System

Abstract

A system is provided.SOLUTION: This system is provided with a means for inputting the detailed requirements of a company, a means for retrieving and extracting a candidate based on the detailed requirements, a means for automatically preparing and transmitting scout mail to the candidate and a means for adjusting the schedule of an interview with the candidate who has received the scout mail.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 companies conduct recruitment activities, it is difficult to perform the scouting and interview arrangement tasks quickly and efficiently, especially for busy recruiting personnel. When recruiting new graduates, there are a large number of applications that do not match the requirements, which requires a lot of time and effort to deal with. Furthermore, when recruiting mid-career employees, searching for and screening candidates to meet the needs of each business division is a heavy burden. Startup companies, in particular, have limited resources to devote to recruitment, and are therefore seeking further efficiency. To solve these issues, there is a need for a system that can improve the efficiency and accuracy of the recruitment process. [Means for solving the problem]

[0005] The present invention provides a system that automatically searches for and extracts optimal candidates based on detailed company requirements. Specifically, the system includes a means for inputting detailed requirements, such as the company's desired work history, skills, years of experience, and industry knowledge; a means for searching for and extracting candidates based on the detailed requirements; a means for automatically creating and sending eye-catching recruiting emails to selected candidates; and a means for scheduling interviews with the candidates. The system also includes a means for linking with various social networking services and educational institution databases, and a means for analyzing and storing the detailed requirements entered by company personnel in a database. Furthermore, the system includes a means for scoring candidates and selecting candidates with high match scores based on the scores, and a means for integrating the schedules of company personnel and candidates to schedule interviews and suggesting optimal dates and times, thereby enabling efficient recruitment operations.

[0006] "Company detailed requirements" refers to information such as work history, skills, years of experience, and industry knowledge that a company requires from the personnel it wishes to hire.

[0007] "Input means" refers to an interface or device that allows a user to input detailed requirements of a company.

[0008] "Search and extraction methods" are the processes and algorithms that identify and shortlist the most suitable candidates based on the detailed requirements entered.

[0009] A "scout email" is an email sent by a company to a candidate to highlight the job opening and the company's appeal.

[0010] "Automated generation means" refers to the process or algorithm by which the system automatically generates text or emails based on conditions.

[0011] The "sending means" is the process or mechanism for sending the generated scouting email to the candidate's email address.

[0012] An "interview scheduling method" is a process or system that coordinates the availability of candidates and company personnel to determine the best date and time for an interview.

[0013] A "social networking service" is a platform on the Internet that allows individuals and companies to share information and interact with each other.

[0014] An "educational institution database" is a database containing data on students and graduates that is managed and made public by educational institutions such as universities and vocational schools.

[0015] "Scoring" is the process of quantifying a candidate's history, skills, etc. and evaluating them based on certain criteria.

[0016] "Schedule integration" is the process of combining multiple calendars and appointments to find the best time and date.

[0017] "Optimal date and time suggestion" means that the system will suggest an interview date and time that is convenient for both the company representative and the candidate. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] This invention is a system that uses AI to search for optimal candidates, send scouting emails, and automate the scheduling of interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0040] 1. Enter the requirements required by the company

[0041] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill, including work history, skills, years of experience, industry knowledge, etc. Once the input is complete, the data is sent from the terminal to the server.

[0042] 2. Search and extract the best candidates

[0043] The server analyzes the received company's detailed requirements and generates an appropriate search query. It then connects with LinkedIn, GitHub, and other social networking services and educational institution databases to search and extract the best candidates. It scores each candidate and lists the candidates with the highest match.

[0044] 3. Automatic creation and sending of scout emails

[0045] The server automatically generates scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[0046] 4. Scheduling an interview

[0047] Candidates who receive the scout email can click the link in the email on their device to access the schedule adjustment form. The candidate can then select a suitable date and time from the suggested dates and times entered in the form, and the data will be sent to the server.

[0048] Specific examples

[0049] For example, if a company wants to hire for a "software engineer" position, the user (company representative) enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information and searches for candidates with the relevant projects and experience on LinkedIn and GitHub. The server then lists 10 candidates who match closely, and automatically sends them a scouting email stating, "We're impressed with your Python and JavaScript projects on GitHub."

[0050] When a candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time. The determined interview date and time is automatically notified to both the candidate and the company representative.

[0051] This allows companies to conduct recruitment activities quickly and efficiently without hassle. The system automates the entire recruitment process, from talent search and scouting to interview arrangements, and is a system that can greatly streamline a company's recruitment operations.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user (company representative) accesses a dedicated web interface and enters the detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.). After entering the information, they press the "Submit" button to send the data to the server.

[0055] Step 2:

[0056] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[0057] Step 3:

[0058] Based on the stored detailed requirements, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[0059] Step 4:

[0060] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[0061] Step 5:

[0062] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[0063] Step 6:

[0064] The server automatically creates scouting emails for the listed candidates. These emails include personalized messages that highlight the attractiveness of the company and are based on the candidate's background and skills. These emails are generated based on templates.

[0065] Step 7:

[0066] The server automatically sends the generated scouting email to the candidate's email address, including a link to schedule an interview.

[0067] Step 8:

[0068] Candidates receive the scout email on their device, click the link in the email to access the schedule arrangement form, select a suitable date and time from the suggested dates and times, and press the "Submit" button.

[0069] Step 9:

[0070] The server receives the schedule adjustment data sent by the candidate, then compares it with the schedule of the company representative to determine the best interview date and time for both parties.

[0071] Step 10:

[0072] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, including details of the interview and login information.

[0073] The above are the specific processing steps of this system.

[0074] Example 1

[0075] 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."

[0076] In corporate recruitment activities, tasks such as searching for suitable candidates, generating and sending scouting emails, and scheduling interviews are often performed manually, which takes a lot of time and effort. There is also the risk of missing the timing to communicate with candidates or overlooking suitable talent. It is essential to solve these problems and improve the efficiency and effectiveness of the recruitment process.

[0077] 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.

[0078] In this invention, the server includes: a means for a user to input detailed job requirements; a means for analyzing candidate information based on the detailed requirements and generating a search query; a means for linking with multiple databases to search, extract, and score candidates; a means for automatically generating and sending personalized scout emails to candidates; a means for candidates who receive the scout email to access an interview scheduling form and enter their desired date and time; and a means for receiving the scheduling information provided by the candidate, integrating it with the schedule of the company representative, and determining and notifying the candidate of the optimal interview date and time. This enables companies to efficiently and quickly search for optimal candidates, send scout emails, and automate the process of scheduling interviews.

[0079] "User" refers to the person in charge of recruitment activities at a company or organization.

[0080] "Detailed job requirements" refer to the skills, years of experience, work history, industry knowledge, and other conditions required for the job a company is looking to hire for.

[0081] "Search Query" refers to a search dataset or command generated based on detailed job requirements.

[0082] "Candidate Information" refers to data about job seekers, such as their work history, skills, and project experience.

[0083] "Database" refers to a data storage system where candidate information is stored, such as LinkedIn or GitHub.

[0084] "Scoring" refers to the process of comparing and evaluating detailed job requirements with candidate information from search results and quantifying the degree of match.

[0085] A "scouting email" is an email sent to candidates who match a company's job requirements to express interest in hiring them.

[0086] "Scheduling Form" refers to an online form that allows candidates to enter their preferred interview date and time.

[0087] "Server" refers to the central computer system that handles all of the above processing and data management.

[0088] The present invention is a system that uses a generative AI model to search for optimal candidates, automates the sending of scouting emails, and schedules interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0089] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to hire, such as work history, skills, years of experience, industry knowledge, etc. This data is sent from the terminal to the server.

[0090] The server analyzes the received detailed requirements using natural language processing (NLP) technology and generates an appropriate search query. Based on the generated search query, the server connects to multiple databases, including LinkedIn and GitHub, to search for and extract candidates. In this process, the server collects information on multiple candidates and performs scoring to create a list of candidates with high match scores.

[0091] The server automatically generates personalized scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are sent to the candidate's email address.

[0092] Candidates receive a scout email and click on the link in the email to access the schedule adjustment form. In the schedule adjustment form, candidates can select a suitable date and time from the proposed interview dates and times. This data is sent to the server via the terminal.

[0093] The server integrates the candidate's desired date and time with the company's schedule to determine the optimal interview date and time. The server then notifies both the candidate and the company's representative of the determined interview date and time. This allows companies to conduct recruitment activities quickly and efficiently without hassle.

[0094] For example, if a company is looking to hire for a "software engineer" position, the user enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information, searches for candidates with the relevant projects and experience on LinkedIn and GitHub, and automatically sends them a scouting email. When the candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company's schedule to determine the optimal interview date and time, and automatically notifies the candidate.

[0095] The above system can improve the efficiency of companies' recruitment activities and significantly reduce the time and effort required. The effects of the present invention can be maximized through this specific implementation method.

[0096] An example prompt is, "Please explain in detail the steps involved in a system that automates a company's recruitment activities, from entering the required qualifications to scheduling an interview."

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] Users access a dedicated web interface and enter detailed job requirements, including work history, skills, years of experience, and industry knowledge.

[0100] The entered job requirements (input: work history, skills, years of experience, industry knowledge, etc.) are sent from the terminal to the server (output: JSON format data).

[0101] Step 2:

[0102] Job requirement data transmitted from the terminal to the server is received.

[0103] The server parses the JSON data and extracts the necessary information (input: JSON format data, output: parsed data object).

[0104] Step 3:

[0105] The server generates a search query based on the analysis results.

[0106] The server uses natural language processing technology to structure the job requirements and convert them into a search query (input: analysis result data object, output: search query).

[0107] Step 4:

[0108] The server uses the generated search query to connect with multiple databases, such as LinkedIn and GitHub, to search and extract candidate information.

[0109] The server collects the search results and scores each candidate (input: search query, output: scored candidate list).

[0110] Step 5:

[0111] The server automatically generates personalized scouting emails for the listed candidates.

[0112] The server uses a generative AI model to create a scouting email that includes wording that appeals to the company and a message about the candidate's skills and background (input: scored candidate list, output: scouting email).

[0113] Step 6:

[0114] The server sends the generated scout email to the candidate's email address.

[0115] The server monitors the status of the email sending and confirms the success of the sending (input: scout email and candidate email address, output: email sending status).

[0116] Step 7:

[0117] Candidates will receive a scouting email and click on the link in the email to access the scheduling form.

[0118] The candidate selects a convenient date and time from the suggested dates and times displayed on the form and sends the input data from the terminal to the server (input: date selected by the candidate, output: date data sent to the server).

[0119] Step 8:

[0120] The server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time.

[0121] The server notifies both the candidate and the company representative of the decided interview date and time (input: candidate's desired date and time and company representative's schedule, output: notification of decided interview date and time).

[0122] The above processing steps automate the recruitment process, enabling companies to conduct recruitment activities efficiently and effectively.

[0123] (Application example 1)

[0124] 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."

[0125] Traditionally, the process for companies to find suitable candidates, send out scouting emails, and schedule interviews has often been manual, requiring time and effort. Furthermore, when it comes to maintaining and repairing factory robots, finding and contacting technicians at the right time can be difficult, resulting in production line downtime. There is a need to solve these issues and streamline corporate and factory operations.

[0126] 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.

[0127] In this invention, the server includes means for inputting detailed requirements of a company, means for searching and extracting candidates based on the detailed requirements, means for automatically creating and sending scout emails to the candidates, means for arranging interview dates with candidates who have received the scout emails, and means for the robot to perform self-diagnosis, search for specialized engineers, and arrange maintenance schedules. This allows companies to conduct recruitment activities efficiently, and also makes it possible to quickly and efficiently perform maintenance and repairs of factory robots.

[0128] "Detailed company requirements" refers to the specific hiring conditions, such as the skills, years of experience, and industry knowledge required for the job the company is seeking.

[0129] "Candidate Search and Selection Means" means a means capable of locating and selecting suitable candidates from a database based on specified detailed requirements.

[0130] A "scout email" refers to a recruiting email sent by a company to selected candidates as part of its recruitment activities.

[0131] "Means for arranging interview dates" refers to a means that has the function of arranging interview dates and times between companies and candidates and determining the optimal interview schedule.

[0132] "Self-diagnosis" refers to the ability of a machine or system to monitor its own condition and automatically determine malfunctions or situations requiring maintenance.

[0133] "Professional technician" means a person who has particular techniques or skills and who has specialized knowledge to perform the maintenance and repair of machines and systems.

[0134] "Means for coordinating maintenance schedules" refers to the means by which a machine or system has the ability to coordinate and confirm optimal maintenance dates and times with a specialist.

[0135] "Social networking service" refers to a web service that enables individuals and businesses to exchange information and connect with each other over the Internet.

[0136] "Institutional database" refers to a database of alumni information and research results held by an educational institution such as a school or university.

[0137] This invention provides a system that streamlines corporate recruitment activities and factory robot maintenance. This system includes functions for inputting detailed requirements, searching and extracting candidates, automatically generating and sending scouting emails, arranging interview dates, and also for robot self-diagnosis and searching and scheduling maintenance engineers.

[0138] System configuration

[0139] 1. Enter detailed requirements

[0140] Users (company personnel) use a web interface to input detailed requirements for the job they are looking to hire for, such as skills, years of experience, industry knowledge, etc. The input data is then sent from the company's terminal to the server.

[0141] 2. Candidate search and selection

[0142] The server analyzes the details entered, generates the appropriate search query, and then connects with LinkedIn and other social networking services, as well as educational institution databases, to find and extract the best candidates.

[0143] 3. Automatic creation and sending of scout emails

[0144] The server automatically generates scouting emails for candidates listed in the search results. The emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[0145] 4. Scheduling an interview

[0146] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times entered in the form, and the data is sent to the server. The server combines the candidate's desired date and time with the company representative's schedule, determines the optimal interview date and time, and notifies both parties.

[0147] 5. Robot self-diagnosis

[0148] The factory robots are self-diagnostic and monitor their performance, and if there is an error or maintenance required, the robots send that information to a server.

[0149] 6. Searching for and scheduling specialists

[0150] The server analyzes the error information received from the robot and searches for and extracts the appropriate technician. Various databases are used for the search, and a maintenance request message is automatically sent to the appropriate technician. After the technician replies, the server coordinates the optimal maintenance date and time between the robot and the technician, and notifies both parties of the decided date and time.

[0151] Example

[0152] Software used:

[0153] Python, Requests library, LinkedIn API

[0154] Hardware used:

[0155] Corporate terminals, servers, factory robots, internet-connected devices

[0156] Example prompt sentence:

[0157] Robot diagnosis results:

[0158] Error code: E404

[0159] Error: Mechanical failure in arm joint

[0160] Technician search query:

[0161] "technician+mechanical+failure+arm+joint"

[0162] Specific message example:

[0163] Subject: Urgent Maintenance Required for Arm Joint Failure

[0164] Dear [Technician Name],

[0165] Our robot has detected a mechanical failure in its arm joint and we require immediate assistance. Can you assist in resolving this issue at your earliest convenience?

[0166] Best,

[0167] Robot Maintenance Team

[0168] This allows companies to conduct recruitment activities quickly and efficiently without hassle, and also enables maintenance and repair of factory robots to be carried out quickly and efficiently.

[0169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0170] Step 1:

[0171] The user enters details of the company's requirements into a web interface, including the skills required for the job, years of experience, industry knowledge, etc. This data is then sent from the terminal to the server.

[0172] Input: Detailed job requirements (skills, years of experience, industry knowledge)

[0173] Output: Detailed requirements data sent to the server

[0174] Step 2:

[0175] The server analyzes the received detailed requirements data and generates appropriate search queries that are used against social networking services and educational institution databases.

[0176] Input: Detailed requirement data

[0177] Output: Search query

[0178] Step 3:

[0179] The server uses the generated search query to search and extract the best candidates from LinkedIn and other databases, which are then scored and listed in order of best match.

[0180] Input: Search query

[0181] Output: List of candidates

[0182] Step 4:

[0183] The server automatically generates and sends scouting emails to the listed candidates, including a personalized message about the company's appeal and the candidate's skills and background.

[0184] Input: Listed candidates

[0185] Output: Scout email sent

[0186] Step 5:

[0187] When a candidate receives a scout email and clicks on the link in the email, they will access the schedule adjustment form. The candidate will select a suitable date and time from the suggested dates and times entered in the form and enter it. This will send the schedule data to the server.

[0188] Input: Candidate's action when clicking the link in the scouting email

[0189] Output: Schedule data sent to the server

[0190] Step 6:

[0191] The server combines the desired date and time sent by the candidate with the schedule of the company representative to determine the optimal interview date and time, and notifies both parties of the determined interview date and time.

[0192] Input: Candidate's desired date and time, company representative's schedule data

[0193] Output: Notification of the decided interview date and time

[0194] Step 7:

[0195] Factory robots perform self-diagnosis and, if a malfunction or maintenance is detected, send error information to a server.

[0196] Input: Robot self-diagnosis results

[0197] Output: Error information sent to the server

[0198] Step 8:

[0199] The server analyzes the error information received from the robot, searches for and extracts the appropriate technician, and retrieves information about the technician from the technician database.

[0200] Input: Robot error information

[0201] Output: Searched and extracted engineers

[0202] Step 9:

[0203] The server automatically generates and sends a maintenance request message to the extracted technician.

[0204] Input: Extracted technician information

[0205] Output: Maintenance request message sent

[0206] Step 10:

[0207] The technician responds to the maintenance request, and the server adjusts the maintenance date and time based on the response. The adjusted date and time are notified to the robot and the technician.

[0208] Input: Technician's response

[0209] Output: Notification of adjusted maintenance date and time

[0210] 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.

