: Employee B."

[1182] Query generation

[1183] server

[1184] The server generates a formal and specific query based on the user's inquiry. This process uses a generative AI model. For example, it generates a sentence like, "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?"

[1185] Terminal

[1186] The generated query text is sent to the terminal and displayed to the user, who can then copy and paste it or send it as is to quickly make a query.

[1187] Specific examples

[1188] For example, if a user wants to consult about the security of a new web service, they first access the system and enter their inquiry. The server analyzes the inquiry and finds an employee who is knowledgeable about security. The server then obtains the employee's contact information and provides it to the user. The server also generates a formal inquiry sentence based on the inquiry and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[1189] Prompt Sentence Examples

[1190] "Can you recommend an employee with expertise in the security measures required for our new web service?"

[1191] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1192] Step 1:

[1193] Data collection and database creation

[1194] Input: Data entered by employees regarding their technical skills, knowledge, experience, and personality.

[1195] Server: The server receives data from employees about their self-reported technical skills, knowledge, and experience through an input form, and also collects data about their friendliness through a peer rating system.

[1196] Output: A consolidated employee dataset.

[1197] (Specific operation) The server runs a daily batch process to scrape form input and evaluation data and add it to the database. For example, if an employee enters "security, 5 years experience," that information is saved in the database.

[1198] Step 2:

[1199] Receiving inquiries

[1200] Input: The specific inquiry entered by the user using the terminal.

[1201] User: The user enters the inquiry (e.g., "I would like to consult about the security of a new web service") into the text box on the terminal and presses the send button.

[1202] Terminal: The terminal receives the entered text and sends it to the server as an HTTP POST request.

[1203] Output: HTTP request containing the query.

[1204] (Specific operation) When the user enters "I would like to consult about the security of a new web service" and clicks "Submit," the device generates an HTTP request containing this content and sends it to the server.

[1205] Step 3:

[1206] Analysis of inquiry content

[1207] Input: An HTTP request containing the query sent from the device.

[1208] Server: The server receives the HTTP request and invokes an NLP (Natural Language Processing) engine to analyze the query. The NLP engine extracts key keywords from the query.

[1209] Output: Extracted keywords.

[1210] (Specific operation) The server receives the text "I would like to consult about the security of a new web service," and the NLP engine extracts the keyword "security."

[1211] Step 4:

[1212] Searching for relevant data and recommending the best people

[1213] Input: Keywords extracted by analysis (e.g. "security").

[1214] Server: The server searches the database for employees with skills and knowledge related to the extracted keywords. The list of employees obtained as a result of the search is scored using a machine learning model to recommend the most suitable candidate. The scoring takes into account factors such as technical ability, experience, and friendliness.

[1215] Output: Best fit information.

[1216] (Specific operation) The server generates a list of employees with skills related to "security." For example, employee B is recommended as the most suitable person with a score of 95 points for technical ability, 90 points for experience, and 80 points for per capita.

[1217] Step 5:

[1218] Presenting information to the most suitable person

[1219] Input: Recommended best person information.

[1220] Server: The server obtains the information of the recommended person and sends it to the terminal.

[1221] Terminal: The terminal receives the information of the most suitable person sent from the server and presents it to the user.

[1222] Output: The best match information presented to the user.

[1223] (Specific operation) Employee B's details are displayed in the user's browser, and the user is notified that "Employee B is the best person to consult about security issues."

[1224] Step 6:

[1225] Query generation

[1226] Input: The user's specific inquiry and the recommended best person information.

[1227] Server: The server uses a generative AI model to generate formal queries for the recommended people.

[1228] Output: The generated query text.

[1229] (Specific operation) The generative AI model generates the sentence, "Employee B, I would like to consult you about the security of a new web service. Could you assist me?"

[1230] Step 7:

[1231] Presentation of generated query sentences

[1232] Input: The generated query text.

[1233] Server: The server sends the generated query sentence to the terminal.

[1234] Terminal: The terminal receives the query text sent from the server and displays it to the user. The user uses this text to make a query.

[1235] Output: The query text presented to the user.

[1236] (Specific operation) The following message will be displayed on the user's screen: "Employee B, I would like to consult you about the security of a new web service. Could you please assist me?" The user can quickly make an inquiry by copying and pasting this message or sending it as is.

[1237] (Application example 1)

[1238] 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."

