System

Abstract

A system is provided.SOLUTION: A system comprising: means for a human resources officer of an enterprise to input recruitment requirements, such as work experience, skill set, years of experience, industry knowledge; means for collecting candidate information from a plurality of data sources and analyzing candidates based on the recruitment requirements; means for generating and sending customized scout mail to selected candidates; and means for automatically adjusting interview schedules between candidates and the enterprise.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] The recruitment process for companies involves time-consuming and labor-intensive scouting and finding candidates with specific skill sets and experience. Traditional recruitment methods are highly inefficient, requiring separate searches across multiple platforms and manual scheduling of interviews. The present invention aims to solve these problems and streamline the recruitment process for companies. [Means for solving the problem]

[0005] The present invention provides a system for streamlining a company's recruitment process. Specifically, the system includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements; a means for generating customized scout emails and sending them to selected candidates; and a means for automatically coordinating interview schedules between candidates and companies. Furthermore, the system includes a means for receiving candidate replies to the customized scout emails and a means for integrating the interview schedules of companies and candidates to determine optimal interview dates, thereby achieving a smooth and effective recruitment process.

[0006] "Employment requirements" refer to specific conditions such as work history, skill set, years of experience, and industry knowledge that a company is looking for.

[0007] "Data sources" refers to multiple information providers from which information about human resources can be obtained, such as LinkedIn, GitHub, Twitter, and university databases.

[0008] "Candidate Information" refers to data collected from data sources, such as individual candidate's work history, skill set, years of experience, and contact information.

[0009] A "scouting email" refers to an email sent by a company to a candidate containing information about a job opening or an invitation to an interview.

[0010] "Interview schedule" refers to the date and time of the interview arranged between the candidate and the company's interviewer. [Brief explanation of the drawings]

[0011] [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

[0012] 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.

[0013] First, the terms used in the following description will be explained.

[0014] 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).

[0015] 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.

[0016] 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.

[0017] 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.

[0018] 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."

[0019] [First embodiment]

[0020] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0021] 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.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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.

[0027] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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."

[0032] The present invention is a system for streamlining a company's recruitment process, and includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for receiving candidate replies to the customized scout emails and a means for integrating the interview schedules of companies and candidates to determine optimal interview dates, thereby achieving a smooth and effective recruitment process.

[0033] Specific Embodiments of the System

[0034] System Configuration

[0035] 1. User Device: A computer or mobile device used by a company's HR personnel.

[0036] 2. Server: A computer system that provides AI-driven recruiting services.

[0037] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[0038] Program processing explanation

[0039] Candidate Matching

[0040] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[0041] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[0042] Generate and send scout emails

[0043] The server selects a scouting email template for the listed candidates and generates customized scouting emails by filling in the individual information of each candidate. The generated emails are automatically sent to each candidate.

[0044] Arranging interview schedules

[0045] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0046] The server collects schedule data from both parties and automatically arranges the optimal interview date. The confirmed interview date is notified to both the candidate and the company interviewer.

[0047] Specific examples

[0048] Candidate Matching Example

[0049] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[0050] Work Experience: Software Engineer

[0051] Skill Set: Python, Machine Learning

[0052] Years of experience: 3 years or more

[0053] Industry Knowledge: Financial Technology

[0054] Based on this, the server searches each data source and creates a list of optimal candidates.

[0055] Example of generating a scout email

[0056] The server generates a customized scouting email based on the selected candidate list, like this:

[0057] Candidate's name

[0058] Company name and brief introduction

[0059] Job details

[0060] Application procedure explanation

[0061] The server sends the generated scout email to the candidate.

[0062] Example of adjusting interview schedule

[0063] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date. The confirmed interview date is notified to both parties.

[0064] In this way, the present invention can fully automate and streamline a company's recruitment process, improving the speed and accuracy of recruitment.

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0068] Step 2:

[0069] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[0070] Step 3:

[0071] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases, etc.) based on the received hiring requirements.

[0072] Step 4:

[0073] The server sends an API request to each data source using the generated search query.

[0074] Step 5:

[0075] The server collects candidate information returned from each data source, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[0076] Step 6:

[0077] The server integrates the collected candidate information and analyzes it based on the company's hiring requirements, selecting candidates with the highest suitability and generating an optimal candidate list.

[0078] Step 7:

[0079] The server selects a template for a customized scouting email containing individual information of the candidates based on the list of optimal candidates.

[0080] Step 8:

[0081] The server embeds the candidate's name, company information, details of the job position, and other information into the template to generate a customized scouting email.

[0082] Step 9:

[0083] The server automatically sends the generated scout email to each candidate.

[0084] Step 10:

[0085] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[0086] Step 11:

[0087] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[0088] Step 12:

[0089] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[0090] Step 13:

[0091] The server collects schedule data for candidates and company interviewers, compares the schedules of both parties, and automatically arranges the optimal interview date.

[0092] Step 14:

[0093] The server notifies both the candidate and the company's interviewer of the determined interview date.

[0094] Example 1

[0095] 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."

[0096] Traditionally, companies' recruitment processes have involved a lot of manual work, which has made it time-consuming and labor-intensive, and it has been difficult to find suitable candidates. Furthermore, generating scouting emails and arranging interview schedules has also been time-consuming, making it difficult to conduct efficient recruitment activities. For this reason, companies have been seeking a way to select candidates more quickly and accurately and streamline the entire recruitment process.

[0097] 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.

[0098] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scouting emails and sending them to selected candidates, and a means for comparing candidates with company interview schedules and automatically arranging optimal interview dates. This enables companies to quickly and accurately select excellent candidates from a wide range of data sources and efficiently arrange scouting activities and interview schedules.

[0099] The "recruitment requirement input means" is a means for a company's human resources personnel to input the desired candidate conditions such as work history, skill set, years of experience, and industry knowledge.

[0100] "Data Collection Methods" means methods for collecting candidate information from multiple data sources, including online professional networking services, open source platforms, social media, and educational institution databases.

[0101] "Candidate analysis means" refers to the means of analyzing collected candidate information based on the company's recruitment requirements and selecting the most suitable candidates. This uses machine learning algorithms and filtering technology.

[0102] The "scout email generation means" is a means for generating a customized scout email incorporating individual information for a selected candidate. This means uses a template including an introduction to the company and details of the job opening.

[0103] The "scout mail sending means" is a means for automatically sending the generated customized scout mail to the candidate.

[0104] The "interview schedule adjustment means" is a means for automatically adjusting interview schedules between candidates and companies. This means compares the schedule data of both parties to determine the optimal interview date.

[0105] The "interview schedule comparison means" is a means for comparing the interview schedules of candidates and companies and automatically arranging the most suitable interview date.

[0106] The "schedule notification means" is a means for notifying the candidate and the company's interviewer of the confirmed interview date.

[0107] The present invention is a system for improving the efficiency of a company's recruitment process, and is implemented using the following hardware and software.

[0108] System Configuration

[0109] The system consists of the following elements:

[0110] 1. User Device: A computer or mobile device used by a company's HR personnel.

[0111] 2. Server: A computer system that provides AI-driven recruiting services.

[0112] 3. Data sources: Multiple online platforms (e.g., professional networking services, open source platforms, social media, educational institution databases, etc.).

[0113] Program processing explanation

[0114] Enter recruitment requirements

[0115] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server.

[0116] Data collection and analysis

[0117] The server generates a search query based on the received hiring requirements. The server then uses the generated query to send API requests to multiple data sources and collects the candidate information returned from each data source. The collected candidate information is then integrated and analyzed based on the company's hiring requirements. This analysis may involve the use of machine learning algorithms.

[0118] Generate and send scout emails

[0119] The server generates a list of optimal candidates and selects a scouting email template based on this list. It generates customized scouting emails by filling in information based on each candidate's name, experience, and skills. The generated scouting emails are automatically sent to each candidate.

[0120] Prompt Sentence Examples

[0121] For example, to generate a prompt like this:

[0122] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[0123] Arranging interview schedules

[0124] The user (candidate) clicks on the link in the scout email and enters their available schedule for an interview. This information is sent to the server. Similarly, the company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0125] The server collects the schedule data of candidates and interviewers, automatically arranges the optimal interview date, and notifies both the candidate and interviewer of the confirmed interview date.

[0126] Specific examples

[0127] A user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[0128] Work Experience: Software Engineer

[0129] Skill Set: Python, Machine Learning

[0130] Years of experience: 3 years or more

[0131] Industry Knowledge: Financial Technology

[0132] Based on this, the server searches each data source and creates a list of optimal candidates.

[0133] The server then generates a customized scouting email based on the selected candidates, like this:

[0134] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[0135] The user (candidate) clicks on the link in the scouting email and enters the date and time they are available for an interview. For example, they enter "May 1st, 2:00 PM to 4:00 PM." This information is sent to the server.

[0136] The company's human resources staff also enter the interviewer's schedule, for example, "May 1st, 1:00 PM to 5:00 PM."

[0137] The server compares the schedules of the candidate and interviewer and automatically adjusts the optimal interview date to "3:00 PM on May 1st." This confirmed interview date is notified to both parties.

[0138] As mentioned above, a company's recruitment process can be fully automated and made more efficient, improving the speed and accuracy of recruitment.

[0139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0140] Step 1: User enters hiring requirements

[0141] The user (a company's human resources officer) accesses the web interface using a user terminal. On the interface, he / she enters the hiring requirements such as work history, skill set, years of experience, and industry knowledge, and clicks the "Submit" button. The entered hiring requirements are sent to the server.

[0142] Input: Work history, skill set, years of experience, industry knowledge

[0143] Output: The job requirements data is sent to the server.