[0211] This invention is a system that uses AI and an emotion engine to automate the process of searching for optimal candidates, sending scouting emails, and arranging interview schedules in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0212] 1. Enter the requirements required by the company

[0213] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.) The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database.

[0214] 2. Search and extract the best candidates

[0215] The server generates a search query based on the saved detailed requirements data of companies and sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases. The server receives and analyzes the response data to extract candidates and score each candidate. Based on the scores, candidates with the highest match are ranked and listed.

[0216] 3. Automatic creation and sending of scout emails

[0217] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message that highlights the attractiveness of the company and is based on the candidate's skills and background. Furthermore, an emotion engine is used to recognize the candidate's current emotional state and adjust the content of the email accordingly. The generated scouting emails are then automatically sent to the candidate's email address.

[0218] 4. Scheduling an interview

[0219] Candidates who receive the scouting email can click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times on the form, and once the data is entered, it is sent to the server.

[0220] The server compares the schedule adjustment data received from the candidate with the schedule of the company representative. It uses an emotion engine to analyze the emotional state of the company representative and candidate and proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the company representative and the candidate.

[0221] Specific examples

[0222] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches its LinkedIn and GitHub databases. Ten highly matching candidates are listed, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your GitHub project (Python, R)."

[0223] Before sending an email, a sentiment engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently posted something positive, the tone of the email will be more positive as well.

[0224] When a candidate receives the email, they click the link to access the scheduling form and select a suitable date and time from the suggested options. The server then integrates this with the company representative's schedule and uses an emotion engine to analyze the emotional state of both parties before determining the optimal interview date and time.

[0225] The confirmed interview date and time is automatically notified to both the candidate and the company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the analysis results of the emotion engine.

[0226] In this way, the present invention is a system that, by combining an emotion engine, can further personalize the conventional recruitment process and make it more efficient and effective.

[0227] The processing flow will be explained below.

[0228] Step 1:

[0229] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. After entering the detailed requirements, the user presses the "Submit" button to send the data to the server.

[0230] Step 2:

[0231] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[0232] Step 3:

[0233] Based on the stored detailed requirement data, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[0234] Step 4:

[0235] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[0236] Step 5:

[0237] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[0238] Step 6:

[0239] For each candidate on the list, the server uses an emotion engine to tailor the content of scouting emails. Specifically, it analyzes the candidate's past email responses and social media posts to recognize their current emotional state, and customizes the tone and content of the email accordingly.

[0240] Step 7:

[0241] The server automatically generates and sends a customized scouting email to the candidate's email address, containing the scouting information and a link to schedule an interview.

[0242] Step 8:

[0243] After receiving the scout email on their device, the candidate clicks on the link in the email to access the schedule arrangement form, selects a suitable date and time from the suggested dates and times in the form, and submits the information they entered to the server.

[0244] Step 9:

[0245] The server receives the schedule adjustment data sent by the candidate. It then compares it with the company representative's schedule and proposes the optimal date and time for both parties. It uses an emotion engine to analyze the emotional state of the company representative and the candidate. The optimal interview date and time is determined taking this information into consideration.

[0246] Step 10:

[0247] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, and based on the results of the emotion engine's analysis, conveys sincere and positive messages to the candidate.

[0248] As a specific example, if a company wants to hire for a "data scientist" position, the company representative enters detailed requirements, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server uses these requirements to search databases such as LinkedIn and GitHub, and lists 10 candidates who most closely match the requirements. Before sending a scouting email, the emotion engine analyzes the candidate's emotional state and adjusts the content of the email. When scheduling an interview, the emotion engine is also used to consider the emotional state of both the company representative and the candidate, and the optimal date and time is suggested and notified.

[0249] Example 2

[0250] 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."

[0251] In corporate recruitment activities, quickly finding suitable candidates, efficiently contacting them, and arranging interview dates is a very time-consuming process. In particular, communication that does not take into consideration the emotional state of the candidate and the company representative can cause stress for both parties, which can ultimately reduce recruitment efficiency. A system that solves this problem and makes recruitment activities more efficient and effective is needed.

[0252] 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.

[0253] In this invention, the server includes means for inputting detailed requirements of a company, means for searching for and extracting candidates based on the detailed requirements, means for creating and sending automatic scout emails to the candidates, means for arranging interview dates with candidates who have received the scout email, means having an emotion engine for analyzing the emotional states of the candidates and company personnel, means for adjusting the content of the email based on the emotion analysis results, and means for proposing the optimal interview date and time based on the emotion analysis results.This not only streamlines the process from searching for candidates to arranging interview dates and times, but also makes use of the emotion engine to enable less stressful communication for both candidates and company personnel.

[0254] "Company's detailed requirements" are the specific conditions and standards that a company requires for the position (e.g., work history, skills, years of experience, industry knowledge, etc.).

[0255] A "candidate" is an individual whom a company considers for recruitment purposes.

[0256] The "emotion engine" is software that analyzes the emotional state of candidates and company representatives and adjusts the system's operation based on the analysis results.

[0257] A "scout email" is an email sent by a company to a candidate to convey their interest in hiring.

[0258] "Interview scheduling" is the process of deciding the date and time of the interview, taking into consideration the convenience of the company representative and the candidate.

[0259] An "external database" is a database that exists outside the system and provides information about candidates (e.g., a social networking service or an educational institution's database).

[0260] "Search and extraction" is the process of finding and retrieving matching information from a database based on specified criteria.

[0261] "Analysis" is the process of analyzing input data or acquired data to find meaning and value.

[0262] "Storage" is the process of recording acquired data in a storage medium such as a database so that it can be retrieved when needed.

[0263] "Automatic creation" is the process by which the system automatically generates the necessary information and content without human intervention.

[0264] "Proposing the optimal interview date and time" means presenting the most suitable interview date and time for both parties based on the analysis results of the emotion engine, etc.

[0265] This invention is a system that combines multiple pieces of hardware and software to streamline corporate recruitment activities. This system automates all processes, including inputting the company's requirements, searching and extracting suitable candidates, creating and sending automatic scouting emails, and scheduling interviews. Specific implementation methods are described below.

[0266] 1. Enter the requirements required by the company

[0267] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill (work history, skills, years of experience, industry knowledge, etc.). The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database. This process uses a web browser, HTTP requests, and a database (e.g., MySQL or PostgreSQL).

[0268] 2. Search and extract the best candidates

[0269] The server generates a search query based on the company's detailed requirements data and sends an API request to various external databases (e.g., social networking services, educational institution databases). The received response data is analyzed using a machine learning algorithm (e.g., Python's scikit-learn or TensorFlow) to score candidates. Finally, a list of candidates with high matching scores is generated.

[0270] 3. Automatic creation and sending of scout emails

[0271] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message highlighting the company's attractiveness and based on the candidate's skills and experience. Furthermore, an emotion engine (e.g., Python's NLTK or TextBlob) is used to analyze the candidate's emotional state and adjust the email content accordingly. The generated scouting emails are automatically sent using Python's smtplib library.

[0272] 4. Scheduling an interview

[0273] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times, enters the information, and the data is sent to the server. The server compares the received schedule arrangement data with the schedule of the company representative, analyzes the emotional state of the candidate and company representative using an emotion engine, and then proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative.

[0274] Specific examples

[0275] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches databases such as LinkedIn and GitHub. A list of 10 highly matching candidates is generated, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your project."

[0276] Before sending the email, the emotion engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently made positive posts, the tone of the email will be positive to match. When the candidate receives the email, clicks the link to access the scheduling form and selects a suitable date and time from the suggested dates and times, the server compares this with the company representative's schedule and uses the emotion engine to analyze the emotional states of both parties to determine the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the results of the emotion engine's analysis.

[0277] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0278] Step 1:

[0279] Enter your company's detailed requirements

[0280] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. Specifically, the user launches a web browser, accesses the company's dedicated login page, enters the required information in each field, and clicks the "Submit" button. This input data (detailed requirements) is sent from the browser to the terminal via a POST request.

[0281] Input: Detailed requirement data entered by the user into the web form

[0282] Output: Detailed requirements data submitted

[0283] Step 2:

[0284] Parsing and storing detailed requirements data

[0285] The device sends the entered detailed requirements data to the server, which receives the data, analyzes it, and stores it in a corporate database. Specifically, a server-side script (e.g., Python, Java, etc.) receives the data, analyzes and organizes it using natural language processing, and then stores it in a database (e.g., MySQL or PostgreSQL).

[0286] Input: Detailed requirements data entered by the user

[0287] Output: Detailed requirements data analyzed and stored in a corporate database

[0288] Step 3:

[0289] Generate and submit candidate search queries

[0290] The server generates a search query based on the stored detailed requirements data of the company. The server then uses this search query to send API requests to various external databases (e.g., social networking services or educational institution databases). Specifically, the server generates a query using natural language processing technology and SQL or API requests, and sends it to the external database as an HTTP request.

[0291] Input: Saved detailed company requirements data

[0292] Output: The search query sent to the external database

[0293] Step 4:

[0294] Receiving and analyzing candidate data

[0295] The server receives and parses the response data from the external database. Specifically, it parses the returned data in JSON or XML format using Python's json module or other compatible libraries to extract candidate information.

[0296] Input: Response data from an external database

[0297] Output: Parsed candidate data

[0298] Step 5:

[0299] Candidate scoring and shortlisting

[0300] The server uses a machine learning algorithm to score the analyzed candidate data. Specifically, it uses Python libraries such as scikit-learn and TensorFlow to calculate the degree to which the candidate's skills match the detailed requirements, assigns a score, and then ranks and lists the candidates based on the score.

[0301] Input: Parsed candidate data

[0302] Output: Scored candidate list

[0303] Step 6:

[0304] Generate and send scout emails

[0305] The server generates scouting emails based on the scored candidate list. These emails highlight the company's attractiveness and include personalized messages based on the candidate's skills and experience. It also uses an emotion engine to analyze the candidate's emotional state and adjusts the email content accordingly. Specifically, it generates the email body using a template engine, performs emotion analysis using Python's NLTK and TextBlob, and sends the email using the smtplib library.

[0306] Input: Scored candidate list and sentiment engine analysis results

[0307] Output: Scout email sent

[0308] Step 7:

[0309] Scheduling an interview

[0310] Candidates receive the scouting email and click on the link in the email to access the scheduling form, which they do by clicking the link, opening the page in their browser, selecting a suitable date and time from the suggested dates and times, and submitting the form.

[0311] Input: Clicking on the link in the scout email and entering the schedule adjustment data

[0312] Output: Sent schedule adjustment data

[0313] Step 8:

[0314] Processing and notification of scheduling data

[0315] The server receives the schedule adjustment data sent by the candidate and compares it with the schedule of the company representative. Specifically, it retrieves the company representative's calendar information from the database and compares it with the candidate's input data to determine the optimal interview date and time. At this time, an emotion engine is used to analyze the emotional states of both parties and propose the optimal date and time. Finally, the confirmed interview date and time is automatically notified to both the company representative and the candidate.

[0316] Input: Company personnel schedule data and candidate schedule adjustment data

[0317] Output: Confirmed interview date and time, and notification sent

[0318] (Application example 2)

[0319] 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."

[0320] Modern recruitment activities involve many time-consuming tasks, such as searching for candidates, sending scouting emails, and scheduling interviews. Furthermore, companies must efficiently utilize numerous databases and information sources to find the best candidates to meet their requirements. While analyzing emotional states and providing personalized content could potentially improve the effectiveness of recruitment activities, there is a lack of methods to achieve this. Therefore, to efficiently complete these tasks, a system is needed that can search for candidates based on a company's detailed requirements, analyze their emotional states, and recommend and notify them of personalized content.

[0321] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting detailed requirements of a company, a means for searching for and extracting candidates based on the detailed requirements, a means for automatically creating and sending scout emails to the candidates, a means for arranging interview dates with candidates who have received the scout emails, a means for analyzing the user's emotional state and recommending personalized content, and a means for notifying the user of the recommended content. This makes it possible to improve the efficiency of companies' recruitment activities and provide personalized content based on their emotional state.

[0322] The "means for entering detailed company requirements" is an interface for entering information such as the skills and experience required for the job sought by company personnel.

[0323] "Means for searching and extracting candidates" refers to a system that searches for candidate information from social networking services and educational institution databases based on the detailed requirements of a company, and identifies suitable candidates.

[0324] The "means for automatically creating and sending scouting emails" is a mechanism for automatically creating email content for selected candidates and sending messages that appeal to the attractiveness of the company.

[0325] The "means of arranging interview dates" is a system that checks the availability of candidates who receive scouting emails with that of company personnel to determine the most suitable interview date and time.

[0326] "Means for analyzing a user's emotional state" refers to an algorithm that identifies a user's emotions from social media posts, messages, etc. and evaluates their state.

[0327] A "means for recommending personalized content" is a system for identifying and recommending optimal content to a user based on the analyzed emotional state of the user.

[0328] "Means for notifying users of recommended content" means a mechanism for communicating recommended content to users by push notification or other means.

[0329] This invention is a system that searches for and extracts candidates based on the detailed requirements of a company, automatically sends scouting emails, and schedules interviews. It can also analyze the user's emotional state and recommend and notify personalized content. Specific embodiments for implementing the invention are described below.

[0330] First, a company representative uses a dedicated web interface to enter detailed requirements for the job they are recruiting for (e.g., skills, years of experience, industry knowledge, etc.). This data is sent from the terminal to a server, which analyzes the received data and stores it in a company database. The server software used is a database management system (e.g., MySQL) or a web server (e.g., Apache).

[0331] Next, the server generates a search query based on the saved detailed requirements data of the companies and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. After receiving the response data, the server analyzes it to extract candidates, and scores and ranks each candidate.

[0332] The server automatically generates and sends scouting emails to ranked candidates. These emails include a message highlighting the attractiveness of the company and personalized content based on the candidate's skills and experience. An emotion engine is used to recognize the candidate's emotional state and adjust the email content accordingly. This process uses an emotion analysis algorithm (e.g., Google Cloud Natural Language API).

[0333] When a candidate receives a scouting email and clicks on the link in the email, they can access a schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times and enters the information, which is then sent to the server. The server compares the candidate's data with the company representative's schedule, uses an emotion engine to suggest the optimal interview date and time, and notifies both the company representative and the candidate of the confirmed date and time.

[0334] It also includes a function to analyze the user's emotional state and recommend personalized content. The server identifies the user's emotions from social media posts and messages and evaluates their state. Based on this, it identifies the most suitable content (e.g., videos, articles, music, etc.) and notifies the user. The algorithms used include a voice emotion recognition engine (e.g., IBM Watson) and a content recommendation system (e.g., TensorFlow).

[0335] For example, if the user is "feeling stressed," the system will recommend relaxation music or videos with a relaxing effect. Examples of prompts for the generative AI model are:

[0336] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[0337] As described above, the present invention streamlines corporate recruitment activities and provides personalized content that matches the user's emotional state, thereby realizing more effective human resource management.

[0338] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0339] Step 1:

[0340] As a means of inputting detailed company requirements, the terminal uses a dedicated web interface to input detailed requirements (skills, years of experience, industry knowledge, etc.) required for the job being recruited. The input data is sent to the server as the company's detailed requirements.

[0341] Step 2:

[0342] The server analyzes the received detailed requirement data and stores it in the company database. The database management system used here is MySQL as an example. The input data is the detailed requirement information, and the output is the analyzed requirement information stored in the company database.

[0343] Step 3:

[0344] The server generates a search query based on the stored detailed requirements data and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. The server receives and analyzes the response data to extract candidates, score each candidate, and rank them. The input data are the detailed requirements and candidate information from the social networking services, and the output is a scored candidate list.

[0345] Step 4:

[0346] The server automatically generates scouting emails for ranked candidates. These scouting emails include a message highlighting the company's attractiveness and personalized content based on the candidate's skills and experience. An emotion engine (e.g., Google Cloud Natural Language API) is used to recognize the candidate's emotional state and adjust the email content accordingly. The input data is candidate information and the results of emotion analysis, and the output is a personalized scouting email.

[0347] Step 5:

[0348] The server sends the generated scout email to the candidate's email address. The candidate clicks the link in the email to access the schedule adjustment form. They select a convenient date and time from the suggested dates and times on their device and enter the data, which is then sent to the server. The input data is the candidate's selected date and time, and the output is the schedule adjustment data sent to the server.

[0349] Step 6:

[0350] The server compares the scheduling data received from the candidate with the company's schedule and uses an emotion engine to suggest the optimal interview date and time. The algorithms used include an emotion analysis algorithm (e.g., Google Cloud Natural Language API). The input data is the candidate's scheduling data and the company's schedule, and the output is the optimal interview date and time.

[0351] Step 7:

[0352] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time. This notification is also conveyed in a sincere and positive manner based on the analysis results of the emotion engine. The input data is the confirmed interview date and time, and the output is the notification to the company representative and the candidate.

[0353] Step 8:

[0354] Furthermore, a means of analyzing the user's emotional state and recommending personalized content is added. The server identifies the user's emotions from social media posts and messages and evaluates their state. The emotion analysis engine used utilizes a voice emotion recognition engine (e.g., IBM Watson). The input data are the user's posts and messages, and the output is the analyzed emotional state.

[0355] Step 9:

[0356] The server identifies and recommends appropriate content (videos, articles, music, etc.) based on the analyzed user emotional state. This process uses a content recommendation system (e.g., TensorFlow). The input data is the analyzed emotional state, and the output is the recommended content.

[0357] Step 10:

[0358] The server notifies the user of the recommended content by push notification or other means. The input data is the recommended content, and the output is the notification to the user.

[0359] For example, if the user is analyzed as "feeling stressed," the server will recommend relaxation music or videos with a relaxing effect. An example of a prompt for the generative AI model is as follows:

[0360] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[0361] 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.

[0362] 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.