[1239] Technical problems and business-related questions frequently arise in factories, requiring quick and appropriate responses. With conventional methods, it takes time to find someone with the appropriate technical skills and knowledge, making it difficult to solve problems efficiently. Furthermore, generating formal inquiry sentences based on the inquiry content is time-consuming, which hinders smooth communication.

[1240] 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.

[1241] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating formal inquiry sentences from the inquiry sentences using a generative model, and means for providing the generated inquiry sentences to users via display means. This enables quick and appropriate responses to technical problems and business questions that arise in the factory, enabling efficient problem solving and smooth communication.

[1242] "Collected data on technical skills, knowledge, experience, and personality" refers to information on technical skills, knowledge, and experience self-reported by employees, as well as information on personality as assessed by colleagues.

[1243] "Means for creating a database" refers to means for systematically storing and managing the above data.

[1244] "Means for receiving and analyzing inquiries from users" refers to means for receiving specific problems or inquiries entered by users and mechanically analyzing the contents of those inquiries.

[1245] "Means for recommending appropriate individuals based on the analysis results and presenting their contact information" refers to means for identifying employees with skills and knowledge related to the analyzed inquiry content and providing the user with the employee's contact information.

[1246] "Means for generating formal inquiry sentences from inquiry content using a generative model" refers to means for generating formal inquiry sentences based on the inquiry content from a user using a generative artificial intelligence model.

[1247] The "means for providing the generated query sentence to the user via the display means" refers to a means for visually presenting the generated query sentence to the user.

[1248] "Means for comprehensively evaluating technical ability, knowledge, experience, and personality" refers to a means for identifying the most suitable person by comprehensively evaluating technical ability, knowledge, experience, and personality when analyzing the content of an inquiry.

[1249] "Means for generating query sentences using prompt sentences based on a generative model" refers to means for generating formal and specific query sentences using prompt sentences provided by a generative AI model.

[1250] This invention is a system for facilitating communication by quickly and accurately responding to technical problems and business-related questions that arise in factories. The system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes user inquiries, and recommends appropriate personnel. It also uses a generative model to generate formal inquiry sentences from the inquiries and provides them to users.

[1251] Collecting internal data and creating a database

[1252] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing and storing this data in a database, detailed information on all employees can be managed systematically.

[1253] Receiving and analyzing inquiries from users

[1254] The user enters a specific problem or inquiry into the system through a terminal, for example, "Question about security settings on a new machine." This inquiry is then sent from the terminal to the server.

[1255] The server analyzes the content of the received inquiry, identifies the skills and knowledge related to that content, and then uses an analytical algorithm to search a database for employees with the relevant technical skills and knowledge.

[1256] Recommending the best person

[1257] The server then comprehensively evaluates the analyzed technical skills, knowledge, experience, and friendliness, and recommends the most suitable person from the database. For example, it may recommend someone who is knowledgeable about the security settings of a new machine. The recommended person's contact information is then sent to the user's device.

[1258] Query generation

[1259] The server uses a generative AI model to generate a formal query based on the user's query, such as a prompt: "Please generate a formal query based on questions about the security settings of a new machine."

[1260] The generated inquiry text will look something like this: "Hello, person in charge. I would like to ask about the security settings of a new machine. Could you please help me? I would appreciate your advice on the following points. Thank you."

[1261] The generated query sentences are presented to the user via the terminal, enabling the user to communicate appropriately and quickly.

[1262] These processes are primarily performed by a server using database management software (e.g., SQLite) and generative AI models (e.g., OpenAI GPT-3), covering a series of steps from data collection, analysis, recommendation, query generation, to final presentation.

[1263] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1264] Step 1:

[1265] The user enters specific problems or inquiries into the system through the terminal. For example, they enter "questions about security settings on a new machine." This input data is sent to the server in JSON format. In this step, it is important that the user's inquiries are entered into the terminal specifically and clearly.

[1266] Step 2:

[1267] The terminal sends the query to the server. The data sent includes the query entered by the user. The server receives the query and stores it in a database. The server then performs preprocessing to analyze the query.

[1268] Step 3:

[1269] The server analyzes the received query using a natural language processing (NLP) algorithm. The input for this analysis is the query entered by the user, and the output is generated as keywords for the identified technology or knowledge. For example, the keyword "security settings" is extracted. This step requires accurate analysis of the query.