[0144] Step 2: Server generates search query

[0145] The server analyzes the received recruitment requirements data and generates search queries corresponding to each data source (professional networking services, open source platforms, social media, educational institution databases, etc.).

[0146] Input: Recruitment requirements data

[0147] Output: Generated search query

[0148] Step 3: Data collection by the server

[0149] The server sends API requests to each data source using the generated search query, which returns candidate information that the server collects, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[0150] Input: Search query

[0151] Output: Candidate information data

[0152] Step 4: Server integrates and analyzes candidate data

[0153] The server consolidates the collected candidate information and analyzes the data based on the hiring requirements, sometimes using machine learning algorithms. As a result of the analysis, a list of the best candidates is generated.

[0154] Input: Candidate information data, recruitment requirements data

[0155] Output: A list of the best candidates

[0156] Step 5: Server generates scout email

[0157] The server selects a scouting email template based on the list of optimal candidates. The template includes an introduction to the company and details of the job opening. It then fills in information based on each candidate's name, experience, and skills.

[0158] Input: Best candidate list

[0159] Output: Customized scout email

[0160] Step 6: Server sends scout email

[0161] The server automatically sends customized scouting emails to each candidate, and the sending history is also recorded as a log.

[0162] Input: Customized Scout Email

[0163] Output: Scout email sending history

[0164] Step 7: Candidate schedule entry

[0165] The user (candidate) clicks the link in the scout email and enters their available interview schedule. For example, they might enter "May 1st, 2:00 PM to 4:00 PM." After entering the information, they click the "Submit" button and this information is sent to the server.

[0166] Input: Interview Schedule

[0167] Output: Candidate interview schedule data

[0168] Step 8: Company interviewer inputs schedule

[0169] The user (a company's human resources manager) inputs the interviewer's schedule and sends it to the server. For example, the user might input "May 1st, 1:00 PM to 5:00 PM." After inputting the information, the user clicks the "Submit" button and the information is sent to the server.

[0170] Input: Interviewer Schedule

[0171] Output: Company interviewer schedule data

[0172] Step 9: Server schedules interviews

[0173] The server collects and compares the schedule data of candidates and company interviewers, and automatically arranges the optimal interview date. For example, it determines that "3:00 PM on May 1st" is the optimal date based on the candidate and interviewer's schedules.

[0174] Input: Candidate interview schedule data, company interviewer schedule data

[0175] Output: Optimal interview dates

[0176] Step 10: Notification of confirmed interview date

[0177] The server notifies both the candidate and the company's interviewer of the confirmed optimal interview date. For example, it sends a notification such as "The interview will be held at 3:00 PM on May 1st." The sending history is also recorded as a log.

[0178] Input: Best interview date

[0179] Output: Interview schedule notification, notification sending history

[0180] (Application example 1)

[0181] 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."

[0182] The traditional recruitment process involves many manual tasks, from entering recruitment requirements to selecting candidates, generating scout emails, and arranging interview schedules, resulting in inefficiency. Furthermore, particularly in factories and other workplaces, personnel familiar with specific machines and technologies are required, and searching for candidates who meet these requirements requires a great deal of effort. Furthermore, the technology used in the recruitment process is not integrated into on-site operations, resulting in time and resources being dispersed and inefficiency being reduced. Against this backdrop, there is a growing need for a more efficient and automated recruitment system.

[0183] 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.

[0184] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements; a means for generating customized scouting emails and sending them to selected candidates; and a means for a robot used in the factory to support the recruitment process. This enables the entire recruitment process to be automated and candidates to be selected efficiently. Furthermore, integrating in-factory operations with the recruitment process is expected to enable the rapid recruitment of personnel who are familiar with specific technologies and machines.

[0185] A "corporate human resources officer" is a person in charge of recruiting, managing, and evaluating human resources within a company.

[0186] "Work history" refers to information about a candidate's past jobs and work history.

[0187] A "skill set" is a specific set of skills and knowledge that a candidate possesses.

[0188] "Years of experience" refers to the number of years of work experience a candidate has accumulated in a particular job field.

[0189] "Industry knowledge" refers to specialized knowledge and understanding of a particular industry.

[0190] "Data Sources" are the multiple information sources used to obtain candidate information.

[0191] "Candidate Information" refers to data relating to a candidate's background, skills, experience, etc., that is relevant to recruitment.

[0192] A "scout email" is an email sent to a company's desired talent, conveying the company's intention to hire them.

[0193] "Means for automatic adjustment" refers to a function in which the system automatically adjusts the optimal schedule without manual operation.

[0194] The "robot" is an automated device that assists in the recruitment process within a factory.

[0195] A "system" is an integrated device consisting of multiple functional elements designed to achieve a specific purpose.

[0196] The present invention is a system for streamlining and automating a company's recruitment process. This system is intended for use in factories and other workplaces, and works in conjunction with robots used in the workplace. The system of the present invention includes the following components:

[0197] 1. User Device

[0198] The user terminal is a computer or smartphone used by a company's human resources personnel, through which they can input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0199] 2. Server

[0200] The server is the central computer system for the entire system. It is equipped with AI to collect and analyze candidate information from multiple data sources. This server generates appropriate search queries based on the recruitment requirements entered by HR personnel and sends API requests to multiple data sources (e.g., LinkedIn, GitHub, etc.).

[0201] 3. Robot

[0202] Robots are automated devices that assist with work in factories and are also involved in the recruitment process, particularly in selecting candidates with skills relevant to factory work and arranging interviews.

[0203] 4. Data Source

[0204] Data sources are multiple sources used to obtain candidate information, including LinkedIn, GitHub, university databases, social media, etc.

[0205] System Operation

[0206] The server receives the hiring requirements entered by the HR personnel through the user's device and generates a search query based on them. This query is used to collect and integrate candidate information from multiple data sources. The collected data is analyzed by AI on the server, and a list of candidates who best match the hiring requirements is generated.

[0207] The server then uses the candidate information to generate a customized scouting email containing the candidate's name, a company profile, details of the position, and instructions on the application process, which is then automatically sent to selected candidates.

[0208] Furthermore, when a candidate replies to a scouting email, that information is sent to the server. The server automatically adjusts the interview schedule between the candidate and the company and determines the optimal interview date and time. Once the interview date and time are decided, both the candidate and the company are notified.

[0209] Specific examples

[0210] For example, a human resources manager at a factory might use a smartphone to enter the following information about a "mechanical engineer" position:

[0211] Work Experience: Mechanical Engineer

[0212] Skill set: Machine maintenance, programming

[0213] Years of experience: 5 years or more

[0214] Industry knowledge: Automation technology

[0215] Based on this, the server searches for candidates from LinkedIn and GitHub, automatically generates a list of the best candidates, and then generates and sends customized scouting emails to the selected candidates, as follows:

[0216] "Hello [candidate's name],

[0217] After looking at your profile, we believe you may be interested in our mechanical engineer position, so we are sending you a scouting email.

[0218] Please consider applying.

[0219] Application link: [Application link]

[0220] Available interview dates and times are automatically arranged by the server and notified to candidates and companies.

[0221] In this way, the system of the present invention streamlines a company's recruitment process, and enables the rapid recruitment of personnel who can immediately contribute to on-site operations in particular.

[0222] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0223] Step 1:

[0224] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. The input data is sent to the server in JSON format.

[0225] Input: Recruitment requirements (work history, skill set, years of experience, industry knowledge)

[0226] Output: Recruitment requirements data sent to the server

[0227] Step 2:

[0228] The server generates a search query based on the received job requirements data. This search query is used to send API requests to multiple data sources. Specifically, a query is generated to search for candidates that match the job requirements.

[0229] Input: Recruitment requirements data

[0230] Output: Search query

[0231] Step 3:

[0232] The server uses the generated search query to send API requests to multiple data sources, retrieving candidate information from LinkedIn, GitHub, university databases, etc.

[0233] Input: Search query

[0234] Output: Candidate information retrieved from the data source

[0235] Step 4:

[0236] The server integrates candidate information collected from multiple data sources and analyzes it based on the hiring requirements. This generates a list of optimal candidates. Specifically, the AI ​​model evaluates the candidate's work history and skill set and calculates the degree of match with the hiring requirements.

[0237] Input: Collected candidate information

[0238] Output: A list of the best candidates

[0239] Step 5:

[0240] The server generates a customized scouting email based on the best candidates list. The scouting email includes the candidate's name, company profile, details of the job position, and an explanation of the application process. The generated scouting email is automatically sent to the candidate.

[0241] Input: Best candidate list

[0242] Output: Scout email sent

[0243] Step 6:

[0244] When a candidate replies to a scouting email, the information is sent to the server, which receives the candidate's reply, checks available interview schedules, and collects the schedules of the company's interviewers.

[0245] Input: Candidate's reply

[0246] Output: Candidate and interviewer schedule data

[0247] Step 7:

[0248] The server adjusts the optimal interview date based on the schedule data of the candidate and the company's interviewers, automatically selecting a date and time that is convenient for both the candidate and the company.

[0249] Input: Candidate and interviewer schedule data

[0250] Output: Optimal interview dates

[0251] Step 8:

[0252] The server notifies both the candidate and the company's interviewer of the confirmed interview date via email or calendar notification.

[0253] Input: Best interview date

[0254] Output: Interview schedule notification

[0255] 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.

[0256] The present invention provides a system for streamlining a company's recruitment process and taking into account the emotional states of both candidates and companies. The system includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for combining an emotional engine to recognize emotional states and optimize the content of the scout emails and the interview schedules.

[0257] Specific Embodiments of the System

[0258] System Configuration

[0259] 1. User Device: A computer or mobile device used by a company's human resources personnel and candidates.

[0260] 2. Server: A computer system that provides AI-driven recruiting services, including an emotion engine.