[0363] 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.

[0364] [Second embodiment]

[0365] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0366] 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.

[0367] 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).

[0368] 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.

[0369] 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.

[0370] 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).

[0371] 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.

[0372] 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.

[0373] 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.

[0374] 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.

[0375] 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.

[0376] 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."

[0377] This invention is a system that uses AI to search for optimal candidates, send scouting emails, and automate the scheduling of interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0378] 1. Enter the requirements required by the company

[0379] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill, including work history, skills, years of experience, industry knowledge, etc. Once the input is complete, the data is sent from the terminal to the server.

[0380] 2. Search and extract the best candidates

[0381] The server analyzes the received company's detailed requirements and generates an appropriate search query. It then connects with LinkedIn, GitHub, and other social networking services and educational institution databases to search and extract the best candidates. It scores each candidate and lists the candidates with the highest match.

[0382] 3. Automatic creation and sending of scout emails

[0383] The server automatically generates scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[0384] 4. Scheduling an interview

[0385] Candidates who receive the scout email can click the link in the email on their device to access the schedule adjustment form. The candidate can then select a suitable date and time from the suggested dates and times entered in the form, and the data will be sent to the server.

[0386] Specific examples

[0387] For example, if a company wants to hire for a "software engineer" position, the user (company representative) enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information and searches for candidates with the relevant projects and experience on LinkedIn and GitHub. The server then lists 10 candidates who match closely, and automatically sends them a scouting email stating, "We're impressed with your Python and JavaScript projects on GitHub."

[0388] When a candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time. The determined interview date and time is automatically notified to both the candidate and the company representative.

[0389] This allows companies to conduct recruitment activities quickly and efficiently without hassle. The system automates the entire recruitment process, from talent search and scouting to interview arrangements, and is a system that can greatly streamline a company's recruitment operations.

[0390] The processing flow will be explained below.

[0391] Step 1:

[0392] The user (company representative) accesses a dedicated web interface and enters the detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.). After entering the information, they press the "Submit" button to send the data to the server.

[0393] Step 2:

[0394] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[0395] Step 3:

[0396] Based on the stored detailed requirements, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[0397] Step 4:

[0398] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[0399] Step 5:

[0400] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[0401] Step 6:

[0402] The server automatically creates scouting emails for the listed candidates. These emails include personalized messages that highlight the attractiveness of the company and are based on the candidate's background and skills. These emails are generated based on templates.

[0403] Step 7:

[0404] The server automatically sends the generated scouting email to the candidate's email address, including a link to schedule an interview.

[0405] Step 8:

[0406] Candidates receive the scout email on their device, click the link in the email to access the schedule arrangement form, select a suitable date and time from the suggested dates and times, and press the "Submit" button.

[0407] Step 9:

[0408] The server receives the schedule adjustment data sent by the candidate, then compares it with the schedule of the company representative to determine the best interview date and time for both parties.

[0409] Step 10:

[0410] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, including details of the interview and login information.

[0411] The above are the specific processing steps of this system.

[0412] Example 1

[0413] 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."

[0414] In corporate recruitment activities, tasks such as searching for suitable candidates, generating and sending scouting emails, and scheduling interviews are often performed manually, which takes a lot of time and effort. There is also the risk of missing the timing to communicate with candidates or overlooking suitable talent. It is essential to solve these problems and improve the efficiency and effectiveness of the recruitment process.

[0415] 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.

[0416] In this invention, the server includes: a means for a user to input detailed job requirements; a means for analyzing candidate information based on the detailed requirements and generating a search query; a means for linking with multiple databases to search, extract, and score candidates; a means for automatically generating and sending personalized scout emails to candidates; a means for candidates who receive the scout email to access an interview scheduling form and enter their desired date and time; and a means for receiving the scheduling information provided by the candidate, integrating it with the schedule of the company representative, and determining and notifying the candidate of the optimal interview date and time. This enables companies to efficiently and quickly search for optimal candidates, send scout emails, and automate the process of scheduling interviews.

[0417] "User" refers to the person in charge of recruitment activities at a company or organization.

[0418] "Detailed job requirements" refer to the skills, years of experience, work history, industry knowledge, and other conditions required for the job a company is looking to hire for.

[0419] "Search Query" refers to a search dataset or command generated based on detailed job requirements.

[0420] "Candidate Information" refers to data about job seekers, such as their work history, skills, and project experience.

[0421] "Database" refers to a data storage system where candidate information is stored, such as LinkedIn or GitHub.

[0422] "Scoring" refers to the process of comparing and evaluating detailed job requirements with candidate information from search results and quantifying the degree of match.

[0423] A "scouting email" is an email sent to candidates who match a company's job requirements to express interest in hiring them.

[0424] "Scheduling Form" refers to an online form that allows candidates to enter their preferred interview date and time.

[0425] "Server" refers to the central computer system that handles all of the above processing and data management.

[0426] The present invention is a system that uses a generative AI model to search for optimal candidates, automates the sending of scouting emails, and schedules interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0427] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to hire, such as work history, skills, years of experience, industry knowledge, etc. This data is sent from the terminal to the server.

[0428] The server analyzes the received detailed requirements using natural language processing (NLP) technology and generates an appropriate search query. Based on the generated search query, the server connects to multiple databases, including LinkedIn and GitHub, to search for and extract candidates. In this process, the server collects information on multiple candidates and performs scoring to create a list of candidates with high match scores.

[0429] The server automatically generates personalized scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are sent to the candidate's email address.

[0430] Candidates receive a scout email and click on the link in the email to access the schedule adjustment form. In the schedule adjustment form, candidates can select a suitable date and time from the proposed interview dates and times. This data is sent to the server via the terminal.

[0431] The server integrates the candidate's desired date and time with the company's schedule to determine the optimal interview date and time. The server then notifies both the candidate and the company's representative of the determined interview date and time. This allows companies to conduct recruitment activities quickly and efficiently without hassle.

[0432] For example, if a company is looking to hire for a "software engineer" position, the user enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information, searches for candidates with the relevant projects and experience on LinkedIn and GitHub, and automatically sends them a scouting email. When the candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company's schedule to determine the optimal interview date and time, and automatically notifies the candidate.

[0433] The above system can improve the efficiency of companies' recruitment activities and significantly reduce the time and effort required. The effects of the present invention can be maximized through this specific implementation method.

[0434] An example prompt is, "Please explain in detail the steps involved in a system that automates a company's recruitment activities, from entering the required qualifications to scheduling an interview."

[0435] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0436] Step 1:

[0437] Users access a dedicated web interface and enter detailed job requirements, including work history, skills, years of experience, and industry knowledge.

[0438] The entered job requirements (input: work history, skills, years of experience, industry knowledge, etc.) are sent from the terminal to the server (output: JSON format data).

[0439] Step 2:

[0440] Job requirement data transmitted from the terminal to the server is received.

[0441] The server parses the JSON data and extracts the necessary information (input: JSON format data, output: parsed data object).

[0442] Step 3:

[0443] The server generates a search query based on the analysis results.

[0444] The server uses natural language processing technology to structure the job requirements and convert them into a search query (input: analysis result data object, output: search query).

[0445] Step 4:

[0446] The server uses the generated search query to connect with multiple databases, such as LinkedIn and GitHub, to search and extract candidate information.

[0447] The server collects the search results and scores each candidate (input: search query, output: scored candidate list).

[0448] Step 5:

[0449] The server automatically generates personalized scouting emails for the listed candidates.

[0450] The server uses a generative AI model to create a scouting email that includes wording that appeals to the company and a message about the candidate's skills and background (input: scored candidate list, output: scouting email).

[0451] Step 6:

[0452] The server sends the generated scout email to the candidate's email address.

[0453] The server monitors the status of the email sending and confirms the success of the sending (input: scout email and candidate email address, output: email sending status).

[0454] Step 7:

[0455] Candidates will receive a scouting email and click on the link in the email to access the scheduling form.

[0456] The candidate selects a convenient date and time from the suggested dates and times displayed on the form and sends the input data from the terminal to the server (input: date selected by the candidate, output: date data sent to the server).

[0457] Step 8:

[0458] The server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time.

[0459] The server notifies both the candidate and the company representative of the decided interview date and time (input: candidate's desired date and time and company representative's schedule, output: notification of decided interview date and time).

[0460] The above processing steps automate the recruitment process, enabling companies to conduct recruitment activities efficiently and effectively.

[0461] (Application example 1)

[0462] 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."

[0463] Traditionally, the process for companies to find suitable candidates, send out scouting emails, and schedule interviews has often been manual, requiring time and effort. Furthermore, when it comes to maintaining and repairing factory robots, finding and contacting technicians at the right time can be difficult, resulting in production line downtime. There is a need to solve these issues and streamline corporate and factory operations.

[0464] 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.

[0465] In this invention, the server includes means for inputting detailed requirements of a company, means for searching and extracting candidates based on the detailed requirements, means for automatically creating and sending scout emails to the candidates, means for arranging interview dates with candidates who have received the scout emails, and means for the robot to perform self-diagnosis, search for specialized engineers, and arrange maintenance schedules. This allows companies to conduct recruitment activities efficiently, and also makes it possible to quickly and efficiently perform maintenance and repairs of factory robots.

[0466] "Detailed company requirements" refers to the specific hiring conditions, such as the skills, years of experience, and industry knowledge required for the job the company is seeking.

[0467] "Candidate Search and Selection Means" means a means capable of locating and selecting suitable candidates from a database based on specified detailed requirements.

[0468] A "scout email" refers to a recruiting email sent by a company to selected candidates as part of its recruitment activities.

[0469] "Means for arranging interview dates" refers to a means that has the function of arranging interview dates and times between companies and candidates and determining the optimal interview schedule.

[0470] "Self-diagnosis" refers to the ability of a machine or system to monitor its own condition and automatically determine malfunctions or situations requiring maintenance.

[0471] "Professional technician" means a person who has particular techniques or skills and who has specialized knowledge to perform the maintenance and repair of machines and systems.

[0472] "Means for coordinating maintenance schedules" refers to the means by which a machine or system has the ability to coordinate and confirm optimal maintenance dates and times with a specialist.

[0473] "Social networking service" refers to a web service that enables individuals and businesses to exchange information and connect with each other over the Internet.

[0474] "Institutional database" refers to a database of alumni information and research results held by an educational institution such as a school or university.

[0475] This invention provides a system that streamlines corporate recruitment activities and factory robot maintenance. This system includes functions for inputting detailed requirements, searching and extracting candidates, automatically generating and sending scouting emails, arranging interview dates, and also for robot self-diagnosis and searching and scheduling maintenance engineers.

[0476] System configuration

[0477] 1. Enter detailed requirements

[0478] Users (company personnel) use a web interface to input detailed requirements for the job they are looking to hire for, such as skills, years of experience, industry knowledge, etc. The input data is then sent from the company's terminal to the server.

[0479] 2. Candidate search and selection

[0480] The server analyzes the details entered, generates the appropriate search query, and then connects with LinkedIn and other social networking services, as well as educational institution databases, to find and extract the best candidates.

[0481] 3. Automatic creation and sending of scout emails

[0482] The server automatically generates scouting emails for candidates listed in the search results. The emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[0483] 4. Scheduling an interview

[0484] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times entered in the form, and the data is sent to the server. The server combines the candidate's desired date and time with the company representative's schedule, determines the optimal interview date and time, and notifies both parties.

[0485] 5. Robot self-diagnosis

[0486] The factory robots are self-diagnostic and monitor their performance, and if there is an error or maintenance required, the robots send that information to a server.

[0487] 6. Searching for and scheduling specialists

[0488] The server analyzes the error information received from the robot and searches for and extracts the appropriate technician. Various databases are used for the search, and a maintenance request message is automatically sent to the appropriate technician. After the technician replies, the server coordinates the optimal maintenance date and time between the robot and the technician, and notifies both parties of the decided date and time.

[0489] Example

[0490] Software used:

[0491] Python, Requests library, LinkedIn API

[0492] Hardware used:

[0493] Corporate terminals, servers, factory robots, internet-connected devices

[0494] Example prompt sentence:

[0495] Robot diagnosis results:

[0496] Error code: E404

[0497] Error: Mechanical failure in arm joint

[0498] Technician search query:

[0499] "technician+mechanical+failure+arm+joint"

[0500] Specific message example:

[0501] Subject: Urgent Maintenance Required for Arm Joint Failure

[0502] Dear [Technician Name],

[0503] Our robot has detected a mechanical failure in its arm joint and we require immediate assistance. Can you assist in resolving this issue at your earliest convenience?

[0504] Best,

[0505] Robot Maintenance Team

[0506] This allows companies to conduct recruitment activities quickly and efficiently without hassle, and also enables maintenance and repair of factory robots to be carried out quickly and efficiently.

[0507] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0508] Step 1:

[0509] The user enters details of the company's requirements into a web interface, including the skills required for the job, years of experience, industry knowledge, etc. This data is then sent from the terminal to the server.

[0510] Input: Detailed job requirements (skills, years of experience, industry knowledge)

[0511] Output: Detailed requirements data sent to the server

[0512] Step 2:

[0513] The server analyzes the received detailed requirements data and generates appropriate search queries that are used against social networking services and educational institution databases.

[0514] Input: Detailed requirement data

[0515] Output: Search query

[0516] Step 3:

[0517] The server uses the generated search query to search and extract the best candidates from LinkedIn and other databases, which are then scored and listed in order of best match.

[0518] Input: Search query

[0519] Output: List of candidates

[0520] Step 4:

[0521] The server automatically generates and sends scouting emails to the listed candidates, including a personalized message about the company's appeal and the candidate's skills and background.

[0522] Input: Listed candidates

[0523] Output: Scout email sent

[0524] Step 5:

[0525] When a candidate receives a scout email and clicks on the link in the email, they will access the schedule adjustment form. The candidate will select a suitable date and time from the suggested dates and times entered in the form and enter it. This will send the schedule data to the server.

[0526] Input: Candidate's action when clicking the link in the scouting email

[0527] Output: Schedule data sent to the server

[0528] Step 6:

[0529] The server combines the desired date and time sent by the candidate with the schedule of the company representative to determine the optimal interview date and time, and notifies both parties of the determined interview date and time.

[0530] Input: Candidate's desired date and time, company representative's schedule data

[0531] Output: Notification of the decided interview date and time

[0532] Step 7:

[0533] Factory robots perform self-diagnosis and, if a malfunction or maintenance is detected, send error information to a server.

[0534] Input: Robot self-diagnosis results

[0535] Output: Error information sent to the server

[0536] Step 8:

[0537] The server analyzes the error information received from the robot, searches for and extracts the appropriate technician, and retrieves information about the technician from the technician database.

[0538] Input: Robot error information

[0539] Output: Searched and extracted engineers

[0540] Step 9:

[0541] The server automatically generates and sends a maintenance request message to the extracted technician.

[0542] Input: Extracted technician information

[0543] Output: Maintenance request message sent

[0544] Step 10:

[0545] The technician responds to the maintenance request, and the server adjusts the maintenance date and time based on the response. The adjusted date and time are notified to the robot and the technician.

[0546] Input: Technician's response

[0547] Output: Notification of adjusted maintenance date and time

[0548] 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.

[0549] This invention is a system that uses AI and an emotion engine to automate the process of searching for optimal candidates, sending scouting emails, and arranging interview schedules in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0550] 1. Enter the requirements required by the company

[0551] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.) The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database.

[0552] 2. Search and extract the best candidates

[0553] The server generates a search query based on the saved detailed requirements data of companies and sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases. The server receives and analyzes the response data to extract candidates and score each candidate. Based on the scores, candidates with the highest match are ranked and listed.

[0554] 3. Automatic creation and sending of scout emails

[0555] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message that highlights the attractiveness of the company and is based on the candidate's skills and background. Furthermore, an emotion engine is used to recognize the candidate's current emotional state and adjust the content of the email accordingly. The generated scouting emails are then automatically sent to the candidate's email address.

[0556] 4. Scheduling an interview

[0557] Candidates who receive the scouting email can click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times on the form, and once the data is entered, it is sent to the server.

[0558] The server compares the schedule adjustment data received from the candidate with the schedule of the company representative. It uses an emotion engine to analyze the emotional state of the company representative and candidate and proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the company representative and the candidate.

[0559] Specific examples

[0560] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches its LinkedIn and GitHub databases. Ten highly matching candidates are listed, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your GitHub project (Python, R)."

[0561] Before sending an email, a sentiment engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently posted something positive, the tone of the email will be more positive as well.

[0562] When a candidate receives the email, they click the link to access the scheduling form and select a suitable date and time from the suggested options. The server then integrates this with the company representative's schedule and uses an emotion engine to analyze the emotional state of both parties before determining the optimal interview date and time.

[0563] The confirmed interview date and time is automatically notified to both the candidate and the company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the analysis results of the emotion engine.

[0564] In this way, the present invention is a system that, by combining an emotion engine, can further personalize the conventional recruitment process and make it more efficient and effective.

[0565] The processing flow will be explained below.

[0566] Step 1:

[0567] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. After entering the detailed requirements, the user presses the "Submit" button to send the data to the server.

[0568] Step 2:

[0569] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[0570] Step 3:

[0571] Based on the stored detailed requirement data, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[0572] Step 4:

[0573] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[0574] Step 5:

[0575] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[0576] Step 6:

[0577] For each candidate on the list, the server uses an emotion engine to tailor the content of scouting emails. Specifically, it analyzes the candidate's past email responses and social media posts to recognize their current emotional state, and customizes the tone and content of the email accordingly.

[0578] Step 7:

[0579] The server automatically generates and sends a customized scouting email to the candidate's email address, containing the scouting information and a link to schedule an interview.