[1270] Step 4:

[1271] The server searches the database for employees with the specified skills and knowledge. The input data are the keywords extracted in step 3, and the output data is a list of employees with the relevant technical skills, knowledge, experience, and personality. The server then executes an SQL query to find the relevant employees in the database.

[1272] Step 5:

[1273] The server recommends the most suitable candidate based on the search results. The input data is the employee list obtained in step 4, and the output data is the contact information of the recommended candidate. The server identifies the most suitable candidate using an algorithm that comprehensively evaluates technical ability, knowledge, experience, and friendliness.

[1274] Step 6:

[1275] The server uses a generative AI model (e.g., OpenAI GPT-3) to generate a formal query based on the user's query. The input data here is the user's query and information about the recommended person, and the output data is the generated query. For example, the generated query might be, "I'd like to ask about the security settings for my new machine. Could you help me with that?"

[1276] Step 7:

[1277] The server provides the generated query sentence to the user via the terminal. The input data is the query sentence generated in step 6, and the output data is the query sentence displayed on the terminal. The terminal visually presents this query sentence to the user, allowing the user to use this sentence directly to communicate appropriately.

[1278] Through these steps, a system will be created that enables smooth and efficient communication by quickly and appropriately responding to technical issues and business questions that arise within the factory.

[1279] 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.

[1280] This invention is a system that finds the most suitable person and ensures smooth communication when a user plans a new service or makes an inquiry to another department within the company. Furthermore, this invention incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system stores collected data on technical ability, knowledge, experience, and friendliness in a database, analyzes the content of the user's inquiry, and recommends the appropriate person. It also generates appropriate sentences based on the content of the inquiry and presents them to the user.

[1281] Collecting internal data and creating a database

[1282] server

[1283] The server collects data on employees' self-reported technical skills, knowledge, and experience, as well as information on their friendliness as assessed by their colleagues. By centralizing this information and storing it in a database, detailed information on all employees can be managed systematically.

[1284] Receiving and analyzing inquiries from users

[1285] User

[1286] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[1287] Terminal

[1288] The terminal transmits the inquiry entered by the user to the server.

[1289] server

[1290] The server analyzes the received inquiry and identifies the technology and knowledge related to the inquiry. For example, if the inquiry is about security, it identifies employees with security technology and knowledge.

[1291] Recommending the best person

[1292] server

[1293] The server searches the database to find people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[1294] It also uses an emotion engine to analyze the user's emotions and adjust the recommendations to match them with the most suitable person, for example, if the user is feeling very anxious, it will recommend a particularly personable employee.

[1295] Query generation

[1296] server

[1297] The server generates a formal yet specific inquiry based on the user's inquiry. For example, it might generate a sentence like, "Hello, Employee B. I'd like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you." Furthermore, an emotion engine reflects the user's emotions and adjusts the sentence to an appropriate tone. For example, if the user is nervous, a gentler tone is added to the sentence.

[1298] Terminal

[1299] The generated inquiry sentence is sent to the terminal and displayed to the user, who can use this sentence to communicate appropriately and quickly.

[1300] Specific examples

[1301] For example, if a user is very concerned about the security of a new web service and wants to consult with someone, they first access the system and enter their inquiry. The server analyzes the inquiry and finds employee B, who is knowledgeable about security. The emotion engine then recognizes the user's anxiety and recommends employee B, who is more personable. The server then obtains employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence that takes into account the user's nervousness and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[1302] In this way, by combining an emotion engine, the present invention is a system that not only finds the appropriate person and generates a query sentence, but also realizes communication that takes into consideration the user's emotions.

[1303] The processing flow will be explained below.

[1304] Step 1:

[1305] The server collects data on employees' technical skills, knowledge, experience, and friendliness, and stores it in a database. This includes both data entered by employees themselves and evaluations from colleagues. For example, if employee A has strong technical skills in Java and is also evaluated by his colleagues as being friendly, this information will be stored in the database.

[1306] Step 2:

[1307] Users access the system and enter specific problems or inquiries, such as "I'd like to consult about the security of a new web service."

[1308] Step 3:

[1309] The terminal receives the inquiry entered by the user and transmits it to the server.

[1310] Step 4:

[1311] The server analyzes the received inquiry. Specifically, it uses natural language processing technology to identify related technologies and knowledge from the inquiry. In this example, technologies related to "security" are identified.

[1312] Step 5:

[1313] The server uses an emotion engine to recognize the user's emotions and analyzes the emotion data, for example, recognizing that the user is feeling stressed or anxious from their writing.