[0261] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[0262] Program processing explanation

[0263] Candidate Matching

[0264] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[0265] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[0266] Scout email generation and emotion recognition

[0267] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state and optimize the email content based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[0268] Interview scheduling and emotion recognition

[0269] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0270] The server collects both parties' schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. The server automatically schedules the optimal interview date to reduce stress and discomfort. The confirmed interview date is notified to both the candidate and the company's interviewer.

[0271] Specific examples

[0272] Candidate Matching Example

[0273] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[0274] Work Experience: Software Engineer

[0275] Skill Set: Python, Machine Learning

[0276] Years of experience: 3 years or more

[0277] Industry Knowledge: Financial Technology

[0278] Based on this, the server searches each data source and creates a list of optimal candidates.

[0279] Example of scout email generation and emotion recognition

[0280] The server generates a customized scouting email based on the selected candidate list, like this:

[0281] Candidate's name

[0282] Company name and brief introduction

[0283] Job details

[0284] Application procedure explanation

[0285] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[0286] Example of interview schedule adjustment and emotion recognition

[0287] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[0288] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[0289] The processing flow will be explained below.

[0290] Step 1:

[0291] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0292] Step 2:

[0293] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[0294] Step 3:

[0295] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases) based on the received hiring requirements.

[0296] Step 4:

[0297] The server then sends an API request to each data source using the generated search query, which collects candidate information from each data source.

[0298] Step 5:

[0299] The server collects and consolidates the candidate information returned from each data source, including the candidate's work history, skill set, years of experience, contact details, and more.

[0300] Step 6:

[0301] The server analyzes the collected candidate information and generates a list of candidates who best fit the company's hiring requirements, using an algorithm to evaluate each candidate's suitability.

[0302] Step 7:

[0303] The server selects a scouting email template based on the best candidates list, which includes company information and details of the job opening.

[0304] Step 8:

[0305] The server uses an emotion engine to recognize the candidate's emotional state and optimizes the content of the scouting email based on the candidate's interest and reactions. For example, if a candidate has shown positive reactions in the past, the email content will reflect those characteristics.

[0306] Step 9:

[0307] The server automatically sends customized scouting emails to candidates, each containing candidate-specific information.

[0308] Step 10:

[0309] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[0310] Step 11:

[0311] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[0312] Step 12:

[0313] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[0314] Step 13:

[0315] The server collects schedule data for candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, and automatically arranges optimal interview dates to avoid stress or discomfort for either candidate or interviewer.

[0316] Step 14:

[0317] The server notifies the candidate and the company's interviewer of the confirmed interview date by email or other means, and the schedule is confirmed.

[0318] Example 2

[0319] 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."

[0320] In the traditional recruitment process, a company's human resources personnel must manage a huge amount of candidate information and spend a lot of time and effort to respond appropriately to each candidate. It is also difficult to conduct recruitment activities taking into account the emotional state of both the candidate and the company, which can lead to inappropriate interview schedules and inappropriate content in scouting emails. This can result in an inefficient recruitment process, leaving candidates and companies dissatisfied.

[0321] 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.

[0322] In this invention, the server includes: a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple sources and analyzing the candidates based on the recruitment requirements; a means for generating customized emails and sending them to selected candidates; a means for automatically coordinating interview schedules between candidates and companies; a means for recognizing the emotional states of candidates and companies using an emotion engine; and a means for optimizing the content of emails and interview schedules based on the emotional states. This makes it possible to automate the recruitment process and conduct smooth recruitment activities by taking into account the emotional states of both companies and candidates.

[0323] A "corporate human resources officer" is a person who is engaged in the job of selecting candidates and handling recruitment procedures within a company.

[0324] "Work history" refers to information about the job history and positions held by a candidate.

[0325] A "skill set" refers to the specific set of skills and abilities a candidate possesses.

[0326] "Years of experience" is information that indicates the number of years a candidate has worked in a particular job or industry.

[0327] "Industry knowledge" refers to the specialized knowledge a candidate has about a particular industry.

[0328] "Sources" are external databases or platforms from which data about candidates is obtained.

[0329] "Candidate Information" refers to information including data such as a candidate's work history, skill set, years of experience, and industry knowledge.

[0330] "Analysis" refers to the process of extracting, classifying, and evaluating the obtained data according to the purpose and making appropriate decisions.

[0331] "Customized email" refers to emails whose content is individually tailored based on the candidate's individual information.

[0332] An "interview schedule" is a plan that shows the dates, times, and locations of interviews between candidates and companies.

[0333] "Automatic adjustment" means that the system makes optimal adjustments without human intervention.

[0334] An "emotion engine" is technology or software that analyzes the emotional state of candidates and companies and responds based on that.

[0335] "Emotional state" refers to the psychological and emotional state of the candidate and the company, including factors such as stress, interest, and satisfaction.

[0336] "Optimization" means adjusting or improving something to be most effective or efficient for a given purpose.

[0337] A "system" is a structure in which multiple elements work together to achieve a specific purpose.

[0338] System Configuration

[0339] The present invention is a system for streamlining a company's recruitment process and taking into account the emotional state of both the candidate and the company. The system includes the following components:

[0340] User terminal

[0341] A computer or mobile device used by a company's recruiters and candidates. This includes PCs with a web browser, smartphones, tablets, etc.

[0342] server

[0343] A computer system that provides AI-driven recruiting services, including an emotion engine, and performs various data processing and analysis.

[0344] Data Source

[0345] Obtain candidate information from multiple sources (e.g., social media platforms, professional networking sites, university databases, etc.).

[0346] Program processing explanation

[0347] Candidate Matching

[0348] The user (a company's human resources officer) uses a user terminal to enter recruitment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The entered information is sent to the server, which generates a search query based on this information. The generated query is used to send an API request to multiple data sources. The candidate information returned from each data source is collected and integrated. The integrated data is analyzed based on the company's recruitment requirements, and a list of optimal candidates is generated.

[0349] Scout email generation and emotion recognition

[0350] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state. The content of the email is optimized based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[0351] Interview scheduling and emotion recognition

[0352] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff similarly enters the interviewer's schedule and sends it to the server. The server collects this schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. It then automatically arranges the optimal interview date to reduce stress and discomfort. The confirmed interview date is then notified to both the candidate and the company's interviewer.

[0353] Specific examples

[0354] Candidate Matching Example

[0355] The user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[0356] Work Experience: Software Engineer

[0357] Skill Set: Python, Machine Learning

[0358] Years of experience: 3 years or more

[0359] Industry Knowledge: Financial Technology

[0360] Based on this, the server searches each data source and creates a list of the best candidates.

[0361] Example of scout email generation and emotion recognition

[0362] The server generates a customized scouting email based on the selected candidate list, like this:

[0363] Candidate's name

[0364] Company name and brief introduction

[0365] Job details

[0366] Application procedure explanation

[0367] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[0368] Example of interview schedule adjustment and emotion recognition

[0369] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[0370] The present invention can be implemented by using a generative AI model to create example prompts as follows:

[0371] "Find a Software Engineer candidate with the following skill set: Python, Machine Learning, 3+ years of experience, Financial Technology industry"

[0372] "Generate the best scouting email from this list of candidates."

[0373] Please use the schedule below to schedule your interview.

[0374] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] The user uses a terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The input information is sent to the server. The input is the company's employment requirements, and the output is the employment requirements data saved on the server. The user's specific actions are to type the required information into the input form and click the "Submit" button.

[0378] Step 2:

[0379] The server generates a search query based on the job requirements received from the user. Here, it receives the job requirements data as input data and generates a search query as output. The specific operation of the server is to analyze the job requirements data and build a query string based on it.

[0380] Step 3:

[0381] The server uses the generated search query to send API requests to multiple data sources. The input is the search query, and the output is the candidate information collected from each data source. Specifically, the server sends an HTTP request to an API endpoint and receives the candidate information as a response.

[0382] Step 4:

[0383] The server consolidates the collected candidate information. The input is candidate information obtained from multiple data sources, and the output is consolidated candidate data. Specifically, it standardizes data in different formats and consolidates them into a single database.

[0384] Step 5:

[0385] The server analyzes the integrated candidate data based on the company's hiring requirements and generates a list of optimal candidates. The input is the integrated candidate data and hiring requirements data, and the output is a list of optimal candidates. The specific operation of the server is to analyze the data using machine learning algorithms and filtering technology.

[0386] Step 6:

[0387] The server selects a scout email template based on the list of optimal candidates and generates customized scout emails by embedding individual information for each candidate. The input is the list of optimal candidates and the scout email template, and the output is a customized scout email. Specifically, the server runs a template engine to embed individual information into the template.

[0388] Step 7:

[0389] The server uses an emotion engine to analyze the emotional state of each candidate. The input is the candidate's past activity data and reaction data, and the output is emotional state data. Specifically, the server uses an emotion analysis algorithm to evaluate the emotional state from the data.

[0390] Step 8:

[0391] The server optimizes the content of the scout email based on the emotional state data. The input is a customized scout email and the emotional state data, and the output is an optimized scout email. Specifically, the server corrects and edits the email content.

[0392] Step 9:

[0393] The server automatically sends optimized scout emails to each candidate. The input is the optimized scout email, and the output is a notification of completion of sending. The specific operation is to send the email through the mail server.

[0394] Step 10:

[0395] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is sent to the server. The input is the candidate's schedule information, and the output is the schedule information saved on the server. Specifically, the schedule information is entered into a web form and sent.

[0396] Step 11:

[0397] Similarly, the user (a company's human resources officer) also enters the interviewer's schedule and sends it to the server. The input is the company's interviewer's schedule information, and the output is the schedule information saved on the server. Specifically, the human resources officer enters information into a web form and submits it.