[0580] Step 8:

[0581] After receiving the scout email on their device, the candidate clicks on the link in the email to access the schedule arrangement form, selects a suitable date and time from the suggested dates and times in the form, and submits the information they entered to the server.

[0582] Step 9:

[0583] The server receives the schedule adjustment data sent by the candidate. It then compares it with the company representative's schedule and proposes the optimal date and time for both parties. It uses an emotion engine to analyze the emotional state of the company representative and the candidate. The optimal interview date and time is determined taking this information into consideration.

[0584] Step 10:

[0585] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, and based on the results of the emotion engine's analysis, conveys sincere and positive messages to the candidate.

[0586] As a specific example, if a company wants to hire for a "data scientist" position, the company representative enters detailed requirements, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server uses these requirements to search databases such as LinkedIn and GitHub, and lists 10 candidates who most closely match the requirements. Before sending a scouting email, the emotion engine analyzes the candidate's emotional state and adjusts the content of the email. When scheduling an interview, the emotion engine is also used to consider the emotional state of both the company representative and the candidate, and the optimal date and time is suggested and notified.

[0587] Example 2

[0588] 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."

[0589] In corporate recruitment activities, quickly finding suitable candidates, efficiently contacting them, and arranging interview dates is a very time-consuming process. In particular, communication that does not take into consideration the emotional state of the candidate and the company representative can cause stress for both parties, which can ultimately reduce recruitment efficiency. A system that solves this problem and makes recruitment activities more efficient and effective is needed.

[0590] 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.

[0591] In this invention, the server includes means for inputting detailed requirements of a company, means for searching for and extracting candidates based on the detailed requirements, means for creating and sending automatic scout emails to the candidates, means for arranging interview dates with candidates who have received the scout email, means having an emotion engine for analyzing the emotional states of the candidates and company personnel, means for adjusting the content of the email based on the emotion analysis results, and means for proposing the optimal interview date and time based on the emotion analysis results.This not only streamlines the process from searching for candidates to arranging interview dates and times, but also makes use of the emotion engine to enable less stressful communication for both candidates and company personnel.

[0592] "Company's detailed requirements" are the specific conditions and standards that a company requires for the position (e.g., work history, skills, years of experience, industry knowledge, etc.).

[0593] A "candidate" is an individual whom a company considers for recruitment purposes.

[0594] The "emotion engine" is software that analyzes the emotional state of candidates and company representatives and adjusts the system's operation based on the analysis results.

[0595] A "scout email" is an email sent by a company to a candidate to convey their interest in hiring.

[0596] "Interview scheduling" is the process of deciding the date and time of the interview, taking into consideration the convenience of the company representative and the candidate.

[0597] An "external database" is a database that exists outside the system and provides information about candidates (e.g., a social networking service or an educational institution's database).

[0598] "Search and extraction" is the process of finding and retrieving matching information from a database based on specified criteria.

[0599] "Analysis" is the process of analyzing input data or acquired data to find meaning and value.

[0600] "Storage" is the process of recording acquired data in a storage medium such as a database so that it can be retrieved when needed.

[0601] "Automatic creation" is the process by which the system automatically generates the necessary information and content without human intervention.

[0602] "Proposing the optimal interview date and time" means presenting the most suitable interview date and time for both parties based on the analysis results of the emotion engine, etc.

[0603] This invention is a system that combines multiple pieces of hardware and software to streamline corporate recruitment activities. This system automates all processes, including inputting the company's requirements, searching and extracting suitable candidates, creating and sending automatic scouting emails, and scheduling interviews. Specific implementation methods are described below.

[0604] 1. Enter the requirements required by the company

[0605] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill (work history, skills, years of experience, industry knowledge, etc.). The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database. This process uses a web browser, HTTP requests, and a database (e.g., MySQL or PostgreSQL).

[0606] 2. Search and extract the best candidates

[0607] The server generates a search query based on the company's detailed requirements data and sends an API request to various external databases (e.g., social networking services, educational institution databases). The received response data is analyzed using a machine learning algorithm (e.g., Python's scikit-learn or TensorFlow) to score candidates. Finally, a list of candidates with high matching scores is generated.

[0608] 3. Automatic creation and sending of scout emails

[0609] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message highlighting the company's attractiveness and based on the candidate's skills and experience. Furthermore, an emotion engine (e.g., Python's NLTK or TextBlob) is used to analyze the candidate's emotional state and adjust the email content accordingly. The generated scouting emails are automatically sent using Python's smtplib library.

[0610] 4. Scheduling an interview

[0611] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times, enters the information, and the data is sent to the server. The server compares the received schedule arrangement data with the schedule of the company representative, analyzes the emotional state of the candidate and company representative using an emotion engine, and then proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative.

[0612] Specific examples

[0613] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches databases such as LinkedIn and GitHub. A list of 10 highly matching candidates is generated, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your project."

[0614] Before sending the email, the emotion engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently made positive posts, the tone of the email will be positive to match. When the candidate receives the email, clicks the link to access the scheduling form and selects a suitable date and time from the suggested dates and times, the server compares this with the company representative's schedule and uses the emotion engine to analyze the emotional states of both parties to determine the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the results of the emotion engine's analysis.

[0615] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0616] Step 1:

[0617] Enter your company's detailed requirements

[0618] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. Specifically, the user launches a web browser, accesses the company's dedicated login page, enters the required information in each field, and clicks the "Submit" button. This input data (detailed requirements) is sent from the browser to the terminal via a POST request.

[0619] Input: Detailed requirement data entered by the user into the web form

[0620] Output: Detailed requirements data submitted

[0621] Step 2:

[0622] Parsing and storing detailed requirements data

[0623] The device sends the entered detailed requirements data to the server, which receives the data, analyzes it, and stores it in a corporate database. Specifically, a server-side script (e.g., Python, Java, etc.) receives the data, analyzes and organizes it using natural language processing, and then stores it in a database (e.g., MySQL or PostgreSQL).

[0624] Input: Detailed requirements data entered by the user

[0625] Output: Detailed requirements data analyzed and stored in a corporate database

[0626] Step 3:

[0627] Generate and submit candidate search queries

[0628] The server generates a search query based on the stored detailed requirements data of the company. The server then uses this search query to send API requests to various external databases (e.g., social networking services or educational institution databases). Specifically, the server generates a query using natural language processing technology and SQL or API requests, and sends it to the external database as an HTTP request.

[0629] Input: Saved detailed company requirements data

[0630] Output: The search query sent to the external database

[0631] Step 4:

[0632] Receiving and analyzing candidate data

[0633] The server receives and parses the response data from the external database. Specifically, it parses the returned data in JSON or XML format using Python's json module or other compatible libraries to extract candidate information.

[0634] Input: Response data from an external database

[0635] Output: Parsed candidate data

[0636] Step 5:

[0637] Candidate scoring and shortlisting

[0638] The server uses a machine learning algorithm to score the analyzed candidate data. Specifically, it uses Python libraries such as scikit-learn and TensorFlow to calculate the degree to which the candidate's skills match the detailed requirements, assigns a score, and then ranks and lists the candidates based on the score.

[0639] Input: Parsed candidate data

[0640] Output: Scored candidate list

[0641] Step 6:

[0642] Generate and send scout emails

[0643] The server generates scouting emails based on the scored candidate list. These emails highlight the company's attractiveness and include personalized messages based on the candidate's skills and experience. It also uses an emotion engine to analyze the candidate's emotional state and adjusts the email content accordingly. Specifically, it generates the email body using a template engine, performs emotion analysis using Python's NLTK and TextBlob, and sends the email using the smtplib library.

[0644] Input: Scored candidate list and sentiment engine analysis results

[0645] Output: Scout email sent

[0646] Step 7:

[0647] Scheduling an interview

[0648] Candidates receive the scouting email and click on the link in the email to access the scheduling form, which they do by clicking the link, opening the page in their browser, selecting a suitable date and time from the suggested dates and times, and submitting the form.

[0649] Input: Clicking on the link in the scout email and entering the schedule adjustment data

[0650] Output: Sent schedule adjustment data

[0651] Step 8:

[0652] Processing and notification of scheduling data

[0653] The server receives the schedule adjustment data sent by the candidate and compares it with the schedule of the company representative. Specifically, it retrieves the company representative's calendar information from the database and compares it with the candidate's input data to determine the optimal interview date and time. At this time, an emotion engine is used to analyze the emotional states of both parties and propose the optimal date and time. Finally, the confirmed interview date and time is automatically notified to both the company representative and the candidate.

[0654] Input: Company personnel schedule data and candidate schedule adjustment data

[0655] Output: Confirmed interview date and time, and notification sent

[0656] (Application example 2)

[0657] 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."

[0658] Modern recruitment activities involve many time-consuming tasks, such as searching for candidates, sending scouting emails, and scheduling interviews. Furthermore, companies must efficiently utilize numerous databases and information sources to find the best candidates to meet their requirements. While analyzing emotional states and providing personalized content could potentially improve the effectiveness of recruitment activities, there is a lack of methods to achieve this. Therefore, to efficiently complete these tasks, a system is needed that can search for candidates based on a company's detailed requirements, analyze their emotional states, and recommend and notify them of personalized content.

[0659] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting detailed requirements of a company, a means for searching for and extracting candidates based on the detailed requirements, a means for automatically creating and sending scout emails to the candidates, a means for arranging interview dates with candidates who have received the scout emails, a means for analyzing the user's emotional state and recommending personalized content, and a means for notifying the user of the recommended content. This makes it possible to improve the efficiency of companies' recruitment activities and provide personalized content based on their emotional state.

[0660] The "means for entering detailed company requirements" is an interface for entering information such as the skills and experience required for the job sought by company personnel.

[0661] "Means for searching and extracting candidates" refers to a system that searches for candidate information from social networking services and educational institution databases based on the detailed requirements of a company, and identifies suitable candidates.

[0662] The "means for automatically creating and sending scouting emails" is a mechanism for automatically creating email content for selected candidates and sending messages that appeal to the attractiveness of the company.

[0663] The "means of arranging interview dates" is a system that checks the availability of candidates who receive scouting emails with that of company personnel to determine the most suitable interview date and time.

[0664] "Means for analyzing a user's emotional state" refers to an algorithm that identifies a user's emotions from social media posts, messages, etc. and evaluates their state.

[0665] A "means for recommending personalized content" is a system for identifying and recommending optimal content to a user based on the analyzed emotional state of the user.

[0666] "Means for notifying users of recommended content" means a mechanism for communicating recommended content to users by push notification or other means.

[0667] This invention is a system that searches for and extracts candidates based on the detailed requirements of a company, automatically sends scouting emails, and schedules interviews. It can also analyze the user's emotional state and recommend and notify personalized content. Specific embodiments for implementing the invention are described below.

[0668] First, a company representative uses a dedicated web interface to enter detailed requirements for the job they are recruiting for (e.g., skills, years of experience, industry knowledge, etc.). This data is sent from the terminal to a server, which analyzes the received data and stores it in a company database. The server software used is a database management system (e.g., MySQL) or a web server (e.g., Apache).

[0669] Next, the server generates a search query based on the saved detailed requirements data of the companies and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. After receiving the response data, the server analyzes it to extract candidates, and scores and ranks each candidate.

[0670] The server automatically generates and sends scouting emails to ranked candidates. These emails include a message highlighting the attractiveness of the company and personalized content based on the candidate's skills and experience. An emotion engine is used to recognize the candidate's emotional state and adjust the email content accordingly. This process uses an emotion analysis algorithm (e.g., Google Cloud Natural Language API).

[0671] When a candidate receives a scouting email and clicks on the link in the email, they can access a schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times and enters the information, which is then sent to the server. The server compares the candidate's data with the company representative's schedule, uses an emotion engine to suggest the optimal interview date and time, and notifies both the company representative and the candidate of the confirmed date and time.

[0672] It also includes a function to analyze the user's emotional state and recommend personalized content. The server identifies the user's emotions from social media posts and messages and evaluates their state. Based on this, it identifies the most suitable content (e.g., videos, articles, music, etc.) and notifies the user. The algorithms used include a voice emotion recognition engine (e.g., IBM Watson) and a content recommendation system (e.g., TensorFlow).

[0673] For example, if the user is "feeling stressed," the system will recommend relaxation music or videos with a relaxing effect. Examples of prompts for the generative AI model are:

[0674] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[0675] As described above, the present invention streamlines corporate recruitment activities and provides personalized content that matches the user's emotional state, thereby realizing more effective human resource management.

[0676] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0677] Step 1:

[0678] As a means of inputting detailed company requirements, the terminal uses a dedicated web interface to input detailed requirements (skills, years of experience, industry knowledge, etc.) required for the job being recruited. The input data is sent to the server as the company's detailed requirements.

[0679] Step 2:

[0680] The server analyzes the received detailed requirement data and stores it in the company database. The database management system used here is MySQL as an example. The input data is the detailed requirement information, and the output is the analyzed requirement information stored in the company database.

[0681] Step 3:

[0682] The server generates a search query based on the stored detailed requirements data and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. The server receives and analyzes the response data to extract candidates, score each candidate, and rank them. The input data are the detailed requirements and candidate information from the social networking services, and the output is a scored candidate list.

[0683] Step 4:

[0684] The server automatically generates scouting emails for ranked candidates. These scouting emails include a message highlighting the company's attractiveness and personalized content based on the candidate's skills and experience. An emotion engine (e.g., Google Cloud Natural Language API) is used to recognize the candidate's emotional state and adjust the email content accordingly. The input data is candidate information and the results of emotion analysis, and the output is a personalized scouting email.

[0685] Step 5:

[0686] The server sends the generated scout email to the candidate's email address. The candidate clicks the link in the email to access the schedule adjustment form. They select a convenient date and time from the suggested dates and times on their device and enter the data, which is then sent to the server. The input data is the candidate's selected date and time, and the output is the schedule adjustment data sent to the server.

[0687] Step 6:

[0688] The server compares the scheduling data received from the candidate with the company's schedule and uses an emotion engine to suggest the optimal interview date and time. The algorithms used include an emotion analysis algorithm (e.g., Google Cloud Natural Language API). The input data is the candidate's scheduling data and the company's schedule, and the output is the optimal interview date and time.

[0689] Step 7:

[0690] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time. This notification is also conveyed in a sincere and positive manner based on the analysis results of the emotion engine. The input data is the confirmed interview date and time, and the output is the notification to the company representative and the candidate.

[0691] Step 8:

[0692] Furthermore, a means of analyzing the user's emotional state and recommending personalized content is added. The server identifies the user's emotions from social media posts and messages and evaluates their state. The emotion analysis engine used utilizes a voice emotion recognition engine (e.g., IBM Watson). The input data are the user's posts and messages, and the output is the analyzed emotional state.

[0693] Step 9:

[0694] The server identifies and recommends appropriate content (videos, articles, music, etc.) based on the analyzed user emotional state. This process uses a content recommendation system (e.g., TensorFlow). The input data is the analyzed emotional state, and the output is the recommended content.

[0695] Step 10:

[0696] The server notifies the user of the recommended content by push notification or other means. The input data is the recommended content, and the output is the notification to the user.

[0697] For example, if the user is analyzed as "feeling stressed," the server will recommend relaxation music or videos with a relaxing effect. An example of a prompt for the generative AI model is as follows:

[0698] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[0699] 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.

[0700] 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.

[0701] 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.

[0702] [Third embodiment]

[0703] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0704] 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.

[0705] 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).

[0706] 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.

[0707] 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.

[0708] 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).

[0709] 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.

[0710] 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.

[0711] 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.

[0712] 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.

[0713] 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.

[0714] 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."

[0715] This invention is a system that uses AI to search for optimal candidates, send scouting emails, and automate the scheduling of interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0716] 1. Enter the requirements required by the company

[0717] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill, including work history, skills, years of experience, industry knowledge, etc. Once the input is complete, the data is sent from the terminal to the server.

[0718] 2. Search and extract the best candidates

[0719] The server analyzes the received company's detailed requirements and generates an appropriate search query. It then connects with LinkedIn, GitHub, and other social networking services and educational institution databases to search and extract the best candidates. It scores each candidate and lists the candidates with the highest match.

[0720] 3. Automatic creation and sending of scout emails

[0721] The server automatically generates scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[0722] 4. Scheduling an interview

[0723] Candidates who receive the scout email can click the link in the email on their device to access the schedule adjustment form. The candidate can then select a suitable date and time from the suggested dates and times entered in the form, and the data will be sent to the server.

[0724] Specific examples

[0725] For example, if a company wants to hire for a "software engineer" position, the user (company representative) enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information and searches for candidates with the relevant projects and experience on LinkedIn and GitHub. The server then lists 10 candidates who match closely, and automatically sends them a scouting email stating, "We're impressed with your Python and JavaScript projects on GitHub."

[0726] When a candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time. The determined interview date and time is automatically notified to both the candidate and the company representative.

[0727] This allows companies to conduct recruitment activities quickly and efficiently without hassle. The system automates the entire recruitment process, from talent search and scouting to interview arrangements, and is a system that can greatly streamline a company's recruitment operations.

[0728] The processing flow will be explained below.

[0729] Step 1:

[0730] The user (company representative) accesses a dedicated web interface and enters the detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.). After entering the information, they press the "Submit" button to send the data to the server.

[0731] Step 2:

[0732] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[0733] Step 3:

[0734] Based on the stored detailed requirements, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[0735] Step 4:

[0736] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[0737] Step 5:

[0738] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[0739] Step 6:

[0740] The server automatically creates scouting emails for the listed candidates. These emails include personalized messages that highlight the attractiveness of the company and are based on the candidate's background and skills. These emails are generated based on templates.

[0741] Step 7:

[0742] The server automatically sends the generated scouting email to the candidate's email address, including a link to schedule an interview.