[1314] Step 6:

[1315] The server searches the database based on the emotion data and the inquiry content to find the number of people with the skills and knowledge related to the inquiry. For example, employee B, who is knowledgeable about security, is selected as the most suitable person.

[1316] Step 7:

[1317] The server comprehensively evaluates candidate employees based on their technical skills, experience, friendliness, and emotional data, and recommends the most suitable candidate. The recommendation includes the employee's contact information. For example, if the user is feeling anxious, a friendly employee will be given priority.

[1318] Step 8:

[1319] The terminal receives information about the recommended people from the server and presents it to the user.

[1320] Step 9:

[1321] The server generates a formal and specific inquiry based on the user's inquiry, such as "Hello, Employee B. I would like to consult you about the security of a new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[1322] Step 10:

[1323] The server then adds appropriate tone and expressions to the generated query based on the user's emotional data. For example, if the user is nervous, it adds a gentle tone to the sentence.

[1324] Step 11:

[1325] The terminal displays the generated inquiry sentence to the user, who can then use this sentence to communicate appropriately.

[1326] By explaining the specific operations for each step in detail, it becomes easier to understand how the system operates. In actual operation, these steps are executed seamlessly, enabling users to efficiently communicate with the appropriate people within the company.

[1327] Example 2

[1328] 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."

[1329] Current internal communication systems make it difficult for users to find the right person, and it takes a lot of time and effort to ensure smooth communication. Furthermore, systems act without considering the user's feelings, which can lead to low user satisfaction. In particular, there is a problem in that it is difficult to smoothly connect with the right person when planning a new service or making inquiries to other departments.

[1330] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1331] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate sentences based on the inquiry contents and presenting them to the user, means for analyzing the user's emotions, means for adjusting the recommendation results based on the analyzed emotions, and means for generating inquiry sentences that reflect the emotions. This enables users to quickly find appropriate people and realize communication that takes the user's emotions into consideration.

[1332] A "database" is a system that centrally manages data and enables efficient search and access.

[1333] "Technical capabilities" refers to specialized technical skills and knowledge in a particular field.

[1334] "Knowledge" is a collection of information and understanding about a particular topic or field.

[1335] "Experience" refers to practical career and achievements in a particular activity or field.

[1336] "Agreeableness" is an individual characteristic that indicates ease and likeability in communicating and cooperating with others.

[1337] "User" refers to an individual who uses the System to make a specific inquiry.

[1338] An "emotion engine" is an algorithm or software that analyzes a user's emotions and understands and applies those emotions.

[1339] "Natural language processing tools" are software and algorithms used to analyze and understand natural language.

[1340] An "algorithm" is a set of procedures or computational methods for solving a particular problem.

[1341] "Inquiry content" refers to the specific questions or inquiries that users enter into the system.

[1342] A "query sentence" is a formal communication sentence generated by the system based on a user's query.

[1343] This invention is a system that finds the most appropriate person to contact when a user plans a new service or makes an inquiry to another department within the company, and ensures smooth communication. This system incorporates an emotion engine that recognizes the user's emotions and reflects those emotions to facilitate smoother communication. This system operates by utilizing multiple hardware and software components.

[1344] First, the server collects data on employees' self-reported technical skills, knowledge, and experience, including details provided by employees through input forms. It also collects information on employee friendliness based on peer evaluations, and stores this information in a centralized database (e.g., MySQL or PostgreSQL). This allows for the systematic management of all employee details.

[1345] Next, users access a dedicated web page or application and enter their specific problem or inquiry, such as "I'd like to consult about the security of a new web service."

[1346] The device (e.g., the user's PC or smartphone) sends the query to the server, which first analyzes the query using natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords, then searches a database to identify employees with relevant skills and knowledge.

[1347] Furthermore, the server analyzes the user's emotions using an emotion engine (e.g., Hugging Face Transformers). This allows the system to adjust the recommendations accordingly, for example, if the user is feeling anxious or nervous. For example, a user who is feeling very anxious will be recommended a particularly personable employee.

[1348] The server generates an appropriate query based on the user's query and the selected person. It uses a generative AI model (e.g., OpenAI's GPT) to create specific and formal sentences, and adjusts the tone based on the analysis results of the emotion engine.

[1349] The generated query sentence is sent to the terminal and displayed to the user, who can use it to communicate quickly and accurately.