[0398] Step 12:

[0399] The server collects both parties' schedule data and automatically arranges the optimal interview schedule using an emotion engine. The input is the candidate's and interviewer's schedule information and emotional state data, and the output is the optimal interview schedule. The specific operation of the server is to analyze the schedule data and calculate the optimal schedule.

[0400] Step 13:

[0401] The server notifies both the candidate and the company's interviewer of the confirmed interview date. The input is the optimal interview date, and the output is a notification message. Specifically, the server sends the notification via email or a messaging system.

[0402] Through the above steps, the present invention fully automates and streamlines a company's recruitment process, realizing smooth recruitment activities that take into account the emotional states of both candidates and companies.

[0403] (Application example 2)

[0404] 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."

[0405] In the recruitment process, companies are required to efficiently find suitable candidates who meet requirements such as work history, skill set, years of experience, and industry knowledge. In delivery operations, it is also important to consider the emotional state of delivery personnel and customers to improve service quality. Conventional methods have difficulty simultaneously optimizing recruitment and delivery schedules, and this issue needs to be addressed.

[0406] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0407] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, and a means for generating customized scouting emails and sending them to selected candidates. This makes it possible to streamline the recruitment process and further evaluate the emotional states of delivery personnel and customers in delivery work and optimize delivery schedules.

[0408] "Work history" refers to a candidate's professional history and work experience.

[0409] A "skill set" refers to the collection of skills, knowledge, and abilities required for a specific job or function.

[0410] "Years of experience" refers to the length of time a candidate has actually worked in a particular occupation or industry.

[0411] "Industry knowledge" refers to specialized knowledge and information about a particular industry.

[0412] "Data Sources" are sources for collecting candidate information, including, for example, professional networking sites and university databases.

[0413] "Candidate analysis" refers to the process of evaluating and comparing the suitability and capabilities of candidates based on the recruitment requirements entered.

[0414] A "scouting email" refers to a job information email customized for a specific candidate.

[0415] "Interview scheduling" refers to the process of coordinating the schedules of the candidate and the company's interviewer and determining the optimal interview date and time.

[0416] "Delivery services" refers to the delivery of goods and services to customers.

[0417] "Delivery Person" refers to a worker who is responsible for delivering goods to customers.

[0418] "Customer" means any person or entity that receives goods or services.

[0419] "Emotional state" refers to the current emotional or mental state of an individual or group.

[0420] "Schedule optimization" refers to the process of arranging various schedules in the most efficient way, making the most of time and effort.

[0421] This invention is a system for optimizing a company's recruitment process and delivery operations. The system's main components are a server, a user terminal, multiple data sources, and an emotion engine. The specific operation of each component and the overall system configuration are described below.

[0422] System Configuration

[0423] User terminal

[0424] User terminals are devices such as computers and smartphones used by human resources personnel and candidates. They can input recruitment requirements and arrange interview schedules via the user terminals.

[0425] server

[0426] The server is a computer system that provides the core AI-driven recruiting service and delivery operation management. It includes multiple modules, such as an emotion engine, a data analysis engine, and a schedule optimization engine. This server is composed of Python programs that collect information from data sources, analyze it, recognize emotions, and send notifications.

[0427] Data Source

[0428] Data sources are the multiple sources used to gather candidate information, such as professional networking sites, project management tools, email data, and university databases.

[0429] Program processing

[0430] Data Collection and Query Generation

[0431] The server receives recruitment requirements such as work history, skill set, years of experience, and industry knowledge from a user's device. Based on this information, the server generates a search query and sends API requests to multiple data sources. The server then integrates the candidate information obtained and creates a list of optimal candidates that match the recruitment requirements.

[0432] sentiment analysis

[0433] The server uses an emotion engine such as the TextBlob library to analyze the emotional states of the scout email, delivery personnel, and customers. Based on the analysis results, the server optimizes the content of the scout email and the delivery schedule.

[0434] Generate scout emails

[0435] The server generates a customized scouting email based on the candidate list. The scouting email includes the candidate's name, company name, details of the job position, and an explanation of the application process. Based on the evaluation by the emotion engine, the content is optimized based on the candidate's interest and suitability.

[0436] Arranging interview schedules

[0437] The server collects interview schedules provided by candidates and company interviewers, and uses an emotion engine to automatically determine the optimal interview dates that minimize stress and discomfort.

[0438] Optimizing delivery schedules

[0439] The emotion engine analyzes the emotional state of delivery personnel and customers and automatically adjusts optimal delivery schedules to reduce stress and fatigue, thereby improving service quality and maximizing labor efficiency.

[0440] Specific examples

[0441] Specific examples of candidate matching

[0442] For example, a company's HR representative enters the following hiring requirements:

[0443] Work Experience: Software Engineer

[0444] Skill Set: Python, Machine Learning

[0445] Years of experience: 3 years or more

[0446] Industry Knowledge: Financial Technology

[0447] Based on this, the server searches each data source and creates a list of the most suitable candidates.

[0448] Example of scout email generation

[0449] Generate a customized scout email like this:

[0450] Candidate's name

[0451] Company name and brief introduction

[0452] Job details

[0453] Application procedure explanation

[0454] It uses an emotion engine to assess candidate interest and reactions and optimize email content accordingly.

[0455] Specific examples of interview schedule adjustments

[0456] For example, a candidate inputs the date and time they are available for an interview, and the server collects the schedules of the company's interviewers. The server then automatically determines the optimal interview date using an emotion engine and notifies both parties.

[0457] Prompt Sentence Examples

[0458] "Job Requirements: Hiring delivery drivers with at least one year of delivery experience. Skill Set: Customer service, lifesaving. Years of Experience: At least one year. Industry Knowledge: Food delivery."

[0459] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0460] Step 1:

[0461] A company's human resources staff inputs hiring requirements such as work history, skill set, years of experience, and industry knowledge into the user terminal. The user terminal then sends the hiring requirements data to the server. Once the input hiring requirements data reaches the server, the next processing step begins.

[0462] Step 2:

[0463] The server generates a search query based on the job requirements data received in the previous step. The server uses Python to generate this query and then sends API requests to multiple data sources (e.g., career networking sites, university databases, etc.) to gather candidate information.

[0464] Step 3:

[0465] The server consolidates the collected candidate information and analyzes the candidates based on the hiring requirements. This analysis process uses statistical analysis and machine learning models to select the most suitable candidates. The analysis results in a list of the best candidates, which is then passed on to the next processing step.

[0466] Step 4:

[0467] The server creates a customized scouting email for each candidate based on the generated candidate list. It uses an emotion engine (e.g., TextBlob library) to analyze the candidate's emotional state and optimize the email content based on the candidate's interest level. The optimized scouting email is then automatically sent to the candidate.

[0468] Step 5:

[0469] If a candidate receives a scouting email and is interested, they click the link in the email and enter the date and time they are available for an interview. This input data is sent from the user's terminal to the server.

[0470] Step 6:

[0471] The server collects interview schedules provided by candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, determines the optimal interview date to minimize stress and discomfort, and notifies both parties.

[0472] Step 7:

[0473] The server analyzes the emotional state of the delivery person and the customer during food delivery work. The emotion engine evaluates the delivery person using information entered by the delivery person and feedback data from the customer. Based on the evaluation results, the delivery schedule is optimized and the optimal delivery route and time slot are automatically adjusted to reduce stress.

[0474] Step 8:

[0475] The server notifies the delivery staff and customers of the optimized delivery schedule. Notifications are sent via smartphone application and email. The delivery staff delivers based on the optimized schedule and route, improving customer satisfaction.

[0476] 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.

[0477] 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.

[0478] 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.

[0479] [Second embodiment]

[0480] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0481] 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.

[0482] 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).

[0483] 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.

[0484] 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.

[0485] 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).

[0486] 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.

[0487] 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.

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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."

[0492] The present invention is a system for streamlining a company's recruitment process, and includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for receiving candidate replies to the customized scout emails and a means for integrating the interview schedules of companies and candidates to determine optimal interview dates, thereby achieving a smooth and effective recruitment process.

[0493] Specific Embodiments of the System

[0494] System Configuration

[0495] 1. User Device: A computer or mobile device used by a company's HR personnel.

[0496] 2. Server: A computer system that provides AI-driven recruiting services.

[0497] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[0498] Program processing explanation

[0499] Candidate Matching

[0500] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[0501] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[0502] Generate and send scout emails

[0503] The server selects a scouting email template for the listed candidates and generates customized scouting emails by filling in the individual information of each candidate. The generated emails are automatically sent to each candidate.

[0504] Arranging interview schedules

[0505] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0506] The server collects schedule data from both parties and automatically arranges the optimal interview date. The confirmed interview date is notified to both the candidate and the company interviewer.

[0507] Specific examples

[0508] Candidate Matching Example

[0509] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[0510] Work Experience: Software Engineer

[0511] Skill Set: Python, Machine Learning

[0512] Years of experience: 3 years or more

[0513] Industry Knowledge: Financial Technology

[0514] Based on this, the server searches each data source and creates a list of optimal candidates.

[0515] Example of generating a scout email

[0516] The server generates a customized scouting email based on the selected candidate list, like this:

[0517] Candidate's name

[0518] Company name and brief introduction

[0519] Job details

[0520] Application procedure explanation

[0521] The server sends the generated scout email to the candidate.

[0522] Example of adjusting interview schedule

[0523] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date. The confirmed interview date is notified to both parties.

[0524] In this way, the present invention can fully automate and streamline a company's recruitment process, improving the speed and accuracy of recruitment.

[0525] The processing flow will be explained below.