[0743] Step 8:

[0744] Candidates receive the scout email on their device, click the link in the email to access the schedule arrangement form, select a suitable date and time from the suggested dates and times, and press the "Submit" button.

[0745] Step 9:

[0746] The server receives the schedule adjustment data sent by the candidate, then compares it with the schedule of the company representative to determine the best interview date and time for both parties.

[0747] Step 10:

[0748] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, including details of the interview and login information.

[0749] The above are the specific processing steps of this system.

[0750] Example 1

[0751] 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."

[0752] In corporate recruitment activities, tasks such as searching for suitable candidates, generating and sending scouting emails, and scheduling interviews are often performed manually, which takes a lot of time and effort. There is also the risk of missing the timing to communicate with candidates or overlooking suitable talent. It is essential to solve these problems and improve the efficiency and effectiveness of the recruitment process.

[0753] 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.

[0754] In this invention, the server includes: a means for a user to input detailed job requirements; a means for analyzing candidate information based on the detailed requirements and generating a search query; a means for linking with multiple databases to search, extract, and score candidates; a means for automatically generating and sending personalized scout emails to candidates; a means for candidates who receive the scout email to access an interview scheduling form and enter their desired date and time; and a means for receiving the scheduling information provided by the candidate, integrating it with the schedule of the company representative, and determining and notifying the candidate of the optimal interview date and time. This enables companies to efficiently and quickly search for optimal candidates, send scout emails, and automate the process of scheduling interviews.

[0755] "User" refers to the person in charge of recruitment activities at a company or organization.

[0756] "Detailed job requirements" refer to the skills, years of experience, work history, industry knowledge, and other conditions required for the job a company is looking to hire for.

[0757] "Search Query" refers to a search dataset or command generated based on detailed job requirements.

[0758] "Candidate Information" refers to data about job seekers, such as their work history, skills, and project experience.

[0759] "Database" refers to a data storage system where candidate information is stored, such as LinkedIn or GitHub.

[0760] "Scoring" refers to the process of comparing and evaluating detailed job requirements with candidate information from search results and quantifying the degree of match.

[0761] A "scouting email" is an email sent to candidates who match a company's job requirements to express interest in hiring them.

[0762] "Scheduling Form" refers to an online form that allows candidates to enter their preferred interview date and time.

[0763] "Server" refers to the central computer system that handles all of the above processing and data management.

[0764] The present invention is a system that uses a generative AI model to search for optimal candidates, automates the sending of scouting emails, and schedules interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0765] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to hire, such as work history, skills, years of experience, industry knowledge, etc. This data is sent from the terminal to the server.

[0766] The server analyzes the received detailed requirements using natural language processing (NLP) technology and generates an appropriate search query. Based on the generated search query, the server connects to multiple databases, including LinkedIn and GitHub, to search for and extract candidates. In this process, the server collects information on multiple candidates and performs scoring to create a list of candidates with high match scores.

[0767] The server automatically generates personalized scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are sent to the candidate's email address.

[0768] Candidates receive a scout email and click on the link in the email to access the schedule adjustment form. In the schedule adjustment form, candidates can select a suitable date and time from the proposed interview dates and times. This data is sent to the server via the terminal.

[0769] The server integrates the candidate's desired date and time with the company's schedule to determine the optimal interview date and time. The server then notifies both the candidate and the company's representative of the determined interview date and time. This allows companies to conduct recruitment activities quickly and efficiently without hassle.

[0770] For example, if a company is looking to hire for a "software engineer" position, the user enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information, searches for candidates with the relevant projects and experience on LinkedIn and GitHub, and automatically sends them a scouting email. When the candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company's schedule to determine the optimal interview date and time, and automatically notifies the candidate.

[0771] The above system can improve the efficiency of companies' recruitment activities and significantly reduce the time and effort required. The effects of the present invention can be maximized through this specific implementation method.

[0772] An example prompt is, "Please explain in detail the steps involved in a system that automates a company's recruitment activities, from entering the required qualifications to scheduling an interview."

[0773] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0774] Step 1:

[0775] Users access a dedicated web interface and enter detailed job requirements, including work history, skills, years of experience, and industry knowledge.

[0776] The entered job requirements (input: work history, skills, years of experience, industry knowledge, etc.) are sent from the terminal to the server (output: JSON format data).

[0777] Step 2:

[0778] Job requirement data transmitted from the terminal to the server is received.

[0779] The server parses the JSON data and extracts the necessary information (input: JSON format data, output: parsed data object).

[0780] Step 3:

[0781] The server generates a search query based on the analysis results.

[0782] The server uses natural language processing technology to structure the job requirements and convert them into a search query (input: analysis result data object, output: search query).

[0783] Step 4:

[0784] The server uses the generated search query to connect with multiple databases, such as LinkedIn and GitHub, to search and extract candidate information.

[0785] The server collects the search results and scores each candidate (input: search query, output: scored candidate list).

[0786] Step 5:

[0787] The server automatically generates personalized scouting emails for the listed candidates.

[0788] The server uses a generative AI model to create a scouting email that includes wording that appeals to the company and a message about the candidate's skills and background (input: scored candidate list, output: scouting email).

[0789] Step 6:

[0790] The server sends the generated scout email to the candidate's email address.

[0791] The server monitors the status of the email sending and confirms the success of the sending (input: scout email and candidate email address, output: email sending status).

[0792] Step 7:

[0793] Candidates will receive a scouting email and click on the link in the email to access the scheduling form.

[0794] The candidate selects a convenient date and time from the suggested dates and times displayed on the form and sends the input data from the terminal to the server (input: date selected by the candidate, output: date data sent to the server).

[0795] Step 8:

[0796] The server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time.

[0797] The server notifies both the candidate and the company representative of the decided interview date and time (input: candidate's desired date and time and company representative's schedule, output: notification of decided interview date and time).

[0798] The above processing steps automate the recruitment process, enabling companies to conduct recruitment activities efficiently and effectively.

[0799] (Application example 1)

[0800] 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."

[0801] Traditionally, the process for companies to find suitable candidates, send out scouting emails, and schedule interviews has often been manual, requiring time and effort. Furthermore, when it comes to maintaining and repairing factory robots, finding and contacting technicians at the right time can be difficult, resulting in production line downtime. There is a need to solve these issues and streamline corporate and factory operations.

[0802] 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.

[0803] In this invention, the server includes means for inputting detailed requirements of a company, means for searching and extracting candidates based on the detailed requirements, means for automatically creating and sending scout emails to the candidates, means for arranging interview dates with candidates who have received the scout emails, and means for the robot to perform self-diagnosis, search for specialized engineers, and arrange maintenance schedules. This allows companies to conduct recruitment activities efficiently, and also makes it possible to quickly and efficiently perform maintenance and repairs of factory robots.

[0804] "Detailed company requirements" refers to the specific hiring conditions, such as the skills, years of experience, and industry knowledge required for the job the company is seeking.

[0805] "Candidate Search and Selection Means" means a means capable of locating and selecting suitable candidates from a database based on specified detailed requirements.

[0806] A "scout email" refers to a recruiting email sent by a company to selected candidates as part of its recruitment activities.

[0807] "Means for arranging interview dates" refers to a means that has the function of arranging interview dates and times between companies and candidates and determining the optimal interview schedule.

[0808] "Self-diagnosis" refers to the ability of a machine or system to monitor its own condition and automatically determine malfunctions or situations requiring maintenance.

[0809] "Professional technician" means a person who has particular techniques or skills and who has specialized knowledge to perform the maintenance and repair of machines and systems.

[0810] "Means for coordinating maintenance schedules" refers to the means by which a machine or system has the ability to coordinate and confirm optimal maintenance dates and times with a specialist.

[0811] "Social networking service" refers to a web service that enables individuals and businesses to exchange information and connect with each other over the Internet.

[0812] "Institutional database" refers to a database of alumni information and research results held by an educational institution such as a school or university.

[0813] This invention provides a system that streamlines corporate recruitment activities and factory robot maintenance. This system includes functions for inputting detailed requirements, searching and extracting candidates, automatically generating and sending scouting emails, arranging interview dates, and also for robot self-diagnosis and searching and scheduling maintenance engineers.

[0814] System configuration

[0815] 1. Enter detailed requirements

[0816] Users (company personnel) use a web interface to input detailed requirements for the job they are looking to hire for, such as skills, years of experience, industry knowledge, etc. The input data is then sent from the company's terminal to the server.

[0817] 2. Candidate search and selection

[0818] The server analyzes the details entered, generates the appropriate search query, and then connects with LinkedIn and other social networking services, as well as educational institution databases, to find and extract the best candidates.

[0819] 3. Automatic creation and sending of scout emails

[0820] The server automatically generates scouting emails for candidates listed in the search results. The emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[0821] 4. Scheduling an interview

[0822] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times entered in the form, and the data is sent to the server. The server combines the candidate's desired date and time with the company representative's schedule, determines the optimal interview date and time, and notifies both parties.

[0823] 5. Robot self-diagnosis

[0824] The factory robots are self-diagnostic and monitor their performance, and if there is an error or maintenance required, the robots send that information to a server.

[0825] 6. Searching for and scheduling specialists

[0826] The server analyzes the error information received from the robot and searches for and extracts the appropriate technician. Various databases are used for the search, and a maintenance request message is automatically sent to the appropriate technician. After the technician replies, the server coordinates the optimal maintenance date and time between the robot and the technician, and notifies both parties of the decided date and time.

[0827] Example

[0828] Software used:

[0829] Python, Requests library, LinkedIn API

[0830] Hardware used:

[0831] Corporate terminals, servers, factory robots, internet-connected devices

[0832] Example prompt sentence:

[0833] Robot diagnosis results:

[0834] Error code: E404

[0835] Error: Mechanical failure in arm joint

[0836] Technician search query:

[0837] "technician+mechanical+failure+arm+joint"

[0838] Specific message example:

[0839] Subject: Urgent Maintenance Required for Arm Joint Failure

[0840] Dear [Technician Name],

[0841] Our robot has detected a mechanical failure in its arm joint and we require immediate assistance. Can you assist in resolving this issue at your earliest convenience?

[0842] Best,

[0843] Robot Maintenance Team

[0844] This allows companies to conduct recruitment activities quickly and efficiently without hassle, and also enables maintenance and repair of factory robots to be carried out quickly and efficiently.

[0845] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0846] Step 1:

[0847] The user enters details of the company's requirements into a web interface, including the skills required for the job, years of experience, industry knowledge, etc. This data is then sent from the terminal to the server.

[0848] Input: Detailed job requirements (skills, years of experience, industry knowledge)

[0849] Output: Detailed requirements data sent to the server

[0850] Step 2:

[0851] The server analyzes the received detailed requirements data and generates appropriate search queries that are used against social networking services and educational institution databases.

[0852] Input: Detailed requirement data

[0853] Output: Search query

[0854] Step 3:

[0855] The server uses the generated search query to search and extract the best candidates from LinkedIn and other databases, which are then scored and listed in order of best match.

[0856] Input: Search query

[0857] Output: List of candidates

[0858] Step 4:

[0859] The server automatically generates and sends scouting emails to the listed candidates, including a personalized message about the company's appeal and the candidate's skills and background.

[0860] Input: Listed candidates

[0861] Output: Scout email sent

[0862] Step 5:

[0863] When a candidate receives a scout email and clicks on the link in the email, they will access the schedule adjustment form. The candidate will select a suitable date and time from the suggested dates and times entered in the form and enter it. This will send the schedule data to the server.

[0864] Input: Candidate's action when clicking the link in the scouting email

[0865] Output: Schedule data sent to the server

[0866] Step 6:

[0867] The server combines the desired date and time sent by the candidate with the schedule of the company representative to determine the optimal interview date and time, and notifies both parties of the determined interview date and time.

[0868] Input: Candidate's desired date and time, company representative's schedule data

[0869] Output: Notification of the decided interview date and time

[0870] Step 7:

[0871] Factory robots perform self-diagnosis and, if a malfunction or maintenance is detected, send error information to a server.

[0872] Input: Robot self-diagnosis results

[0873] Output: Error information sent to the server

[0874] Step 8:

[0875] The server analyzes the error information received from the robot, searches for and extracts the appropriate technician, and retrieves information about the technician from the technician database.

[0876] Input: Robot error information

[0877] Output: Searched and extracted engineers

[0878] Step 9:

[0879] The server automatically generates and sends a maintenance request message to the extracted technician.

[0880] Input: Extracted technician information

[0881] Output: Maintenance request message sent

[0882] Step 10:

[0883] The technician responds to the maintenance request, and the server adjusts the maintenance date and time based on the response. The adjusted date and time are notified to the robot and the technician.

[0884] Input: Technician's response

[0885] Output: Notification of adjusted maintenance date and time

[0886] 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.

[0887] This invention is a system that uses AI and an emotion engine to automate the process of searching for optimal candidates, sending scouting emails, and arranging interview schedules in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[0888] 1. Enter the requirements required by the company

[0889] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.) The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database.

[0890] 2. Search and extract the best candidates

[0891] The server generates a search query based on the saved detailed requirements data of companies and sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases. The server receives and analyzes the response data to extract candidates and score each candidate. Based on the scores, candidates with the highest match are ranked and listed.

[0892] 3. Automatic creation and sending of scout emails

[0893] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message that highlights the attractiveness of the company and is based on the candidate's skills and background. Furthermore, an emotion engine is used to recognize the candidate's current emotional state and adjust the content of the email accordingly. The generated scouting emails are then automatically sent to the candidate's email address.

[0894] 4. Scheduling an interview

[0895] Candidates who receive the scouting email can click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times on the form, and once the data is entered, it is sent to the server.

[0896] The server compares the schedule adjustment data received from the candidate with the schedule of the company representative. It uses an emotion engine to analyze the emotional state of the company representative and candidate and proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the company representative and the candidate.

[0897] Specific examples

[0898] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches its LinkedIn and GitHub databases. Ten highly matching candidates are listed, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your GitHub project (Python, R)."

[0899] Before sending an email, a sentiment engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently posted something positive, the tone of the email will be more positive as well.

[0900] When a candidate receives the email, they click the link to access the scheduling form and select a suitable date and time from the suggested options. The server then integrates this with the company representative's schedule and uses an emotion engine to analyze the emotional state of both parties before determining the optimal interview date and time.

[0901] The confirmed interview date and time is automatically notified to both the candidate and the company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the analysis results of the emotion engine.

[0902] In this way, the present invention is a system that, by combining an emotion engine, can further personalize the conventional recruitment process and make it more efficient and effective.

[0903] The processing flow will be explained below.

[0904] Step 1:

[0905] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. After entering the detailed requirements, the user presses the "Submit" button to send the data to the server.

[0906] Step 2:

[0907] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[0908] Step 3:

[0909] Based on the stored detailed requirement data, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[0910] Step 4:

[0911] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[0912] Step 5:

[0913] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[0914] Step 6:

[0915] For each candidate on the list, the server uses an emotion engine to tailor the content of scouting emails. Specifically, it analyzes the candidate's past email responses and social media posts to recognize their current emotional state, and customizes the tone and content of the email accordingly.

[0916] Step 7:

[0917] The server automatically generates and sends a customized scouting email to the candidate's email address, containing the scouting information and a link to schedule an interview.

[0918] Step 8:

[0919] After receiving the scout email on their device, the candidate clicks on the link in the email to access the schedule arrangement form, selects a suitable date and time from the suggested dates and times in the form, and submits the information they entered to the server.

[0920] Step 9:

[0921] The server receives the schedule adjustment data sent by the candidate. It then compares it with the company representative's schedule and proposes the optimal date and time for both parties. It uses an emotion engine to analyze the emotional state of the company representative and the candidate. The optimal interview date and time is determined taking this information into consideration.

[0922] Step 10:

[0923] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, and based on the results of the emotion engine's analysis, conveys sincere and positive messages to the candidate.

[0924] As a specific example, if a company wants to hire for a "data scientist" position, the company representative enters detailed requirements, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server uses these requirements to search databases such as LinkedIn and GitHub, and lists 10 candidates who most closely match the requirements. Before sending a scouting email, the emotion engine analyzes the candidate's emotional state and adjusts the content of the email. When scheduling an interview, the emotion engine is also used to consider the emotional state of both the company representative and the candidate, and the optimal date and time is suggested and notified.

[0925] Example 2

[0926] 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."

[0927] In corporate recruitment activities, quickly finding suitable candidates, efficiently contacting them, and arranging interview dates is a very time-consuming process. In particular, communication that does not take into consideration the emotional state of the candidate and the company representative can cause stress for both parties, which can ultimately reduce recruitment efficiency. A system that solves this problem and makes recruitment activities more efficient and effective is needed.

[0928] 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.

[0929] In this invention, the server includes means for inputting detailed requirements of a company, means for searching for and extracting candidates based on the detailed requirements, means for creating and sending automatic scout emails to the candidates, means for arranging interview dates with candidates who have received the scout email, means having an emotion engine for analyzing the emotional states of the candidates and company personnel, means for adjusting the content of the email based on the emotion analysis results, and means for proposing the optimal interview date and time based on the emotion analysis results.This not only streamlines the process from searching for candidates to arranging interview dates and times, but also makes use of the emotion engine to enable less stressful communication for both candidates and company personnel.

[0930] "Company's detailed requirements" are the specific conditions and standards that a company requires for the position (e.g., work history, skills, years of experience, industry knowledge, etc.).

[0931] A "candidate" is an individual whom a company considers for recruitment purposes.

[0932] The "emotion engine" is software that analyzes the emotional state of candidates and company representatives and adjusts the system's operation based on the analysis results.

[0933] A "scout email" is an email sent by a company to a candidate to convey their interest in hiring.

[0934] "Interview scheduling" is the process of deciding the date and time of the interview, taking into consideration the convenience of the company representative and the candidate.