[1350] Specific examples

[1351] For example, if a user has strong concerns about the security of a new web service and wants to seek advice, the following process would take place:

[1352] 1. The user enters the following into the system's input form: "I have strong concerns about the security of a new web service. I would like to consult with you."

[1353] 2. The device sends this inquiry to the server.

[1354] 3. The server receives this information, extracts the keywords "web services," "security," and "anxiety," and searches for a suitable employee. In this case, it finds an employee who is knowledgeable about security and has a good personality.

[1355] 4. Based on the emotion engine, the server recognizes the user's "anxiety" and recommends employee B as someone who can alleviate that anxiety.

[1356] 5. The server generates a friendly inquiry such as, "Hello, Employee B. I would like to consult you about the security of our new web service. Could you please assist me? I would appreciate your advice on the following points. Thank you."

[1357] 6. The terminal displays the generated text to the user, who can then use this text to start a conversation with employee B.

[1358] In this way, the system takes into consideration the user's feelings, efficiently finds the most suitable employee, and ensures smooth communication.

[1359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1360] Step 1:

[1361] Collecting internal data and creating a database

[1362] The server collects self-reported data from employees and evaluation data from colleagues. This includes detailed information such as technical skills, knowledge, and experience provided by employees through an input form. The collected data is stored in a database (e.g., MySQL, PostgreSQL). The input is various data provided by employees, and the output is that this data is stored in the database. Specifically, the server receives data through an API and stores it in the corresponding fields in the database.

[1363] Step 2:

[1364] Receiving inquiries from users

[1365] A user accesses a dedicated web page or application and enters their inquiry. For example, they may enter specific information such as "I would like to consult about the security of a new web service." The input is the user's inquiry, and the output is the inquiry that is sent to the server. Specifically, the user enters data into an input form, and the form data is sent to the server as an HTTP request.

[1366] Step 3:

[1367] Analysis of inquiry content

[1368] The server analyzes the received query. To do this, it uses natural language processing tools (e.g., spaCy, NLTK) to extract important technical keywords from the input query. For example, a keyword such as "security" is extracted. The analyzed keywords are returned as output. Specifically, the server receives an HTTP request and uses a library with text analysis functions to extract keywords.

[1369] Step 4:

[1370] Recommending the best person

[1371] The server searches a database based on the analyzed keywords and lists employees with relevant skills and knowledge. It then uses an emotion engine (e.g., Hugging Face Transformers) to analyze the user's emotions and adjusts the recommendation results for the most suitable person taking this into account. The inputs are the analyzed keywords and the user's emotional data, and the output is a list of recommended employees. Specifically, it searches the database to list relevant employees and selects the most suitable employee based on the results of the emotion analysis.

[1372] Step 5:

[1373] Query generation

[1374] After selecting the most suitable person, the server generates an appropriate query sentence based on the user's inquiry. In this process, a generative AI model (e.g., OpenAI GPT) is used, and the tone is adjusted by also reflecting the results of the emotion engine. For example, a sentence such as "Hello, employee B. I would like to consult you about the security of our new web service. Could you assist me?" is generated. The input is the user's inquiry and information about the recommended employee, and the output is the generated query sentence. Specifically, the prompt sentence is input into the generative AI model, and the result is obtained and the tone is adjusted.

[1375] Step 6:

[1376] Suggestion of inquiry text

[1377] The terminal receives the generated query text from the server and displays it to the user. The input is the query text sent from the server, and the output is displayed on the user's terminal. Specifically, the generated text is received as an HTTP response and displayed on a web page or application.

[1378] As described above, this system achieves efficient communication that takes into consideration the user's feelings through a series of processing steps, and helps direct inquiries to the appropriate person.

[1379] (Application example 2)

[1380] 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."

[1381] The challenge is to provide a system that effectively utilizes the technical skills, knowledge, and experience of employees to achieve fast and accurate communication when designing new manufacturing processes or solving machine problems within a factory. Another important challenge is to consider the feelings of the user making an inquiry, recommend the most appropriate person, and support communication that alleviates the user's anxiety and tension.

[1382] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1383] In this invention, the server includes means for creating a database of collected data on technical ability, knowledge, experience, and friendliness, means for receiving and analyzing inquiries from users, means for recommending appropriate people based on the analysis results and presenting the people's contact information, means for generating appropriate text based on the inquiry content and presenting it to the user, and means for analyzing the user's emotions and adjusting the tone of the recommendation of appropriate people and the text of the inquiry based on the analysis results, thereby enabling users to communicate quickly and smoothly with appropriate personnel within the factory.