[0526] Step 1:

[0527] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0528] Step 2:

[0529] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[0530] Step 3:

[0531] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases, etc.) based on the received hiring requirements.

[0532] Step 4:

[0533] The server sends an API request to each data source using the generated search query.

[0534] Step 5:

[0535] The server collects candidate information returned from each data source, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[0536] Step 6:

[0537] The server integrates the collected candidate information and analyzes it based on the company's hiring requirements, selecting candidates with the highest suitability and generating an optimal candidate list.

[0538] Step 7:

[0539] The server selects a template for a customized scouting email containing individual information of the candidates based on the list of optimal candidates.

[0540] Step 8:

[0541] The server embeds the candidate's name, company information, details of the job position, and other information into the template to generate a customized scouting email.

[0542] Step 9:

[0543] The server automatically sends the generated scout email to each candidate.

[0544] Step 10:

[0545] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[0546] Step 11:

[0547] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[0548] Step 12:

[0549] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[0550] Step 13:

[0551] The server collects schedule data for candidates and company interviewers, compares the schedules of both parties, and automatically arranges the optimal interview date.

[0552] Step 14:

[0553] The server notifies both the candidate and the company's interviewer of the determined interview date.

[0554] Example 1

[0555] 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."

[0556] Traditionally, companies' recruitment processes have involved a lot of manual work, which has made it time-consuming and labor-intensive, and it has been difficult to find suitable candidates. Furthermore, generating scouting emails and arranging interview schedules has also been time-consuming, making it difficult to conduct efficient recruitment activities. For this reason, companies have been seeking a way to select candidates more quickly and accurately and streamline the entire recruitment process.

[0557] 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.

[0558] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scouting emails and sending them to selected candidates, and a means for comparing candidates with company interview schedules and automatically arranging optimal interview dates. This enables companies to quickly and accurately select excellent candidates from a wide range of data sources and efficiently arrange scouting activities and interview schedules.

[0559] The "recruitment requirement input means" is a means for a company's human resources personnel to input the desired candidate conditions such as work history, skill set, years of experience, and industry knowledge.

[0560] "Data Collection Methods" means methods for collecting candidate information from multiple data sources, including online professional networking services, open source platforms, social media, and educational institution databases.

[0561] "Candidate analysis means" refers to the means of analyzing collected candidate information based on the company's recruitment requirements and selecting the most suitable candidates. This uses machine learning algorithms and filtering technology.

[0562] The "scout email generation means" is a means for generating a customized scout email incorporating individual information for a selected candidate. This means uses a template including an introduction to the company and details of the job opening.

[0563] The "scout mail sending means" is a means for automatically sending the generated customized scout mail to the candidate.

[0564] The "interview schedule adjustment means" is a means for automatically adjusting interview schedules between candidates and companies. This means compares the schedule data of both parties to determine the optimal interview date.

[0565] The "interview schedule comparison means" is a means for comparing the interview schedules of candidates and companies and automatically arranging the most suitable interview date.

[0566] The "schedule notification means" is a means for notifying the candidate and the company's interviewer of the confirmed interview date.

[0567] The present invention is a system for improving the efficiency of a company's recruitment process, and is implemented using the following hardware and software.

[0568] System Configuration

[0569] The system consists of the following elements:

[0570] 1. User Device: A computer or mobile device used by a company's HR personnel.

[0571] 2. Server: A computer system that provides AI-driven recruiting services.

[0572] 3. Data sources: Multiple online platforms (e.g., professional networking services, open source platforms, social media, educational institution databases, etc.).

[0573] Program processing explanation

[0574] Enter recruitment requirements

[0575] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server.

[0576] Data collection and analysis

[0577] The server generates a search query based on the received hiring requirements. The server then uses the generated query to send API requests to multiple data sources and collects the candidate information returned from each data source. The collected candidate information is then integrated and analyzed based on the company's hiring requirements. This analysis may involve the use of machine learning algorithms.

[0578] Generate and send scout emails

[0579] The server generates a list of optimal candidates and selects a scouting email template based on this list. It generates customized scouting emails by filling in information based on each candidate's name, experience, and skills. The generated scouting emails are automatically sent to each candidate.

[0580] Prompt Sentence Examples

[0581] For example, to generate a prompt like this:

[0582] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[0583] Arranging interview schedules

[0584] The user (candidate) clicks on the link in the scout email and enters their available schedule for an interview. This information is sent to the server. Similarly, the company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0585] The server collects the schedule data of candidates and interviewers, automatically arranges the optimal interview date, and notifies both the candidate and interviewer of the confirmed interview date.

[0586] Specific examples

[0587] A user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[0588] Work Experience: Software Engineer

[0589] Skill Set: Python, Machine Learning

[0590] Years of experience: 3 years or more

[0591] Industry Knowledge: Financial Technology

[0592] Based on this, the server searches each data source and creates a list of optimal candidates.

[0593] The server then generates a customized scouting email based on the selected candidates, like this:

[0594] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[0595] The user (candidate) clicks on the link in the scouting email and enters the date and time they are available for an interview. For example, they enter "May 1st, 2:00 PM to 4:00 PM." This information is sent to the server.

[0596] The company's human resources staff also enter the interviewer's schedule, for example, "May 1st, 1:00 PM to 5:00 PM."

[0597] The server compares the schedules of the candidate and interviewer and automatically adjusts the optimal interview date to "3:00 PM on May 1st." This confirmed interview date is notified to both parties.

[0598] As mentioned above, a company's recruitment process can be fully automated and made more efficient, improving the speed and accuracy of recruitment.

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

[0600] Step 1: User enters hiring requirements

[0601] The user (a company's human resources officer) accesses the web interface using a user terminal. On the interface, he / she enters the hiring requirements such as work history, skill set, years of experience, and industry knowledge, and clicks the "Submit" button. The entered hiring requirements are sent to the server.

[0602] Input: Work history, skill set, years of experience, industry knowledge

[0603] Output: The job requirements data is sent to the server.

[0604] Step 2: Server generates search query

[0605] The server analyzes the received recruitment requirements data and generates search queries corresponding to each data source (professional networking services, open source platforms, social media, educational institution databases, etc.).

[0606] Input: Recruitment requirements data

[0607] Output: Generated search query

[0608] Step 3: Data collection by the server

[0609] The server sends API requests to each data source using the generated search query, which returns candidate information that the server collects, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[0610] Input: Search query

[0611] Output: Candidate information data

[0612] Step 4: Server integrates and analyzes candidate data

[0613] The server consolidates the collected candidate information and analyzes the data based on the hiring requirements, sometimes using machine learning algorithms. As a result of the analysis, a list of the best candidates is generated.

[0614] Input: Candidate information data, recruitment requirements data

[0615] Output: A list of the best candidates

[0616] Step 5: Server generates scout email

[0617] The server selects a scouting email template based on the list of optimal candidates. The template includes an introduction to the company and details of the job opening. It then fills in information based on each candidate's name, experience, and skills.

[0618] Input: Best candidate list

[0619] Output: Customized scout email

[0620] Step 6: Server sends scout email

[0621] The server automatically sends customized scouting emails to each candidate, and the sending history is also recorded as a log.

[0622] Input: Customized Scout Email

[0623] Output: Scout email sending history

[0624] Step 7: Candidate schedule entry

[0625] The user (candidate) clicks the link in the scout email and enters their available interview schedule. For example, they might enter "May 1st, 2:00 PM to 4:00 PM." After entering the information, they click the "Submit" button and this information is sent to the server.

[0626] Input: Interview Schedule

[0627] Output: Candidate interview schedule data

[0628] Step 8: Company interviewer inputs schedule

[0629] The user (a company's human resources manager) inputs the interviewer's schedule and sends it to the server. For example, the user might input "May 1st, 1:00 PM to 5:00 PM." After inputting the information, the user clicks the "Submit" button and the information is sent to the server.

[0630] Input: Interviewer Schedule

[0631] Output: Company interviewer schedule data

[0632] Step 9: Server schedules interviews

[0633] The server collects and compares the schedule data of candidates and company interviewers, and automatically arranges the optimal interview date. For example, it determines that "3:00 PM on May 1st" is the optimal date based on the candidate and interviewer's schedules.

[0634] Input: Candidate interview schedule data, company interviewer schedule data

[0635] Output: Optimal interview dates

[0636] Step 10: Notification of confirmed interview date

[0637] The server notifies both the candidate and the company's interviewer of the confirmed optimal interview date. For example, it sends a notification such as "The interview will be held at 3:00 PM on May 1st." The sending history is also recorded as a log.

[0638] Input: Best interview date

[0639] Output: Interview schedule notification, notification sending history

[0640] (Application example 1)

[0641] 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."

[0642] The traditional recruitment process involves many manual tasks, from entering recruitment requirements to selecting candidates, generating scout emails, and arranging interview schedules, resulting in inefficiency. Furthermore, particularly in factories and other workplaces, personnel familiar with specific machines and technologies are required, and searching for candidates who meet these requirements requires a great deal of effort. Furthermore, the technology used in the recruitment process is not integrated into on-site operations, resulting in time and resources being dispersed and inefficiency being reduced. Against this backdrop, there is a growing need for a more efficient and automated recruitment system.

[0643] 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.

[0644] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements; a means for generating customized scouting emails and sending them to selected candidates; and a means for a robot used in the factory to support the recruitment process. This enables the entire recruitment process to be automated and candidates to be selected efficiently. Furthermore, integrating in-factory operations with the recruitment process is expected to enable the rapid recruitment of personnel who are familiar with specific technologies and machines.

[0645] A "corporate human resources officer" is a person in charge of recruiting, managing, and evaluating human resources within a company.

[0646] "Work history" refers to information about a candidate's past jobs and work history.