[0935] An "external database" is a database that exists outside the system and provides information about candidates (e.g., a social networking service or an educational institution's database).

[0936] "Search and extraction" is the process of finding and retrieving matching information from a database based on specified criteria.

[0937] "Analysis" is the process of analyzing input data or acquired data to find meaning and value.

[0938] "Storage" is the process of recording acquired data in a storage medium such as a database so that it can be retrieved when needed.

[0939] "Automatic creation" is the process by which the system automatically generates the necessary information and content without human intervention.

[0940] "Proposing the optimal interview date and time" means presenting the most suitable interview date and time for both parties based on the analysis results of the emotion engine, etc.

[0941] This invention is a system that combines multiple pieces of hardware and software to streamline corporate recruitment activities. This system automates all processes, including inputting the company's requirements, searching and extracting suitable candidates, creating and sending automatic scouting emails, and scheduling interviews. Specific implementation methods are described below.

[0942] 1. Enter the requirements required by the company

[0943] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill (work history, skills, years of experience, industry knowledge, etc.). The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database. This process uses a web browser, HTTP requests, and a database (e.g., MySQL or PostgreSQL).

[0944] 2. Search and extract the best candidates

[0945] The server generates a search query based on the company's detailed requirements data and sends an API request to various external databases (e.g., social networking services, educational institution databases). The received response data is analyzed using a machine learning algorithm (e.g., Python's scikit-learn or TensorFlow) to score candidates. Finally, a list of candidates with high matching scores is generated.

[0946] 3. Automatic creation and sending of scout emails

[0947] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message highlighting the company's attractiveness and based on the candidate's skills and experience. Furthermore, an emotion engine (e.g., Python's NLTK or TextBlob) is used to analyze the candidate's emotional state and adjust the email content accordingly. The generated scouting emails are automatically sent using Python's smtplib library.

[0948] 4. Scheduling an interview

[0949] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times, enters the information, and the data is sent to the server. The server compares the received schedule arrangement data with the schedule of the company representative, analyzes the emotional state of the candidate and company representative using an emotion engine, and then proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative.

[0950] Specific examples

[0951] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches databases such as LinkedIn and GitHub. A list of 10 highly matching candidates is generated, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your project."

[0952] Before sending the email, the emotion engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently made positive posts, the tone of the email will be positive to match. When the candidate receives the email, clicks the link to access the scheduling form and selects a suitable date and time from the suggested dates and times, the server compares this with the company representative's schedule and uses the emotion engine to analyze the emotional states of both parties to determine the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the results of the emotion engine's analysis.

[0953] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0954] Step 1:

[0955] Enter your company's detailed requirements

[0956] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. Specifically, the user launches a web browser, accesses the company's dedicated login page, enters the required information in each field, and clicks the "Submit" button. This input data (detailed requirements) is sent from the browser to the terminal via a POST request.

[0957] Input: Detailed requirement data entered by the user into the web form

[0958] Output: Detailed requirements data submitted

[0959] Step 2:

[0960] Parsing and storing detailed requirements data

[0961] The device sends the entered detailed requirements data to the server, which receives the data, analyzes it, and stores it in a corporate database. Specifically, a server-side script (e.g., Python, Java, etc.) receives the data, analyzes and organizes it using natural language processing, and then stores it in a database (e.g., MySQL or PostgreSQL).

[0962] Input: Detailed requirements data entered by the user

[0963] Output: Detailed requirements data analyzed and stored in a corporate database

[0964] Step 3:

[0965] Generate and submit candidate search queries

[0966] The server generates a search query based on the stored detailed requirements data of the company. The server then uses this search query to send API requests to various external databases (e.g., social networking services or educational institution databases). Specifically, the server generates a query using natural language processing technology and SQL or API requests, and sends it to the external database as an HTTP request.

[0967] Input: Saved detailed company requirements data

[0968] Output: The search query sent to the external database

[0969] Step 4:

[0970] Receiving and analyzing candidate data

[0971] The server receives and parses the response data from the external database. Specifically, it parses the returned data in JSON or XML format using Python's json module or other compatible libraries to extract candidate information.

[0972] Input: Response data from an external database

[0973] Output: Parsed candidate data

[0974] Step 5:

[0975] Candidate scoring and shortlisting

[0976] The server uses a machine learning algorithm to score the analyzed candidate data. Specifically, it uses Python libraries such as scikit-learn and TensorFlow to calculate the degree to which the candidate's skills match the detailed requirements, assigns a score, and then ranks and lists the candidates based on the score.

[0977] Input: Parsed candidate data

[0978] Output: Scored candidate list

[0979] Step 6:

[0980] Generate and send scout emails

[0981] The server generates scouting emails based on the scored candidate list. These emails highlight the company's attractiveness and include personalized messages based on the candidate's skills and experience. It also uses an emotion engine to analyze the candidate's emotional state and adjusts the email content accordingly. Specifically, it generates the email body using a template engine, performs emotion analysis using Python's NLTK and TextBlob, and sends the email using the smtplib library.

[0982] Input: Scored candidate list and sentiment engine analysis results

[0983] Output: Scout email sent

[0984] Step 7:

[0985] Scheduling an interview

[0986] Candidates receive the scouting email and click on the link in the email to access the scheduling form, which they do by clicking the link, opening the page in their browser, selecting a suitable date and time from the suggested dates and times, and submitting the form.

[0987] Input: Clicking on the link in the scout email and entering the schedule adjustment data

[0988] Output: Sent schedule adjustment data

[0989] Step 8:

[0990] Processing and notification of scheduling data

[0991] The server receives the schedule adjustment data sent by the candidate and compares it with the schedule of the company representative. Specifically, it retrieves the company representative's calendar information from the database and compares it with the candidate's input data to determine the optimal interview date and time. At this time, an emotion engine is used to analyze the emotional states of both parties and propose the optimal date and time. Finally, the confirmed interview date and time is automatically notified to both the company representative and the candidate.

[0992] Input: Company personnel schedule data and candidate schedule adjustment data

[0993] Output: Confirmed interview date and time, and notification sent

[0994] (Application example 2)

[0995] 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."

[0996] Modern recruitment activities involve many time-consuming tasks, such as searching for candidates, sending scouting emails, and scheduling interviews. Furthermore, companies must efficiently utilize numerous databases and information sources to find the best candidates to meet their requirements. While analyzing emotional states and providing personalized content could potentially improve the effectiveness of recruitment activities, there is a lack of methods to achieve this. Therefore, to efficiently complete these tasks, a system is needed that can search for candidates based on a company's detailed requirements, analyze their emotional states, and recommend and notify them of personalized content.

[0997] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting detailed requirements of a company, a means for searching for and extracting candidates based on the detailed requirements, a means for automatically creating and sending scout emails to the candidates, a means for arranging interview dates with candidates who have received the scout emails, a means for analyzing the user's emotional state and recommending personalized content, and a means for notifying the user of the recommended content. This makes it possible to improve the efficiency of companies' recruitment activities and provide personalized content based on their emotional state.

[0998] The "means for entering detailed company requirements" is an interface for entering information such as the skills and experience required for the job sought by company personnel.

[0999] "Means for searching and extracting candidates" refers to a system that searches for candidate information from social networking services and educational institution databases based on the detailed requirements of a company, and identifies suitable candidates.

[1000] The "means for automatically creating and sending scouting emails" is a mechanism for automatically creating email content for selected candidates and sending messages that appeal to the attractiveness of the company.

[1001] The "means of arranging interview dates" is a system that checks the availability of candidates who receive scouting emails with that of company personnel to determine the most suitable interview date and time.

[1002] "Means for analyzing a user's emotional state" refers to an algorithm that identifies a user's emotions from social media posts, messages, etc. and evaluates their state.

[1003] A "means for recommending personalized content" is a system for identifying and recommending optimal content to a user based on the analyzed emotional state of the user.

[1004] "Means for notifying users of recommended content" means a mechanism for communicating recommended content to users by push notification or other means.

[1005] This invention is a system that searches for and extracts candidates based on the detailed requirements of a company, automatically sends scouting emails, and schedules interviews. It can also analyze the user's emotional state and recommend and notify personalized content. Specific embodiments for implementing the invention are described below.

[1006] First, a company representative uses a dedicated web interface to enter detailed requirements for the job they are recruiting for (e.g., skills, years of experience, industry knowledge, etc.). This data is sent from the terminal to a server, which analyzes the received data and stores it in a company database. The server software used is a database management system (e.g., MySQL) or a web server (e.g., Apache).

[1007] Next, the server generates a search query based on the saved detailed requirements data of the companies and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. After receiving the response data, the server analyzes it to extract candidates, and scores and ranks each candidate.

[1008] The server automatically generates and sends scouting emails to ranked candidates. These emails include a message highlighting the attractiveness of the company and personalized content based on the candidate's skills and experience. An emotion engine is used to recognize the candidate's emotional state and adjust the email content accordingly. This process uses an emotion analysis algorithm (e.g., Google Cloud Natural Language API).

[1009] When a candidate receives a scouting email and clicks on the link in the email, they can access a schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times and enters the information, which is then sent to the server. The server compares the candidate's data with the company representative's schedule, uses an emotion engine to suggest the optimal interview date and time, and notifies both the company representative and the candidate of the confirmed date and time.

[1010] It also includes a function to analyze the user's emotional state and recommend personalized content. The server identifies the user's emotions from social media posts and messages and evaluates their state. Based on this, it identifies the most suitable content (e.g., videos, articles, music, etc.) and notifies the user. The algorithms used include a voice emotion recognition engine (e.g., IBM Watson) and a content recommendation system (e.g., TensorFlow).

[1011] For example, if the user is "feeling stressed," the system will recommend relaxation music or videos with a relaxing effect. Examples of prompts for the generative AI model are:

[1012] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[1013] As described above, the present invention streamlines corporate recruitment activities and provides personalized content that matches the user's emotional state, thereby realizing more effective human resource management.

[1014] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1015] Step 1:

[1016] As a means of inputting detailed company requirements, the terminal uses a dedicated web interface to input detailed requirements (skills, years of experience, industry knowledge, etc.) required for the job being recruited. The input data is sent to the server as the company's detailed requirements.

[1017] Step 2:

[1018] The server analyzes the received detailed requirement data and stores it in the company database. The database management system used here is MySQL as an example. The input data is the detailed requirement information, and the output is the analyzed requirement information stored in the company database.

[1019] Step 3:

[1020] The server generates a search query based on the stored detailed requirements data and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. The server receives and analyzes the response data to extract candidates, score each candidate, and rank them. The input data are the detailed requirements and candidate information from the social networking services, and the output is a scored candidate list.

[1021] Step 4:

[1022] The server automatically generates scouting emails for ranked candidates. These scouting emails include a message highlighting the company's attractiveness and personalized content based on the candidate's skills and experience. An emotion engine (e.g., Google Cloud Natural Language API) is used to recognize the candidate's emotional state and adjust the email content accordingly. The input data is candidate information and the results of emotion analysis, and the output is a personalized scouting email.

[1023] Step 5:

[1024] The server sends the generated scout email to the candidate's email address. The candidate clicks the link in the email to access the schedule adjustment form. They select a convenient date and time from the suggested dates and times on their device and enter the data, which is then sent to the server. The input data is the candidate's selected date and time, and the output is the schedule adjustment data sent to the server.

[1025] Step 6:

[1026] The server compares the scheduling data received from the candidate with the company's schedule and uses an emotion engine to suggest the optimal interview date and time. The algorithms used include an emotion analysis algorithm (e.g., Google Cloud Natural Language API). The input data is the candidate's scheduling data and the company's schedule, and the output is the optimal interview date and time.

[1027] Step 7:

[1028] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time. This notification is also conveyed in a sincere and positive manner based on the analysis results of the emotion engine. The input data is the confirmed interview date and time, and the output is the notification to the company representative and the candidate.

[1029] Step 8:

[1030] Furthermore, a means of analyzing the user's emotional state and recommending personalized content is added. The server identifies the user's emotions from social media posts and messages and evaluates their state. The emotion analysis engine used utilizes a voice emotion recognition engine (e.g., IBM Watson). The input data are the user's posts and messages, and the output is the analyzed emotional state.

[1031] Step 9:

[1032] The server identifies and recommends appropriate content (videos, articles, music, etc.) based on the analyzed user emotional state. This process uses a content recommendation system (e.g., TensorFlow). The input data is the analyzed emotional state, and the output is the recommended content.

[1033] Step 10:

[1034] The server notifies the user of the recommended content by push notification or other means. The input data is the recommended content, and the output is the notification to the user.

[1035] For example, if the user is analyzed as "feeling stressed," the server will recommend relaxation music or videos with a relaxing effect. An example of a prompt for the generative AI model is as follows:

[1036] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[1037] 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.

[1038] 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.

[1039] 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.

[1040] [Fourth embodiment]

[1041] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1042] 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.

[1043] 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).

[1044] 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.

[1045] 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.

[1046] 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).

[1047] 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. 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.

[1048] 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.

[1049] 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.

[1050] 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.

[1051] 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.

[1052] 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.

[1053] 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."

[1054] This invention is a system that uses AI to search for optimal candidates, send scouting emails, and automate interview scheduling in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[1055] 1. Enter the requirements required by the company

[1056] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill, including work history, skills, years of experience, industry knowledge, etc. Once the input is complete, the data is sent from the terminal to the server.

[1057] 2. Search and extract the best candidates

[1058] The server analyzes the received company's detailed requirements and generates an appropriate search query. It then connects with LinkedIn, GitHub, and other social networking services and educational institution databases to search and extract the best candidates. It scores each candidate and lists the candidates with the highest match.

[1059] 3. Automatic creation and sending of scout emails

[1060] The server automatically generates scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[1061] 4. Scheduling an interview

[1062] Candidates who receive the scout email can click the link in the email on their device to access the schedule adjustment form. The candidate can then select a suitable date and time from the suggested dates and times entered in the form, and the data will be sent to the server.

[1063] Specific examples

[1064] For example, if a company wants to hire for a "software engineer" position, the user (company representative) enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information and searches for candidates with the relevant projects and experience on LinkedIn and GitHub. The server then lists 10 candidates who match closely, and automatically sends them a scouting email stating, "We're impressed with your Python and JavaScript projects on GitHub."

[1065] When a candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company's schedule to determine the optimal interview date and time. The determined interview date and time is automatically notified to both the candidate and the company's representative.

[1066] This allows companies to conduct recruitment activities quickly and efficiently without hassle. The system automates the entire recruitment process, from talent search and scouting to interview arrangements, and is a system that can greatly streamline a company's recruitment operations.

[1067] The processing flow will be explained below.

[1068] Step 1:

[1069] The user (company representative) accesses a dedicated web interface and enters the detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.). After entering the information, they press the "Submit" button to send the data to the server.

[1070] Step 2:

[1071] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[1072] Step 3:

[1073] Based on the stored detailed requirements, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[1074] Step 4:

[1075] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[1076] Step 5:

[1077] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[1078] Step 6:

[1079] The server automatically creates scouting emails for the listed candidates. These emails include personalized messages that highlight the attractiveness of the company and are based on the candidate's background and skills. These emails are generated based on templates.

[1080] Step 7:

[1081] The server automatically sends the generated scouting email to the candidate's email address, including a link to schedule an interview.

[1082] Step 8:

[1083] Candidates receive the scout email on their device, click the link in the email to access the schedule arrangement form, select a suitable date and time from the suggested dates and times, and press the "Submit" button.

[1084] Step 9:

[1085] The server receives the schedule adjustment data sent by the candidate, then compares it with the schedule of the company representative to determine the best interview date and time for both parties.

[1086] Step 10:

[1087] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, including details of the interview and login information.

[1088] The above are the specific processing steps of this system.

[1089] Example 1

[1090] 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."

[1091] In corporate recruitment activities, tasks such as searching for suitable candidates, generating and sending scouting emails, and scheduling interviews are often performed manually, which takes a lot of time and effort. There is also the risk of missing the timing to communicate with candidates or overlooking suitable talent. It is essential to solve these problems and improve the efficiency and effectiveness of the recruitment process.

[1092] 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.

[1093] In this invention, the server includes: a means for a user to input detailed job requirements; a means for analyzing candidate information based on the detailed requirements and generating a search query; a means for linking with multiple databases to search, extract, and score candidates; a means for automatically generating and sending personalized scout emails to candidates; a means for candidates who receive the scout email to access an interview scheduling form and enter their desired date and time; and a means for receiving the scheduling information provided by the candidate, integrating it with the schedule of the company representative, and determining and notifying the candidate of the optimal interview date and time. This enables companies to efficiently and quickly search for optimal candidates, send scout emails, and automate the process of scheduling interviews.

[1094] "User" refers to the person in charge of recruitment activities at a company or organization.

[1095] "Detailed job requirements" refer to the skills, years of experience, work history, industry knowledge, and other conditions required for the job a company is looking to hire for.

[1096] "Search Query" refers to a search dataset or command generated based on detailed job requirements.

[1097] "Candidate Information" refers to data about job seekers, such as their work history, skills, and project experience.

[1098] "Database" refers to a data storage system where candidate information is stored, such as LinkedIn or GitHub.

[1099] "Scoring" refers to the process of comparing and evaluating detailed job requirements with candidate information from search results and quantifying the degree of match.

[1100] A "scouting email" is an email sent to candidates who match a company's job requirements to express interest in hiring them.

[1101] "Scheduling Form" refers to an online form that allows candidates to enter their preferred interview date and time.

[1102] "Server" refers to the central computer system that handles all of the above processing and data management.

[1103] The present invention is a system that uses a generative AI model to search for optimal candidates, automates the sending of scouting emails, and schedules interviews in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[1104] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to hire, such as work history, skills, years of experience, industry knowledge, etc. This data is sent from the terminal to the server.