[1384] "Technical ability" refers to the ability based on technical knowledge and skills, and is an important element in carrying out business.

[1385] "Knowledge" refers to information and understanding about a particular field or specialty that enables one to make decisions and take action based on this information.

[1386] "Experience" refers to knowledge and acquired skills based on actual work or projects undertaken in the past, and indicates a person's track record and level of expertise.

[1387] "Agreeableness" refers to the ability to communicate smoothly with others and build cooperative relationships, and is an important element in forming good interpersonal relationships within an organization.

[1388] "Database creation" refers to the process of centralizing collected information and registering it in a database for systematic management.

[1389] A "user" is someone who uses the system to make inquiries or search for information.

[1390] "Inquiry content" refers to questions or inquiries that users input into the system.

[1391] "Analysis means" refers to the methods and techniques used to analyze received data or information and make sense of it.

[1392] "Recommendation" refers to presenting the best options based on specific criteria.

[1393] "Analyzing emotions" refers to the process of assessing and understanding a user's psychological state from their facial expressions and voice.

[1394] "Inquiry text" refers to formal and specific text generated based on a user's question or inquiry.

[1395] "Adjusting tone" refers to changing the way you write or express words to suit the recipient's emotions and the situation.

[1396] The present invention is implemented as a "smart factory communication assistant," a system that efficiently responds to inquiries related to designing new manufacturing processes and solving machine problems within a factory.

[1397] Server configuration and operation

[1398] The server is implemented using the following hardware and software.

[1399] Hardware: Central Processing Unit (CPU), memory, storage devices, network interfaces

[1400] Software: Database management systems (e.g., MySQL), emotion engines (e.g., EmotionEngine)

[1401] The server stores and manages data collected from the factory's robots on employees' technical skills, knowledge, experience, and friendliness in a database. For example, information such as employee A's expertise in security and his track record in the manufacturing process is managed.

[1402] Users (i.e., factory employees) can input their inquiries through the robots in the factory. For example, they can input a specific problem such as "I would like to ask about improving the efficiency of the manufacturing process." This inquiry is then sent to the server via the factory network.

[1403] The server analyzes the content of the received inquiry and identifies the "technical capabilities" and "knowledge" related to that content. For example, if the inquiry is about the "manufacturing process," it will identify employees with related expertise. It also uses an emotion engine to analyze the user's emotions. For example, if the user is feeling "anxious," it will take that emotion into consideration and recommend the most suitable person.

[1404] Based on the analysis results, the server searches the database for an appropriate person (e.g., employee B, who is knowledgeable about the manufacturing process) and presents that person's contact information to the user. At the same time, the server generates a specific and formal inquiry sentence based on the inquiry content. The emotion engine reflects the user's emotions; for example, if the user has "low self-esteem," a gentle tone of sentence is generated. The generated sentence is displayed to the user through the robot's terminal.

[1405] Specific examples

[1406] For example, if an employee in a factory is feeling very anxious and wants to consult about improving the efficiency of the manufacturing process, the user inputs this inquiry into a robot in the factory. The robot sends the inquiry to a server, which analyzes the inquiry and finds Employee B, who is knowledgeable about the manufacturing process. The emotion engine also recognizes the user's anxiety and recommends Employee B, who is more personable. The server then obtains Employee B's contact information and provides that information to the user. The server also generates a friendly inquiry sentence and presents it to the user. In this way, the user can communicate efficiently with the appropriate person.

[1407] Prompt Sentence Examples

[1408] Specific examples of prompt sentences to be input to the generative AI model are as follows:

[1409] For anxious users who want to consult about improving the efficiency of their manufacturing processes, recommend a person who is knowledgeable about the manufacturing process and has a friendly personality, and generate an inquiry message in an appropriate tone.

[1410] In this way, the present invention allows factory employees to quickly and smoothly communicate with the most suitable person based on technical ability, knowledge, experience, and friendliness, while also taking into consideration the user's feelings.

[1411] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1412] Step 1:

[1413] The user inputs the inquiry content by voice to the robot in the factory.

[1414] Input: The user speaks to the robot, "I would like to consult with you about improving the efficiency of our manufacturing process."

[1415] Output: The voice data is converted into text format for the terminal. This is a data processing process to understand the user's intent.