[0647] A "skill set" is a specific set of skills and knowledge that a candidate possesses.

[0648] "Years of experience" refers to the number of years of work experience a candidate has accumulated in a particular job field.

[0649] "Industry knowledge" refers to specialized knowledge and understanding of a particular industry.

[0650] "Data Sources" are the multiple information sources used to obtain candidate information.

[0651] "Candidate Information" refers to data relating to a candidate's background, skills, experience, etc., that is relevant to recruitment.

[0652] A "scout email" is an email sent to a company's desired talent, conveying the company's intention to hire them.

[0653] "Means for automatic adjustment" refers to a function in which the system automatically adjusts the optimal schedule without manual operation.

[0654] The "robot" is an automated device that assists in the recruitment process within a factory.

[0655] A "system" is an integrated device consisting of multiple functional elements designed to achieve a specific purpose.

[0656] The present invention is a system for streamlining and automating a company's recruitment process. This system is intended for use in factories and other workplaces, and works in conjunction with robots used in the workplace. The system of the present invention includes the following components:

[0657] 1. User Device

[0658] The user terminal is a computer or smartphone used by a company's human resources personnel, through which they can input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0659] 2. Server

[0660] The server is the central computer system for the entire system. It is equipped with AI to collect and analyze candidate information from multiple data sources. This server generates appropriate search queries based on the recruitment requirements entered by HR personnel and sends API requests to multiple data sources (e.g., LinkedIn, GitHub, etc.).

[0661] 3. Robot

[0662] Robots are automated devices that assist with work in factories and are also involved in the recruitment process, particularly in selecting candidates with skills relevant to factory work and arranging interviews.

[0663] 4. Data Source

[0664] Data sources are multiple sources used to obtain candidate information, including LinkedIn, GitHub, university databases, social media, etc.

[0665] System Operation

[0666] The server receives the hiring requirements entered by the HR personnel through the user's device and generates a search query based on them. This query is used to collect and integrate candidate information from multiple data sources. The collected data is analyzed by AI on the server, and a list of candidates who best match the hiring requirements is generated.

[0667] The server then uses the candidate information to generate a customized scouting email containing the candidate's name, a company profile, details of the position, and instructions on the application process, which is then automatically sent to selected candidates.

[0668] Furthermore, when a candidate replies to a scouting email, that information is sent to the server. The server automatically adjusts the interview schedule between the candidate and the company and determines the optimal interview date and time. Once the interview date and time are decided, both the candidate and the company are notified.

[0669] Specific examples

[0670] For example, a human resources manager at a factory might use a smartphone to enter the following information about a "mechanical engineer" position:

[0671] Work Experience: Mechanical Engineer

[0672] Skill set: Machine maintenance, programming

[0673] Years of experience: 5 years or more

[0674] Industry knowledge: Automation technology

[0675] Based on this, the server searches for candidates from LinkedIn and GitHub, automatically generates a list of the best candidates, and then generates and sends customized scouting emails to the selected candidates, as follows:

[0676] "Hello [candidate's name],

[0677] After looking at your profile, we believe you may be interested in our mechanical engineer position, so we are sending you a scouting email.

[0678] Please consider applying.

[0679] Application link: [Application link]

[0680] Available interview dates and times are automatically arranged by the server and notified to candidates and companies.

[0681] In this way, the system of the present invention streamlines a company's recruitment process, and enables the rapid recruitment of personnel who can immediately contribute to on-site operations in particular.

[0682] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0683] Step 1:

[0684] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. The input data is sent to the server in JSON format.

[0685] Input: Recruitment requirements (work history, skill set, years of experience, industry knowledge)

[0686] Output: Recruitment requirements data sent to the server

[0687] Step 2:

[0688] The server generates a search query based on the received job requirements data. This search query is used to send API requests to multiple data sources. Specifically, a query is generated to search for candidates that match the job requirements.

[0689] Input: Recruitment requirements data

[0690] Output: Search query

[0691] Step 3:

[0692] The server uses the generated search query to send API requests to multiple data sources, retrieving candidate information from LinkedIn, GitHub, university databases, etc.

[0693] Input: Search query

[0694] Output: Candidate information retrieved from the data source

[0695] Step 4:

[0696] The server integrates candidate information collected from multiple data sources and analyzes it based on the hiring requirements. This generates a list of optimal candidates. Specifically, the AI ​​model evaluates the candidate's work history and skill set and calculates the degree of match with the hiring requirements.

[0697] Input: Collected candidate information

[0698] Output: A list of the best candidates

[0699] Step 5:

[0700] The server generates a customized scouting email based on the best candidates list. The scouting email includes the candidate's name, company profile, details of the job position, and an explanation of the application process. The generated scouting email is automatically sent to the candidate.

[0701] Input: Best candidate list

[0702] Output: Scout email sent

[0703] Step 6:

[0704] When a candidate replies to a scouting email, the information is sent to the server, which receives the candidate's reply, checks available interview schedules, and collects the schedules of the company's interviewers.

[0705] Input: Candidate's reply

[0706] Output: Candidate and interviewer schedule data

[0707] Step 7:

[0708] The server adjusts the optimal interview date based on the schedule data of the candidate and the company's interviewers, automatically selecting a date and time that is convenient for both the candidate and the company.

[0709] Input: Candidate and interviewer schedule data

[0710] Output: Optimal interview dates

[0711] Step 8:

[0712] The server notifies both the candidate and the company's interviewer of the confirmed interview date via email or calendar notification.

[0713] Input: Best interview date

[0714] Output: Interview schedule notification

[0715] 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.

[0716] The present invention provides a system for streamlining a company's recruitment process and taking into account the emotional states of both candidates and companies. The system includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for combining an emotional engine to recognize emotional states and optimize the content of the scout emails and the interview schedules.

[0717] Specific Embodiments of the System

[0718] System Configuration

[0719] 1. User Device: A computer or mobile device used by a company's human resources personnel and candidates.

[0720] 2. Server: A computer system that provides AI-driven recruiting services, including an emotion engine.

[0721] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[0722] Program processing explanation

[0723] Candidate Matching

[0724] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[0725] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[0726] Scout email generation and emotion recognition

[0727] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state and optimize the email content based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[0728] Interview scheduling and emotion recognition

[0729] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0730] The server collects both parties' schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. The server automatically schedules the optimal interview date to reduce stress and discomfort. The confirmed interview date is notified to both the candidate and the company's interviewer.

[0731] Specific examples

[0732] Candidate Matching Example

[0733] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[0734] Work Experience: Software Engineer

[0735] Skill Set: Python, Machine Learning

[0736] Years of experience: 3 years or more

[0737] Industry Knowledge: Financial Technology

[0738] Based on this, the server searches each data source and creates a list of optimal candidates.

[0739] Example of scout email generation and emotion recognition

[0740] The server generates a customized scouting email based on the selected candidate list, like this:

[0741] Candidate's name

[0742] Company name and brief introduction

[0743] Job details

[0744] Application procedure explanation

[0745] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[0746] Example of interview schedule adjustment and emotion recognition

[0747] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[0748] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0752] Step 2:

[0753] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[0754] Step 3:

[0755] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases) based on the received hiring requirements.

[0756] Step 4:

[0757] The server then sends an API request to each data source using the generated search query, which collects candidate information from each data source.

[0758] Step 5:

[0759] The server collects and consolidates the candidate information returned from each data source, including the candidate's work history, skill set, years of experience, contact details, and more.

[0760] Step 6:

[0761] The server analyzes the collected candidate information and generates a list of candidates who best fit the company's hiring requirements, using an algorithm to evaluate each candidate's suitability.

[0762] Step 7:

[0763] The server selects a scouting email template based on the best candidates list, which includes company information and details of the job opening.

[0764] Step 8:

[0765] The server uses an emotion engine to recognize the candidate's emotional state and optimizes the content of the scouting email based on the candidate's interest and reactions. For example, if a candidate has shown positive reactions in the past, the email content will reflect those characteristics.

[0766] Step 9:

[0767] The server automatically sends customized scouting emails to candidates, each containing candidate-specific information.

[0768] Step 10:

[0769] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[0770] Step 11:

[0771] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[0772] Step 12:

[0773] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[0774] Step 13:

[0775] The server collects schedule data for candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, and automatically arranges optimal interview dates to avoid stress or discomfort for either candidate or interviewer.

[0776] Step 14:

[0777] The server notifies the candidate and the company's interviewer of the confirmed interview date by email or other means, and the schedule is confirmed.

[0778] Example 2

[0779] 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."

[0780] In the traditional recruitment process, a company's human resources personnel must manage a huge amount of candidate information and spend a lot of time and effort to respond appropriately to each candidate. It is also difficult to conduct recruitment activities taking into account the emotional state of both the candidate and the company, which can lead to inappropriate interview schedules and inappropriate content in scouting emails. This can result in an inefficient recruitment process, leaving candidates and companies dissatisfied.

[0781] 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.

[0782] In this invention, the server includes: a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple sources and analyzing the candidates based on the recruitment requirements; a means for generating customized emails and sending them to selected candidates; a means for automatically coordinating interview schedules between candidates and companies; a means for recognizing the emotional states of candidates and companies using an emotion engine; and a means for optimizing the content of emails and interview schedules based on the emotional states. This makes it possible to automate the recruitment process and conduct smooth recruitment activities by taking into account the emotional states of both companies and candidates.

[0783] A "corporate human resources officer" is a person who is engaged in the job of selecting candidates and handling recruitment procedures within a company.

[0784] "Work history" refers to information about the job history and positions held by a candidate.

[0785] A "skill set" refers to the specific set of skills and abilities a candidate possesses.