[1105] The server analyzes the received detailed requirements using natural language processing (NLP) technology and generates an appropriate search query. Based on the generated search query, the server connects to multiple databases, including LinkedIn and GitHub, to search for and extract candidates. In this process, the server collects information on multiple candidates and performs scoring to create a list of candidates with high match scores.

[1106] The server automatically generates personalized scouting emails for the listed candidates. These scouting emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are sent to the candidate's email address.

[1107] Candidates receive a scout email and click the link in the email to access the schedule adjustment form. In the schedule adjustment form, candidates can select a suitable date and time from the proposed interview dates and times. This data is sent to the server via the terminal.

[1108] The server integrates the candidate's desired date and time with the company's schedule to determine the optimal interview date and time. The server then notifies both the candidate and the company's representative of the determined interview date and time. This allows companies to conduct recruitment activities quickly and efficiently without hassle.

[1109] For example, if a company is looking to hire for a "software engineer" position, the user enters detailed requirements into a web interface, including "Python and JavaScript skills, more than three years of work experience, and understanding of AI technology." The server receives this information, searches for candidates with the relevant projects and experience on LinkedIn and GitHub, and automatically sends them a scouting email. When the candidate receives the email and clicks the link to access the schedule arrangement form, the server combines the candidate's desired date and time with the company's schedule to determine the optimal interview date and time, and automatically notifies the candidate.

[1110] The above system can improve the efficiency of companies' recruitment activities and significantly reduce the time and effort required. The effects of the present invention can be maximized through this specific implementation method.

[1111] An example prompt is, "Please explain in detail the steps involved in a system that automates a company's recruitment activities, from entering the required qualifications to scheduling an interview."

[1112] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1113] Step 1:

[1114] Users access a dedicated web interface and enter detailed job requirements, including work history, skills, years of experience, and industry knowledge.

[1115] The entered job requirements (input: work history, skills, years of experience, industry knowledge, etc.) are sent from the terminal to the server (output: JSON format data).

[1116] Step 2:

[1117] Job requirement data transmitted from the terminal to the server is received.

[1118] The server parses the JSON data and extracts the necessary information (input: JSON format data, output: parsed data object).

[1119] Step 3:

[1120] The server generates a search query based on the analysis results.

[1121] The server uses natural language processing technology to structure the job requirements and convert them into a search query (input: analysis result data object, output: search query).

[1122] Step 4:

[1123] The server uses the generated search query to connect with multiple databases, such as LinkedIn and GitHub, to search and extract candidate information.

[1124] The server collects the search results and scores each candidate (input: search query, output: scored candidate list).

[1125] Step 5:

[1126] The server automatically generates personalized scouting emails for the listed candidates.

[1127] The server uses a generative AI model to create a scouting email that includes wording that appeals to the company and a message about the candidate's skills and background (input: scored candidate list, output: scouting email).

[1128] Step 6:

[1129] The server sends the generated scout email to the candidate's email address.

[1130] The server monitors the status of the email sending and confirms the success of the sending (input: scout email and candidate email address, output: email sending status).

[1131] Step 7:

[1132] Candidates will receive a scouting email and click on the link in the email to access the scheduling form.

[1133] The candidate selects a convenient date and time from the suggested dates and times displayed on the form and sends the input data from the terminal to the server (input: date selected by the candidate, output: date data sent to the server).

[1134] Step 8:

[1135] The server combines the candidate's desired date and time with the company representative's schedule to determine the optimal interview date and time.

[1136] The server notifies both the candidate and the company representative of the decided interview date and time (input: candidate's desired date and time and company representative's schedule, output: notification of decided interview date and time).

[1137] The above processing steps automate the recruitment process, enabling companies to conduct recruitment activities efficiently and effectively.

[1138] (Application example 1)

[1139] 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."

[1140] Traditionally, the process for companies to find suitable candidates, send out scouting emails, and schedule interviews has often been manual, requiring time and effort. Furthermore, when it comes to maintaining and repairing factory robots, finding and contacting technicians at the right time can be difficult, resulting in production line downtime. There is a need to solve these issues and streamline corporate and factory operations.

[1141] 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.

[1142] In this invention, the server includes means for inputting detailed requirements of a company, means for searching and extracting candidates based on the detailed requirements, means for automatically creating and sending scout emails to the candidates, means for arranging interview dates with candidates who have received the scout emails, and means for the robot to perform self-diagnosis, search for specialized engineers, and arrange maintenance schedules. This allows companies to conduct recruitment activities efficiently, and also makes it possible to quickly and efficiently perform maintenance and repairs of factory robots.

[1143] "Detailed company requirements" refers to the specific hiring conditions, such as the skills, years of experience, and industry knowledge required for the job the company is seeking.

[1144] "Candidate Search and Selection Means" means a means capable of locating and selecting suitable candidates from a database based on specified detailed requirements.

[1145] A "scout email" refers to a recruiting email sent by a company to selected candidates as part of its recruitment activities.

[1146] "Means for arranging interview dates" refers to a means that has the function of arranging interview dates and times between companies and candidates and determining the optimal interview schedule.

[1147] "Self-diagnosis" refers to the ability of a machine or system to monitor its own condition and automatically determine malfunctions or situations requiring maintenance.

[1148] "Professional technician" means a person who has particular techniques or skills and who has specialized knowledge to perform the maintenance and repair of machines and systems.

[1149] "Means for coordinating maintenance schedules" refers to the means by which a machine or system has the ability to coordinate and confirm optimal maintenance dates and times with a specialist.

[1150] "Social networking service" refers to a web service that enables individuals and businesses to exchange information and connect with each other over the Internet.

[1151] "Institutional database" refers to a database of alumni information and research results held by an educational institution such as a school or university.

[1152] This invention provides a system that streamlines corporate recruitment activities and factory robot maintenance. This system includes functions for inputting detailed requirements, searching and extracting candidates, automatically generating and sending scouting emails, arranging interview dates, and also for robot self-diagnosis and searching and scheduling maintenance engineers.

[1153] System configuration

[1154] 1. Enter detailed requirements

[1155] Users (company personnel) use a web interface to input detailed requirements for the job they are looking to hire for, such as skills, years of experience, industry knowledge, etc. The input data is then sent from the company's terminal to the server.

[1156] 2. Candidate search and selection

[1157] The server analyzes the details entered, generates the appropriate search query, and then connects with LinkedIn and other social networking services, as well as educational institution databases, to find and extract the best candidates.

[1158] 3. Automatic creation and sending of scout emails

[1159] The server automatically generates scouting emails for candidates listed in the search results. The emails include a message that appeals to the company and a personalized message about the candidate's skills and background. The generated scouting emails are automatically sent to the candidate's email address.

[1160] 4. Scheduling an interview

[1161] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times entered in the form, and the data is sent to the server. The server combines the candidate's desired date and time with the company representative's schedule, determines the optimal interview date and time, and notifies both parties.

[1162] 5. Robot self-diagnosis

[1163] The factory robots are self-diagnostic and monitor their performance, and if there is an error or maintenance required, the robots send that information to a server.

[1164] 6. Searching for and scheduling specialists

[1165] The server analyzes the error information received from the robot and searches for and extracts the appropriate technician. Various databases are used for the search, and a maintenance request message is automatically sent to the appropriate technician. After the technician replies, the server coordinates the optimal maintenance date and time between the robot and the technician, and notifies both parties of the decided date and time.

[1166] Example

[1167] Software used:

[1168] Python, Requests library, LinkedIn API

[1169] Hardware used:

[1170] Corporate terminals, servers, factory robots, internet-connected devices

[1171] Example prompt sentence:

[1172] Robot diagnosis results:

[1173] Error code: E404

[1174] Error: Mechanical failure in arm joint

[1175] Technician search query:

[1176] "technician+mechanical+failure+arm+joint"

[1177] Specific message example:

[1178] Subject: Urgent Maintenance Required for Arm Joint Failure

[1179] Dear [Technician Name],

[1180] Our robot has detected a mechanical failure in its arm joint and we require immediate assistance. Can you assist in resolving this issue at your earliest convenience?

[1181] Best,

[1182] Robot Maintenance Team

[1183] This allows companies to conduct recruitment activities quickly and efficiently without hassle, and also enables maintenance and repair of factory robots to be carried out quickly and efficiently.

[1184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1185] Step 1:

[1186] The user enters details of the company's requirements into a web interface, including the skills required for the job, years of experience, industry knowledge, etc. This data is then sent from the terminal to the server.

[1187] Input: Detailed job requirements (skills, years of experience, industry knowledge)

[1188] Output: Detailed requirements data sent to the server

[1189] Step 2:

[1190] The server analyzes the received detailed requirements data and generates appropriate search queries that are used against social networking services and educational institution databases.

[1191] Input: Detailed requirement data

[1192] Output: Search query

[1193] Step 3:

[1194] The server uses the generated search query to search and extract the best candidates from LinkedIn and other databases, which are then scored and listed in order of best match.

[1195] Input: Search query

[1196] Output: Listed candidates

[1197] Step 4:

[1198] The server automatically generates and sends scouting emails to the listed candidates, including a personalized message about the company's appeal and the candidate's skills and background.

[1199] Input: Listed candidates

[1200] Output: Scout email sent

[1201] Step 5:

[1202] When a candidate receives a scout email and clicks on the link in the email, they will access the schedule adjustment form. The candidate will select a suitable date and time from the suggested dates and times entered in the form and enter it. This will send the schedule data to the server.

[1203] Input: Candidate's action when clicking the link in the scouting email

[1204] Output: Schedule data sent to the server

[1205] Step 6:

[1206] The server combines the desired date and time sent by the candidate with the schedule of the company representative to determine the optimal interview date and time, and notifies both parties of the determined interview date and time.

[1207] Input: Candidate's desired date and time, company representative's schedule data

[1208] Output: Notification of the interview date and time

[1209] Step 7:

[1210] Factory robots perform self-diagnosis and, if there is a malfunction or maintenance is required, send error information to the server.

[1211] Input: Robot self-diagnosis results

[1212] Output: Error information sent to the server

[1213] Step 8:

[1214] The server analyzes the error information received from the robot, searches for and extracts the appropriate technician, and retrieves information about the technician from the technician database.

[1215] Input: Robot error information

[1216] Output: Searched and extracted engineers

[1217] Step 9:

[1218] The server automatically generates and sends a maintenance request message to the extracted technician.

[1219] Input: Extracted technician information

[1220] Output: Maintenance request message sent

[1221] Step 10:

[1222] The technician responds to the maintenance request, and the server adjusts the maintenance date and time based on the response. The adjusted date and time are notified to the robot and the technician.

[1223] Input: Technician's response

[1224] Output: Notification of adjusted maintenance date and time

[1225] 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.

[1226] This invention is a system that uses AI and an emotion engine to automate the process of searching for optimal candidates, sending scouting emails, and arranging interview schedules in order to streamline corporate recruitment activities. A specific embodiment of this system will be described.

[1227] 1. Enter the requirements required by the company

[1228] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are recruiting for (work history, skills, years of experience, industry knowledge, etc.) The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database.

[1229] 2. Search and extract the best candidates

[1230] The server generates a search query based on the saved detailed requirements data of companies and sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases. The server receives and analyzes the response data to extract candidates and score each candidate. Based on the scores, candidates with the highest match are ranked and listed.

[1231] 3. Automatic creation and sending of scout emails

[1232] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message that highlights the attractiveness of the company and is based on the candidate's skills and background. Furthermore, an emotion engine is used to recognize the candidate's current emotional state and adjust the content of the email accordingly. The generated scouting emails are then automatically sent to the candidate's email address.

[1233] 4. Scheduling an interview

[1234] Candidates who receive the scouting email can click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times on the form, and once the data is entered, it is sent to the server.

[1235] The server compares the schedule adjustment data received from the candidate with the schedule of the company representative. It uses an emotion engine to analyze the emotional state of the company representative and candidate and proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the company representative and the candidate.

[1236] Specific examples

[1237] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches its LinkedIn and GitHub databases. Ten highly matching candidates are listed, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your GitHub project (Python, R)."

[1238] Before sending an email, a sentiment engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently posted something positive, the tone of the email will be more positive as well.

[1239] When a candidate receives the email, they click the link to access the scheduling form and select a suitable date and time from the suggested options. The server then integrates this with the company representative's schedule and uses an emotion engine to analyze the emotional state of both parties before determining the optimal interview date and time.

[1240] The confirmed interview date and time is automatically notified to both the candidate and the company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the analysis results of the emotion engine.

[1241] In this way, the present invention is a system that, by combining an emotion engine, can further personalize the conventional recruitment process and make it more efficient and effective.

[1242] The processing flow will be explained below.

[1243] Step 1:

[1244] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. After entering the detailed requirements, the user presses the "Submit" button to send the data to the server.

[1245] Step 2:

[1246] The server parses the received detailed requirements data, extracts each requirement, converts it into an appropriate format, and stores this data in a corporate database.

[1247] Step 3:

[1248] Based on the stored detailed requirement data, the server sends API requests to various social networking services (such as LinkedIn and GitHub) and educational institution databases to generate and send search queries for candidates who match the job history, skills, years of experience, and industry knowledge.

[1249] Step 4:

[1250] The server receives response data from each social networking service and the educational institution's database. The received data is provided in JSON format, and is then parsed to extract data for each candidate.

[1251] Step 5:

[1252] The server applies a scoring algorithm to the extracted candidate data to calculate the degree of match for each candidate, and then ranks and lists candidates with the highest match based on the score.

[1253] Step 6:

[1254] For each candidate on the list, the server uses an emotion engine to tailor the content of scouting emails. Specifically, it analyzes the candidate's past email responses and social media posts to recognize their current emotional state, and customizes the tone and content of the email accordingly.

[1255] Step 7:

[1256] The server automatically generates and sends a customized scouting email to the candidate's email address, containing the scouting information and a link to schedule an interview.

[1257] Step 8:

[1258] After receiving the scout email on their device, the candidate clicks on the link in the email to access the schedule arrangement form, selects a suitable date and time from the suggested dates and times in the form, and submits the information they entered to the server.

[1259] Step 9:

[1260] The server receives the schedule adjustment data sent by the candidate. It then compares it with the company representative's schedule and proposes the optimal date and time for both parties. It uses an emotion engine to analyze the emotional state of the company representative and the candidate. The optimal interview date and time is determined taking this information into consideration.

[1261] Step 10:

[1262] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time via email, and based on the results of the emotion engine's analysis, conveys sincere and positive messages to the candidate.

[1263] As a specific example, if a company wants to hire for a "data scientist" position, the company representative enters detailed requirements, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server uses these requirements to search databases such as LinkedIn and GitHub, and lists 10 candidates who most closely match the requirements. Before sending a scouting email, the emotion engine analyzes the candidate's emotional state and adjusts the content of the email. When scheduling an interview, the emotion engine is also used to consider the emotional state of both the company representative and the candidate, and the optimal date and time is suggested and notified.

[1264] Example 2

[1265] 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."

[1266] In corporate recruitment activities, quickly finding suitable candidates, efficiently contacting them, and arranging interview dates is a very time-consuming process. In particular, communication that does not take into consideration the emotional state of the candidate and the company representative can cause stress for both parties, which can ultimately reduce recruitment efficiency. A system that solves this problem and makes recruitment activities more efficient and effective is needed.

[1267] 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.

[1268] In this invention, the server includes means for inputting detailed requirements of a company, means for searching for and extracting candidates based on the detailed requirements, means for creating and sending automatic scout emails to the candidates, means for arranging interview dates with candidates who have received the scout email, means having an emotion engine for analyzing the emotional states of the candidates and company personnel, means for adjusting the content of the email based on the emotion analysis results, and means for proposing the optimal interview date and time based on the emotion analysis results.This not only streamlines the process from searching for candidates to arranging interview dates and times, but also makes use of the emotion engine to enable less stressful communication for both candidates and company personnel.

[1269] "Company's detailed requirements" are the specific conditions and standards that a company requires for the position (e.g., work history, skills, years of experience, industry knowledge, etc.).

[1270] A "candidate" is an individual whom a company considers for recruitment purposes.

[1271] The "emotion engine" is software that analyzes the emotional state of candidates and company representatives and adjusts the system's operation based on the analysis results.

[1272] A "scout email" is an email sent by a company to a candidate to convey their interest in hiring.

[1273] "Interview scheduling" is the process of deciding the date and time of the interview, taking into consideration the convenience of the company representative and the candidate.

[1274] An "external database" is a database that exists outside the system and provides information about candidates (e.g., a social networking service or an educational institution's database).

[1275] "Search and extraction" is the process of finding and retrieving matching information from a database based on specified criteria.

[1276] "Analysis" is the process of analyzing input data or acquired data to find meaning and value.

[1277] "Storage" is the process of recording acquired data in a storage medium such as a database so that it can be retrieved when needed.

[1278] "Automatic creation" is the process by which the system automatically generates the necessary information and content without human intervention.

[1279] "Proposing the optimal interview date and time" means presenting the most suitable interview date and time for both parties based on the analysis results of the emotion engine, etc.

[1280] This invention is a system that combines multiple pieces of hardware and software to streamline corporate recruitment activities. This system automates all processes, including inputting the company's requirements, searching and extracting suitable candidates, creating and sending automatic scouting emails, and scheduling interviews. Specific implementation methods are described below.

[1281] 1. Enter the requirements required by the company

[1282] Users (company personnel) access a dedicated web interface and enter detailed requirements for the job they are looking to fill (work history, skills, years of experience, industry knowledge, etc.). The entered data is sent from the terminal to a server, which then analyzes the received data and stores it in a company database. This process uses a web browser, HTTP requests, and a database (e.g., MySQL or PostgreSQL).