[1416] Step 2:

[1417] The terminal transmits the converted text data to the server.

[1418] Input: Inquiry in text format

[1419] Output: Text data sent to the server

[1420] The device uses voice recognition software to convert the voice data into text format and transmits it over the network to a server.

[1421] Step 3:

[1422] The server analyzes the received text data to identify related technologies and knowledge.

[1423] Input: Inquiry in text format

[1424] Output: Related technology and knowledge (e.g., "manufacturing process")

[1425] The server uses a natural language processing (NLP) model to analyze the text data and identify content related to "manufacturing processes."

[1426] Step 4:

[1427] The server uses an emotion engine to analyze the user's emotions.

[1428] Input: Inquiry in text format

[1429] Output: User's emotional state (e.g., "anxiety")

[1430] The server uses a sentiment analysis model to identify the user's emotions based on the user's text data and, if necessary, voice and facial expression data.

[1431] Step 5:

[1432] The server searches the database to identify the best person with the relevant skills and knowledge and retrieves that person's contact information.

[1433] Input: Related skills and knowledge, user's emotional state

[1434] Output: Contact information for the best person (e.g., Employee B, who is knowledgeable about the manufacturing process)

[1435] The server uses a database management system (DBMS) to search for the most suitable person who has the relevant skills and knowledge and who also corresponds to the emotional state, such as "friendliness."

[1436] Step 6:

[1437] The server generates a specific and formal query sentence based on the query content.

[1438] Input: Text inquiry, information on the best available agent, and the user's emotional state

[1439] Output: Formal query text

[1440] The server uses a generative AI model (such as GPT-3) to generate sentences with an appropriate tone based on the query content and create sentences to present to the user.

[1441] Step 7:

[1442] The terminal displays the generated query sentence to the user.

[1443] Input: Formal query text

[1444] Output: Text displayed to the user

[1445] The terminal displays the generated inquiry sentence in an easy-to-understand manner to the user, and supports the user in using the sentence to carry out appropriate communication.

[1446] This series of processing steps enables users to receive prompt and accurate support regarding the design of new manufacturing processes in factories and the resolution of machine problems.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] 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.

[1451] 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.

[1452] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1453] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1454] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1455] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1456] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1457] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1458] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1459] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1460] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1461] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1462] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1463] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1464] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1465] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1466] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1467] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1468] The following is further disclosed regarding the above embodiment.

[1469] (Claim 1)

[1470] A means of creating a database of collected data on technical skills, knowledge, experience, and friendliness;

[1471] A means of receiving and analyzing inquiries from users,

[1472] a means for recommending suitable individuals based on the analysis results and providing contact information for those individuals;

[1473] A means of generating appropriate text based on the inquiry content and presenting it to the user;

[1474] A system including:

[1475] (Claim 2)

[1476] A means to register information entered by employees themselves and evaluation information from colleagues in a database;

[1477] A means of comprehensively evaluating technical ability, knowledge, experience, and friendliness when analyzing inquiries,

[1478] Including algorithms that recommend the best person based on the analysis results,

[1479] 10. The system of claim 1.

[1480] (Claim 3)

[1481] A means of incorporating formal expressions and specific points when generating queries;

[1482] a display means for returning the generated query text to the user;

[1483] Including,

[1484] 10. The system of claim 1.

[1485] "Example 1"

[1486] (Claim 1)

[1487] A means of creating a database of collected data on technical skills, knowledge, experience, and friendliness;

[1488] A means of receiving and analyzing inquiries from users,

[1489] a means for recommending suitable individuals based on the analysis results and providing contact information for those individuals;

[1490] A means of generating appropriate text based on the inquiry content and presenting it to the user;

[1491] A means for analyzing the content of a user's inquiry using a natural language processing algorithm;

[1492] A means for generating formal and specific query sentences using a generative AI model; and

[1493] A system including:

[1494] (Claim 2)

[1495] A means to register information entered by employees themselves and evaluation information from colleagues in a database;

[1496] A means of comprehensively evaluating technical ability, knowledge, experience, and friendliness when analyzing inquiries,

[1497] Including algorithms that recommend the best person based on the analysis results,

[1498] 10. The system of claim 1.

[1499] (Claim 3)

[1500] A means of incorporating formal expressions and specific points when generating queries;

[1501] a display means for returning the generated query text to the user;

[1502] A means for generating query sentences using a generative AI model;

[1503] Including,

[1504] 10. The system of claim 1.