[0786] "Years of experience" is information that indicates the number of years a candidate has worked in a particular job or industry.

[0787] "Industry knowledge" refers to the specialized knowledge a candidate has about a particular industry.

[0788] "Sources" are external databases or platforms from which data about candidates is obtained.

[0789] "Candidate Information" refers to information including data such as a candidate's work history, skill set, years of experience, and industry knowledge.

[0790] "Analysis" refers to the process of extracting, classifying, and evaluating the obtained data according to the purpose and making appropriate decisions.

[0791] "Customized email" refers to emails whose content is individually tailored based on the candidate's individual information.

[0792] An "interview schedule" is a plan that shows the dates, times, and locations of interviews between candidates and companies.

[0793] "Automatic adjustment" means that the system makes optimal adjustments without human intervention.

[0794] An "emotion engine" is technology or software that analyzes the emotional state of candidates and companies and responds based on that.

[0795] "Emotional state" refers to the psychological and emotional state of the candidate and the company, including factors such as stress, interest, and satisfaction.

[0796] "Optimization" means adjusting or improving something to be most effective or efficient for a given purpose.

[0797] A "system" is a structure in which multiple elements work together to achieve a specific purpose.

[0798] System Configuration

[0799] The present invention is a system for streamlining a company's recruitment process and taking into account the emotional state of both the candidate and the company. The system includes the following components:

[0800] User terminal

[0801] A computer or mobile device used by a company's recruiters and candidates. This includes PCs with a web browser, smartphones, tablets, etc.

[0802] server

[0803] A computer system that provides AI-driven recruiting services, including an emotion engine, and performs various data processing and analysis.

[0804] Data Source

[0805] Obtain candidate information from multiple sources (e.g., social media platforms, professional networking sites, university databases, etc.).

[0806] Program processing explanation

[0807] Candidate Matching

[0808] The user (a company's human resources officer) uses a user terminal to enter recruitment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The entered information is sent to the server, which generates a search query based on this information. The generated query is used to send an API request to multiple data sources. The candidate information returned from each data source is collected and integrated. The integrated data is analyzed based on the company's recruitment requirements, and a list of optimal candidates is generated.

[0809] Scout email generation and emotion recognition

[0810] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state. The content of the email is optimized based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[0811] Interview scheduling and emotion recognition

[0812] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff similarly enters the interviewer's schedule and sends it to the server. The server collects this schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. It then automatically arranges the optimal interview date to reduce stress and discomfort. The confirmed interview date is then notified to both the candidate and the company's interviewer.

[0813] Specific examples

[0814] Candidate Matching Example

[0815] The user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[0816] Work Experience: Software Engineer

[0817] Skill Set: Python, Machine Learning

[0818] Years of experience: 3 years or more

[0819] Industry Knowledge: Financial Technology

[0820] Based on this, the server searches each data source and creates a list of the best candidates.

[0821] Example of scout email generation and emotion recognition

[0822] The server generates a customized scouting email based on the selected candidate list, like this:

[0823] Candidate's name

[0824] Company name and brief introduction

[0825] Job details

[0826] Application procedure explanation

[0827] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[0828] Example of interview schedule adjustment and emotion recognition

[0829] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[0830] The present invention can be implemented by using a generative AI model to create example prompts as follows:

[0831] "Find a Software Engineer candidate with the following skill set: Python, Machine Learning, 3+ years of experience, Financial Technology industry"

[0832] "Generate the best scouting email from this list of candidates."

[0833] Please use the schedule below to schedule your interview.

[0834] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

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

[0836] Step 1:

[0837] The user uses a terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The input information is sent to the server. The input is the company's employment requirements, and the output is the employment requirements data saved on the server. The user's specific actions are to type the required information into the input form and click the "Submit" button.

[0838] Step 2:

[0839] The server generates a search query based on the job requirements received from the user. Here, it receives the job requirements data as input data and generates a search query as output. The specific operation of the server is to analyze the job requirements data and build a query string based on it.

[0840] Step 3:

[0841] The server uses the generated search query to send API requests to multiple data sources. The input is the search query, and the output is the candidate information collected from each data source. Specifically, the server sends an HTTP request to an API endpoint and receives the candidate information as a response.

[0842] Step 4:

[0843] The server consolidates the collected candidate information. The input is candidate information obtained from multiple data sources, and the output is consolidated candidate data. Specifically, it standardizes data in different formats and consolidates them into a single database.

[0844] Step 5:

[0845] The server analyzes the integrated candidate data based on the company's hiring requirements and generates a list of optimal candidates. The input is the integrated candidate data and hiring requirements data, and the output is a list of optimal candidates. The specific operation of the server is to analyze the data using machine learning algorithms and filtering technology.

[0846] Step 6:

[0847] The server selects a scout email template based on the list of optimal candidates and generates customized scout emails by embedding individual information for each candidate. The input is the list of optimal candidates and the scout email template, and the output is a customized scout email. Specifically, the server runs a template engine to embed individual information into the template.

[0848] Step 7:

[0849] The server uses an emotion engine to analyze the emotional state of each candidate. The input is the candidate's past activity data and reaction data, and the output is emotional state data. Specifically, the server uses an emotion analysis algorithm to evaluate the emotional state from the data.

[0850] Step 8:

[0851] The server optimizes the content of the scout email based on the emotional state data. The input is a customized scout email and the emotional state data, and the output is an optimized scout email. Specifically, the server corrects and edits the email content.

[0852] Step 9:

[0853] The server automatically sends optimized scout emails to each candidate. The input is the optimized scout email, and the output is a notification of completion of sending. The specific operation is to send the email through the mail server.

[0854] Step 10:

[0855] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is sent to the server. The input is the candidate's schedule information, and the output is the schedule information saved on the server. Specifically, the schedule information is entered into a web form and sent.

[0856] Step 11:

[0857] Similarly, the user (a company's human resources officer) also enters the interviewer's schedule and sends it to the server. The input is the company's interviewer's schedule information, and the output is the schedule information saved on the server. Specifically, the human resources officer enters information into a web form and submits it.

[0858] Step 12:

[0859] The server collects both parties' schedule data and automatically arranges the optimal interview schedule using an emotion engine. The input is the candidate's and interviewer's schedule information and emotional state data, and the output is the optimal interview schedule. The specific operation of the server is to analyze the schedule data and calculate the optimal schedule.

[0860] Step 13:

[0861] The server notifies both the candidate and the company's interviewer of the confirmed interview date. The input is the optimal interview date, and the output is a notification message. Specifically, the server sends the notification via email or a messaging system.

[0862] Through the above steps, the present invention fully automates and streamlines a company's recruitment process, realizing smooth recruitment activities that take into account the emotional states of both candidates and companies.

[0863] (Application example 2)

[0864] 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."

[0865] In the recruitment process, companies are required to efficiently find suitable candidates who meet requirements such as work history, skill set, years of experience, and industry knowledge. In delivery operations, it is also important to consider the emotional state of delivery personnel and customers to improve service quality. Conventional methods have difficulty simultaneously optimizing recruitment and delivery schedules, and this issue needs to be addressed.

[0866] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0867] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, and a means for generating customized scouting emails and sending them to selected candidates. This makes it possible to streamline the recruitment process and further evaluate the emotional states of delivery personnel and customers in delivery work and optimize delivery schedules.

[0868] "Work history" refers to a candidate's professional history and work experience.

[0869] A "skill set" refers to the collection of skills, knowledge, and abilities required for a specific job or function.

[0870] "Years of experience" refers to the length of time a candidate has actually worked in a particular occupation or industry.

[0871] "Industry knowledge" refers to specialized knowledge and information about a particular industry.

[0872] "Data Sources" are sources for collecting candidate information, including, for example, professional networking sites and university databases.

[0873] "Candidate analysis" refers to the process of evaluating and comparing the suitability and capabilities of candidates based on the recruitment requirements entered.

[0874] A "scouting email" refers to a job information email customized for a specific candidate.

[0875] "Interview scheduling" refers to the process of coordinating the schedules of the candidate and the company's interviewer and determining the optimal interview date and time.

[0876] "Delivery services" refers to the delivery of goods and services to customers.

[0877] "Delivery Person" refers to a worker who is responsible for delivering goods to customers.

[0878] "Customer" means any person or entity that receives goods or services.

[0879] "Emotional state" refers to the current emotional or mental state of an individual or group.

[0880] "Schedule optimization" refers to the process of arranging various schedules in the most efficient way, making the most of time and effort.

[0881] This invention is a system for optimizing a company's recruitment process and delivery operations. The system's main components are a server, a user terminal, multiple data sources, and an emotion engine. The specific operation of each component and the overall system configuration are described below.

[0882] System Configuration

[0883] User terminal

[0884] User terminals are devices such as computers and smartphones used by human resources personnel and candidates. They can input recruitment requirements and arrange interview schedules via the user terminals.

[0885] server

[0886] The server is a computer system that provides the core AI-driven recruiting service and delivery operation management. It includes multiple modules, such as an emotion engine, a data analysis engine, and a schedule optimization engine. This server is composed of Python programs that collect information from data sources, analyze it, recognize emotions, and send notifications.

[0887] Data Source

[0888] Data sources are the multiple sources used to gather candidate information, such as professional networking sites, project management tools, email data, and university databases.

[0889] Program processing

[0890] Data Collection and Query Generation

[0891] The server receives recruitment requirements such as work history, skill set, years of experience, and industry knowledge from a user's device. Based on this information, the server generates a search query and sends API requests to multiple data sources. The server then integrates the candidate information obtained and creates a list of optimal candidates that match the recruitment requirements.