[1283] 2. Search and extract the best candidates

[1284] The server generates a search query based on the company's detailed requirements data and sends an API request to various external databases (e.g., social networking services, educational institution databases). The received response data is analyzed using a machine learning algorithm (e.g., Python's scikit-learn or TensorFlow) to score candidates. Finally, a list of candidates with high matching scores is generated.

[1285] 3. Automatic creation and sending of scout emails

[1286] The server automatically generates scouting emails for the listed candidates. These scouting emails include a personalized message highlighting the company's attractiveness and based on the candidate's skills and experience. Furthermore, an emotion engine (e.g., Python's NLTK or TextBlob) is used to analyze the candidate's emotional state and adjust the email content accordingly. The generated scouting emails are automatically sent using Python's smtplib library.

[1287] 4. Scheduling an interview

[1288] Candidates who receive a scout email click the link in the email on their device to access the schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times, enters the information, and the data is sent to the server. The server compares the received schedule arrangement data with the schedule of the company representative, analyzes the emotional state of the candidate and company representative using an emotion engine, and then proposes the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative.

[1289] Specific examples

[1290] For example, if a company wants to hire for a "data scientist" position, the user (company representative) enters detailed requirements into a web interface, including "Python and R skills, more than five years of work experience, and knowledge of big data analysis." The server receives these requirements and searches databases such as LinkedIn and GitHub. A list of 10 highly matching candidates is generated, and a scouting email is automatically sent to the candidate, stating, "We're impressed with your project."

[1291] Before sending the email, the emotion engine performs sentiment analysis based on the candidate's past email responses and social media posts. For example, if the candidate has recently made positive posts, the tone of the email will be positive to match. When the candidate receives the email, clicks the link to access the scheduling form and selects a suitable date and time from the suggested dates and times, the server compares this with the company representative's schedule and uses the emotion engine to analyze the emotional states of both parties to determine the optimal interview date and time. The confirmed interview date and time is automatically notified to both the candidate and company representative. This notification is conveyed to the candidate in a sincere and positive manner based on the results of the emotion engine's analysis.

[1292] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1293] Step 1:

[1294] Enter your company's detailed requirements

[1295] The user (company representative) accesses a dedicated web interface and enters detailed requirements such as work history, skills, years of experience, industry knowledge, etc. Specifically, the user launches a web browser, accesses the company's dedicated login page, enters the required information in each field, and clicks the "Submit" button. This input data (detailed requirements) is sent from the browser to the terminal via a POST request.

[1296] Input: Detailed requirement data entered by the user into the web form

[1297] Output: Detailed requirements data submitted

[1298] Step 2:

[1299] Parsing and storing detailed requirements data

[1300] The device sends the entered detailed requirements data to the server, which receives the data, analyzes it, and stores it in a corporate database. Specifically, a server-side script (e.g., Python, Java, etc.) receives the data, analyzes and organizes it using natural language processing, and then stores it in a database (e.g., MySQL or PostgreSQL).

[1301] Input: Detailed requirements data entered by the user

[1302] Output: Detailed requirements data analyzed and stored in a corporate database

[1303] Step 3:

[1304] Generate and submit candidate search queries

[1305] The server generates a search query based on the stored detailed requirements data of the company. The server then uses this search query to send API requests to various external databases (e.g., social networking services or educational institution databases). Specifically, the server generates a query using natural language processing technology and SQL or API requests, and sends it to the external database as an HTTP request.

[1306] Input: Saved detailed company requirements data

[1307] Output: The search query sent to the external database

[1308] Step 4:

[1309] Receiving and analyzing candidate data

[1310] The server receives and parses the response data from the external database. Specifically, it parses the returned data in JSON or XML format using Python's json module or other compatible libraries to extract candidate information.

[1311] Input: Response data from an external database

[1312] Output: Parsed candidate data

[1313] Step 5:

[1314] Candidate scoring and shortlisting

[1315] The server uses a machine learning algorithm to score the analyzed candidate data. Specifically, it uses Python libraries such as scikit-learn and TensorFlow to calculate the degree to which the candidate's skills match the detailed requirements, assigns a score, and then ranks and lists the candidates based on the score.

[1316] Input: Parsed candidate data

[1317] Output: Scored candidate list

[1318] Step 6:

[1319] Generate and send scout emails

[1320] The server generates scouting emails based on the scored candidate list. These emails highlight the company's attractiveness and include personalized messages based on the candidate's skills and experience. It also uses an emotion engine to analyze the candidate's emotional state and adjusts the email content accordingly. Specifically, it generates the email body using a template engine, performs emotion analysis using Python's NLTK and TextBlob, and sends the email using the smtplib library.

[1321] Input: Scored candidate list and sentiment engine analysis results

[1322] Output: Scout email sent

[1323] Step 7:

[1324] Scheduling an interview

[1325] Candidates receive the scouting email and click on the link in the email to access the scheduling form, which they do by clicking the link, opening the page in their browser, selecting a suitable date and time from the suggested dates and times, and submitting the form.

[1326] Input: Clicking on the link in the scout email and entering the schedule adjustment data

[1327] Output: Sent schedule adjustment data

[1328] Step 8:

[1329] Processing and notification of scheduling data

[1330] The server receives the schedule adjustment data sent by the candidate and compares it with the schedule of the company representative. Specifically, it retrieves the company representative's calendar information from the database and compares it with the candidate's input data to determine the optimal interview date and time. At this time, an emotion engine is used to analyze the emotional states of both parties and propose the optimal date and time. Finally, the confirmed interview date and time is automatically notified to both the company representative and the candidate.

[1331] Input: Company personnel schedule data and candidate schedule adjustment data

[1332] Output: Confirmed interview date and time, and notification sent

[1333] (Application example 2)

[1334] 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."

[1335] Modern recruitment activities involve many time-consuming tasks, such as searching for candidates, sending scouting emails, and scheduling interviews. Furthermore, companies must efficiently utilize numerous databases and information sources to find the best candidates to meet their requirements. While analyzing emotional states and providing personalized content could potentially improve the effectiveness of recruitment activities, there is a lack of methods to achieve this. Therefore, to efficiently complete these tasks, a system is needed that can search for candidates based on a company's detailed requirements, analyze their emotional states, and recommend and notify them of personalized content.

[1336] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting detailed requirements of a company, a means for searching for and extracting candidates based on the detailed requirements, a means for automatically creating and sending scout emails to the candidates, a means for arranging interview dates with candidates who have received the scout emails, a means for analyzing the user's emotional state and recommending personalized content, and a means for notifying the user of the recommended content. This makes it possible to improve the efficiency of companies' recruitment activities and provide personalized content based on their emotional state.

[1337] The "means for entering detailed company requirements" is an interface for entering information such as the skills and experience required for the job sought by company personnel.

[1338] "Means for searching and extracting candidates" refers to a system that searches for candidate information from social networking services and educational institution databases based on the detailed requirements of a company, and identifies suitable candidates.

[1339] The "means for automatically creating and sending scouting emails" is a mechanism for automatically creating email content for selected candidates and sending messages that appeal to the attractiveness of the company.

[1340] The "means of arranging interview dates" is a system that checks the availability of candidates who receive scouting emails with that of company personnel to determine the most suitable interview date and time.

[1341] "Means for analyzing a user's emotional state" refers to an algorithm that identifies a user's emotions from social media posts, messages, etc. and evaluates their state.

[1342] A "means for recommending personalized content" is a system for identifying and recommending optimal content to a user based on the analyzed emotional state of the user.

[1343] "Means for notifying users of recommended content" means a mechanism for communicating recommended content to users by push notification or other means.

[1344] This invention is a system that searches for and extracts candidates based on the detailed requirements of a company, automatically sends scouting emails, and schedules interviews. It can also analyze the user's emotional state and recommend and notify personalized content. Specific embodiments for implementing the invention are described below.

[1345] First, a company representative uses a dedicated web interface to enter detailed requirements for the job they are recruiting for (e.g., skills, years of experience, industry knowledge, etc.). This data is sent from the terminal to a server, which analyzes the received data and stores it in a company database. The server software used is a database management system (e.g., MySQL) or a web server (e.g., Apache).

[1346] Next, the server generates a search query based on the saved detailed requirements data of the companies and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. After receiving the response data, the server analyzes it to extract candidates, and scores and ranks each candidate.

[1347] The server automatically generates and sends scouting emails to ranked candidates. These emails include a message highlighting the attractiveness of the company and personalized content based on the candidate's skills and experience. An emotion engine is used to recognize the candidate's emotional state and adjust the email content accordingly. This process uses an emotion analysis algorithm (e.g., Google Cloud Natural Language API).

[1348] When a candidate receives a scouting email and clicks on the link in the email, they can access a schedule arrangement form. The candidate selects a suitable date and time from the suggested dates and times and enters the information, which is then sent to the server. The server compares the candidate's data with the company representative's schedule, uses an emotion engine to suggest the optimal interview date and time, and notifies both the company representative and the candidate of the confirmed date and time.

[1349] It also includes a function to analyze the user's emotional state and recommend personalized content. The server identifies the user's emotions from social media posts and messages and evaluates their state. Based on this, it identifies the most suitable content (e.g., videos, articles, music, etc.) and notifies the user. The algorithms used include a voice emotion recognition engine (e.g., IBM Watson) and a content recommendation system (e.g., TensorFlow).

[1350] For example, if the user is "feeling stressed," the system will recommend relaxation music or videos with a relaxing effect. An example of a prompt for the generative AI model is as follows:

[1351] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[1352] As described above, the present invention improves the efficiency of corporate recruitment activities and provides personalized content that matches the user's emotional state, thereby realizing more effective human resource management.

[1353] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1354] Step 1:

[1355] As a means of inputting detailed company requirements, the terminal uses a dedicated web interface to input detailed requirements (skills, years of experience, industry knowledge, etc.) required for the job being recruited. The input data is sent to the server as the company's detailed requirements.

[1356] Step 2:

[1357] The server analyzes the received detailed requirement data and stores it in the company database. The database management system used here is MySQL as an example. The input data is the detailed requirement information, and the output is the analyzed requirement information stored in the company database.

[1358] Step 3:

[1359] The server generates a search query based on the stored detailed requirements data and sends API requests to various social networking services (e.g., LinkedIn, GitHub, etc.) and educational institution databases. The server receives and analyzes the response data to extract candidates, score each candidate, and rank them. The input data are the detailed requirements and candidate information from the social networking services, and the output is a scored candidate list.

[1360] Step 4:

[1361] The server automatically generates scouting emails for ranked candidates. These scouting emails include a message highlighting the company's attractiveness and personalized content based on the candidate's skills and experience. An emotion engine (e.g., Google Cloud Natural Language API) is used to recognize the candidate's emotional state and adjust the email content accordingly. The input data is candidate information and the results of emotion analysis, and the output is a personalized scouting email.

[1362] Step 5:

[1363] The server sends the generated scout email to the candidate's email address. The candidate clicks the link in the email to access the schedule adjustment form. They select a convenient date and time from the suggested dates and times on their device and enter the data, which is then sent to the server. The input data is the candidate's selected date and time, and the output is the schedule adjustment data sent to the server.

[1364] Step 6:

[1365] The server compares the scheduling data received from the candidate with the company's schedule and uses an emotion engine to suggest the optimal interview date and time. The algorithms used include an emotion analysis algorithm (e.g., Google Cloud Natural Language API). The input data is the candidate's scheduling data and the company's schedule, and the output is the optimal interview date and time.

[1366] Step 7:

[1367] The server automatically notifies both the company representative and the candidate of the confirmed interview date and time. This notification is also conveyed in a sincere and positive manner based on the analysis results of the emotion engine. The input data is the confirmed interview date and time, and the output is the notification to the company representative and the candidate.

[1368] Step 8:

[1369] Furthermore, a means of analyzing the user's emotional state and recommending personalized content is added. The server identifies the user's emotions from social media posts and messages and evaluates their state. The emotion analysis engine used utilizes a voice emotion recognition engine (e.g., IBM Watson). The input data are the user's posts and messages, and the output is the analyzed emotional state.

[1370] Step 9:

[1371] The server identifies and recommends appropriate content (videos, articles, music, etc.) based on the analyzed user emotional state. This process uses a content recommendation system (e.g., TensorFlow). The input data is the analyzed emotional state, and the output is the recommended content.

[1372] Step 10:

[1373] The server notifies the user of the recommended content by push notification or other means. The input data is the recommended content, and the output is the notification to the user.

[1374] For example, if the user is analyzed as "feeling stressed," the server will recommend relaxation music or videos with a relaxing effect. An example of a prompt for the generative AI model is as follows:

[1375] “Analyze the user’s emotional state from their posts and messages and recommend content based on that emotion. If the user is feeling stressed, recommend relaxing music or videos that will help them relax.”

[1376] 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.

[1377] 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.

[1378] 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.

[1379] 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.

[1380] 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.

[1381] 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.

[1382] 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).

[1383] 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.

[1384] 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."

[1385] 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.

[1386] 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).

[1387] 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.

[1388] 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.

[1389] 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.

[1390] 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.

[1391] 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.

[1392] 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.

[1393] 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.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] The following is further disclosed regarding the above embodiment.

[1398] (Claim 1)

[1399] a means of inputting the company's detailed requirements;

[1400] A means for searching and extracting candidates based on the detailed requirements;

[1401] A means for automatically creating and sending scout emails to the candidates;

[1402] A means for arranging an interview date with a candidate who has received the scout email;

[1403] A system including:

[1404] (Claim 2)

[1405] It has the means to link with various social networking services and educational institution databases.

[1406] 10. The system of claim 1.

[1407] (Claim 3)

[1408] A means for analyzing the input detailed requirements and storing the results in a database.

[1409] 10. The system of claim 1.

[1410] (Claim 4)

[1411] means for scoring the candidates and selecting the candidates based on the degree of match;

[1412] 10. The system of claim 1.

[1413] (Claim 5)

[1414] When scheduling interviews, the system has a means to integrate the schedules of company personnel and candidates and propose the most suitable date and time.

[1415] 10. The system of claim 1.

[1416] "Example 1"

[1417] (Claim 1)

[1418] a means for a user to input detailed job requirements;

[1419] A means for analyzing candidate information based on the detailed requirements and generating a search query;

[1420] A means of linking multiple databases to search, extract and score candidates,

[1421] means for automatically generating and sending personalized scouting emails to the candidates;

[1422] A means for a candidate who has received the scout email to access a form for scheduling an interview and input a desired date and time;

[1423] A means for receiving the schedule information provided by the candidate, integrating it with the schedule of the company's personnel, and determining and notifying the candidate of the optimal interview date and time;

[1424] A system including:

[1425] (Claim 2)

[1426] It has the means to connect with various social networking platforms and educational institution databases;

[1427] 10. The system of claim 1.

[1428] (Claim 3)

[1429] means for analyzing the input detailed requirements and using natural language processing techniques to generate a search query;

[1430] 10. The system of claim 1.

[1431] "Application Example 1"

[1432] (Claim 1)

[1433] a means of inputting the company's detailed requirements;

[1434] A means for searching and extracting candidates based on the detailed requirements;

[1435] A means for automatically creating and sending scout emails to the candidates;

[1436] A means for arranging an interview date with a candidate who has received the scout email;

[1437] A means for the robot to self-diagnose, find a technician, and schedule maintenance;

[1438] A system including:

[1439] (Claim 2)

[1440] It has the means to link with various social networking services and educational institution databases.

[1441] 10. The system of claim 1.

[1442] (Claim 3)

[1443] A means for analyzing the input detailed requirements and storing the results in a database.

[1444] 10. The system of claim 1.

[1445] "Example 2: Combining Emotion Engines"

[1446] (Claim 1)

[1447] a means of inputting the company's detailed requirements;

[1448] A means for searching and extracting candidates based on the detailed requirements;

[1449] A means for creating and sending automatic scouting emails to the candidates;

[1450] A means for arranging an interview date with a candidate who has received the scout email;

[1451] means for analyzing the emotional states of the candidates and company personnel, the emotional engine;

[1452] means for adjusting the content of the email based on the emotion analysis result;

[1453] A means for proposing an optimal interview date and time based on the emotion analysis result;

[1454] A system including:

[1455] (Claim 2)

[1456] 10. The system of claim 1, further comprising means for interfacing with various external databases.

[1457] (Claim 3)

[1458] 2. The system according to claim 1, further comprising means for analyzing the input detailed requirements and storing the analyzed requirements in a database.

[1459] "Application example 2 when combining emotion engines"

[1460] (Claim 1)

[1461] a means of inputting the company's detailed requirements;

[1462] A means for searching and extracting candidates based on the detailed requirements;

[1463] A means for automatically creating and sending scout emails to the candidates;

[1464] A means for arranging an interview date with a candidate who has received the scout email;

[1465] A means for analyzing a user's emotional state and recommending personalized content;

[1466] means for notifying a user of the recommended content;

[1467] A system including:

[1468] (Claim 2)

[1469] It has the means to link with various social networking services and educational institution databases.

[1470] 10. The system of claim 1.

[1471] (Claim 3)

[1472] A means for analyzing the input detailed requirements and storing the results in a database.

[1473] 10. The system of claim 1. [Explanation of symbols]

[1474] 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 inputting the company's detailed requirements; A means for searching and extracting candidates based on the detailed requirements; means for automatically creating and sending scout emails to the candidates; A means for arranging an interview date with a candidate who has received the scout email; A system including:

2. It has the means to link with various social networking services and educational institution databases. The system of claim 1 .

3. A means for analyzing the input detailed requirements and storing the results in a database. The system of claim 1 .

4. means for scoring the candidates and selecting candidates based on the degree of match; The system of claim 1 .

5. When scheduling interviews, the system has a means to integrate the schedules of company personnel and candidates and propose the most suitable date and time. The system of claim 1 .

Images