[1505] "Application Example 1"

[1506] (Claim 1)

[1507] A means of creating a database of collected data on technical skills, knowledge, experience, and friendliness;

[1508] A means of receiving and analyzing inquiries from users,

[1509] a means for recommending suitable individuals based on the analysis results and providing contact information for those individuals;

[1510] A means of generating appropriate text based on the inquiry content and presenting it to the user;

[1511] means for generating a formal query sentence from the query content using a generative model;

[1512] means for providing the generated query sentence to the user via a display means;

[1513] A system including:

[1514] (Claim 2)

[1515] A means to register information entered by employees themselves and evaluation information from colleagues in a database;

[1516] A means of comprehensively evaluating technical ability, knowledge, experience, and friendliness when analyzing inquiries,

[1517] Including algorithms that recommend the best person based on the analysis results,

[1518] including a means for providing users with contact information for people recommended based on the generative AI model;

[1519] 10. The system of claim 1.

[1520] (Claim 3)

[1521] A means of incorporating formal expressions and specific points when generating queries;

[1522] a display means for returning the generated query text to the user;

[1523] means for generating a query sentence using a prompt sentence based on the generative model;

[1524] Including,

[1525] 10. The system of claim 1.

[1526] "Example 2: Combining Emotion Engines"

[1527] (Claim 1)

[1528] A means of creating a database of collected data on technical skills, knowledge, experience, and friendliness;

[1529] A means of receiving and analyzing inquiries from users,

[1530] a means for recommending suitable individuals based on the analysis results and providing contact information for those individuals;

[1531] A means of generating appropriate text based on the inquiry content and presenting it to the user;

[1532] A means of analyzing user emotions,

[1533] a means for adjusting the recommendation results based on the analyzed emotions;

[1534] A means for generating query sentences that reflect emotions;

[1535] A system including:

[1536] (Claim 2)

[1537] A means to register information entered by employees themselves and evaluation information from colleagues in a database;

[1538] A means of comprehensively evaluating technical ability, knowledge, experience, and friendliness when analyzing inquiries,

[1539] Including algorithms that recommend the best person based on the analysis results,

[1540] 10. The system of claim 1.

[1541] (Claim 3)

[1542] A means of incorporating formal expressions and specific points when generating queries;

[1543] a display means for returning the generated query text to the user;

[1544] Including,

[1545] 10. The system of claim 1.

[1546] "Application example 2 when combining emotion engines"

[1547] Claiming a new invention

[1548] (Claim 1)

[1549] A means of creating a database of collected data on technical skills, knowledge, experience, and friendliness;

[1550] A means of receiving and analyzing inquiries from users,

[1551] a means for recommending suitable individuals based on the analysis results and providing contact information for those individuals;

[1552] A means of generating appropriate text based on the inquiry content and presenting it to the user;

[1553] A means for analyzing user sentiment and adjusting the tone of the appropriate person recommendation and inquiry text based on the analysis results;

[1554] A system including:

[1555] (Claim 2)

[1556] A means to register information entered by employees themselves and evaluation information from colleagues in a database;

[1557] A means of comprehensively evaluating technical ability, knowledge, experience, and friendliness when analyzing inquiries,

[1558] Includes an algorithm that recommends the most suitable person based on the analysis results and user sentiment,

[1559] 10. The system of claim 1.

[1560] (Claim 3)

[1561] A means of incorporating formal expressions and specific points when generating queries;

[1562] a display means for returning the generated query text to the user;

[1563] A means for adjusting the tone of the inquiry text based on the user's sentiment;

[1564] Including,

[1565] 10. The system of claim 1. [Explanation of symbols]

[1566] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of creating a database of collected data on technical skills, knowledge, experience, and friendliness; A means of receiving and analyzing inquiries from users, a means for recommending suitable individuals based on the analysis results and providing contact information for those individuals; A means of generating appropriate text based on the inquiry content and presenting it to the user; A system including:

2. A means to register information entered by employees themselves and evaluation information from colleagues in a database; A means of comprehensively evaluating technical ability, knowledge, experience, and friendliness when analyzing inquiries, Including algorithms that recommend the best person based on the analysis results, The system of claim 1 .

3. A means of incorporating formal expressions and specific points when generating queries; a display means for returning the generated query text to the user; Including, The system of claim 1 .

Images