[0892] sentiment analysis

[0893] The server uses an emotion engine such as the TextBlob library to analyze the emotional states of the scout email, delivery personnel, and customers. Based on the analysis results, the server optimizes the content of the scout email and the delivery schedule.

[0894] Generate scout emails

[0895] The server generates a customized scouting email based on the candidate list. The scouting email includes the candidate's name, company name, details of the job position, and an explanation of the application process. Based on the evaluation by the emotion engine, the content is optimized based on the candidate's interest and suitability.

[0896] Arranging interview schedules

[0897] The server collects interview schedules provided by candidates and company interviewers, and uses an emotion engine to automatically determine the optimal interview dates that minimize stress and discomfort.

[0898] Optimizing delivery schedules

[0899] The emotion engine analyzes the emotional state of delivery personnel and customers and automatically adjusts optimal delivery schedules to reduce stress and fatigue, thereby improving service quality and maximizing labor efficiency.

[0900] Specific examples

[0901] Specific examples of candidate matching

[0902] For example, a company's HR representative enters the following hiring requirements:

[0903] Work Experience: Software Engineer

[0904] Skill Set: Python, Machine Learning

[0905] Years of experience: 3 years or more

[0906] Industry Knowledge: Financial Technology

[0907] Based on this, the server searches each data source and creates a list of the most suitable candidates.

[0908] Example of scout email generation

[0909] Generate a customized scout email like this:

[0910] Candidate's name

[0911] Company name and brief introduction

[0912] Job details

[0913] Application procedure explanation

[0914] It uses an emotion engine to assess candidate interest and reactions and optimize email content accordingly.

[0915] Specific examples of interview schedule adjustments

[0916] For example, a candidate inputs the date and time they are available for an interview, and the server collects the schedules of the company's interviewers. The server then automatically determines the optimal interview date using an emotion engine and notifies both parties.

[0917] Prompt Sentence Examples

[0918] "Job Requirements: Hiring delivery drivers with at least one year of delivery experience. Skill Set: Customer service, lifesaving. Years of Experience: At least one year. Industry Knowledge: Food delivery."

[0919] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0920] Step 1:

[0921] A company's human resources staff inputs hiring requirements such as work history, skill set, years of experience, and industry knowledge into the user terminal. The user terminal then sends the hiring requirements data to the server. Once the input hiring requirements data reaches the server, the next processing step begins.

[0922] Step 2:

[0923] The server generates a search query based on the job requirements data received in the previous step. The server uses Python to generate this query and then sends API requests to multiple data sources (e.g., career networking sites, university databases, etc.) to gather candidate information.

[0924] Step 3:

[0925] The server consolidates the collected candidate information and analyzes the candidates based on the hiring requirements. This analysis process uses statistical analysis and machine learning models to select the most suitable candidates. The analysis results in a list of the best candidates, which is then passed on to the next processing step.

[0926] Step 4:

[0927] The server creates a customized scouting email for each candidate based on the generated candidate list. It uses an emotion engine (e.g., TextBlob library) to analyze the candidate's emotional state and optimize the email content based on the candidate's interest level. The optimized scouting email is then automatically sent to the candidate.

[0928] Step 5:

[0929] If a candidate receives a scouting email and is interested, they click the link in the email and enter the date and time they are available for an interview. This input data is sent from the user's terminal to the server.

[0930] Step 6:

[0931] The server collects interview schedules provided by candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, determines the optimal interview date to minimize stress and discomfort, and notifies both parties.

[0932] Step 7:

[0933] The server analyzes the emotional state of the delivery person and the customer during food delivery work. The emotion engine evaluates the delivery person using information entered by the delivery person and feedback data from the customer. Based on the evaluation results, the delivery schedule is optimized and the optimal delivery route and time slot are automatically adjusted to reduce stress.

[0934] Step 8:

[0935] The server notifies the delivery staff and customers of the optimized delivery schedule. Notifications are sent via smartphone application and email. The delivery staff delivers based on the optimized schedule and route, improving customer satisfaction.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] [Third embodiment]

[0940] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0941] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0942] 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).

[0943] 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.

[0944] 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.

[0945] 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).

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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."

[0952] The present invention is a system for streamlining a company's recruitment process, and includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for receiving candidate replies to the customized scout emails and a means for integrating the interview schedules of companies and candidates to determine optimal interview dates, thereby achieving a smooth and effective recruitment process.

[0953] Specific Embodiments of the System

[0954] System Configuration

[0955] 1. User Device: A computer or mobile device used by a company's HR personnel.

[0956] 2. Server: A computer system that provides AI-driven recruiting services.

[0957] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[0958] Program processing explanation

[0959] Candidate Matching

[0960] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[0961] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[0962] Generate and send scout emails

[0963] The server selects a scouting email template for the listed candidates and generates customized scouting emails by filling in the individual information of each candidate. The generated emails are automatically sent to each candidate.

[0964] Arranging interview schedules

[0965] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[0966] The server collects schedule data from both parties and automatically arranges the optimal interview date. The confirmed interview date is notified to both the candidate and the company interviewer.

[0967] Specific examples

[0968] Candidate Matching Example

[0969] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[0970] Work Experience: Software Engineer

[0971] Skill Set: Python, Machine Learning

[0972] Years of experience: 3 years or more

[0973] Industry Knowledge: Financial Technology

[0974] Based on this, the server searches each data source and creates a list of optimal candidates.

[0975] Example of generating a scout email

[0976] The server generates a customized scouting email based on the selected candidate list, like this:

[0977] Candidate's name

[0978] Company name and brief introduction

[0979] Job details

[0980] Application procedure explanation

[0981] The server sends the generated scout email to the candidate.

[0982] Example of adjusting interview schedule

[0983] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date. The confirmed interview date is notified to both parties.

[0984] In this way, the present invention can fully automate and streamline a company's recruitment process, improving the speed and accuracy of recruitment.

[0985] The processing flow will be explained below.

[0986] Step 1:

[0987] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[0988] Step 2:

[0989] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[0990] Step 3:

[0991] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases, etc.) based on the received hiring requirements.

[0992] Step 4:

[0993] The server sends an API request to each data source using the generated search query.

[0994] Step 5:

[0995] The server collects candidate information returned from each data source, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[0996] Step 6:

[0997] The server integrates the collected candidate information and analyzes it based on the company's hiring requirements, selecting candidates with the highest suitability and generating an optimal candidate list.

[0998] Step 7:

[0999] The server selects a template for a customized scouting email containing individual information of the candidates based on the list of optimal candidates.

[1000] Step 8:

[1001] The server embeds the candidate's name, company information, details of the job position, and other information into the template to generate a customized scouting email.

[1002] Step 9:

[1003] The server automatically sends the generated scout email to each candidate.

[1004] Step 10:

[1005] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[1006] Step 11:

[1007] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[1008] Step 12:

[1009] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[1010] Step 13:

[1011] The server collects schedule data for candidates and company interviewers, compares the schedules of both parties, and automatically arranges the optimal interview date.

[1012] Step 14:

[1013] The server notifies both the candidate and the company's interviewer of the determined interview date.

[1014] Example 1

[1015] 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."

[1016] Traditionally, companies' recruitment processes have involved a lot of manual work, which has made it time-consuming and labor-intensive, and it has been difficult to find suitable candidates. Furthermore, generating scouting emails and arranging interview schedules has also been time-consuming, making it difficult to conduct efficient recruitment activities. For this reason, companies have been seeking a way to select candidates more quickly and accurately and streamline the entire recruitment process.

[1017] 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.

[1018] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scouting emails and sending them to selected candidates, and a means for comparing candidates with company interview schedules and automatically arranging optimal interview dates. This enables companies to quickly and accurately select excellent candidates from a wide range of data sources and efficiently arrange scouting activities and interview schedules.

[1019] The "recruitment requirement input means" is a means for a company's human resources personnel to input the desired candidate conditions such as work history, skill set, years of experience, and industry knowledge.

[1020] "Data Collection Methods" means methods for collecting candidate information from multiple data sources, including online professional networking services, open source platforms, social media, and educational institution databases.

[1021] "Candidate analysis means" refers to the means of analyzing collected candidate information based on the company's recruitment requirements and selecting the most suitable candidates. This uses machine learning algorithms and filtering technology.

[1022] The "scout email generation means" is a means for generating a customized scout email incorporating individual information for a selected candidate. This means uses a template including an introduction to the company and details of the job opening.

[1023] The "scout mail sending means" is a means for automatically sending the generated customized scout mail to the candidate.

[1024] The "interview schedule adjustment means" is a means for automatically adjusting interview schedules between candidates and companies. This means compares the schedule data of both parties to determine the optimal interview date.

[1025] The "interview schedule comparison means" is a means for comparing the interview schedules of candidates and companies and automatically arranging the most suitable interview date.

[1026] The "schedule notification means" is a means for notifying the candidate and the company's interviewer of the confirmed interview date.

[1027] The present invention is a system for improving the efficiency of a company's recruitment process, and is implemented using the following hardware and software.

[1028] System Configuration

[1029] The system consists of the following elements:

[1030] 1. User Device: A computer or mobile device used by a company's HR personnel.

[1031] 2. Server: A computer system that provides AI-driven recruiting services.

[1032] 3. Data sources: Multiple online platforms (e.g., professional networking services, open source platforms, social media, educational institution databases, etc.).

[1033] Program processing explanation

[1034] Enter recruitment requirements

[1035] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server.

[1036] Data collection and analysis

[1037] The server generates a search query based on the received hiring requirements. The server then uses the generated query to send API requests to multiple data sources and collects the candidate information returned from each data source. The collected candidate information is then integrated and analyzed based on the company's hiring requirements. This analysis may involve the use of machine learning algorithms.

[1038] Generate and send scout emails

[1039] The server generates a list of optimal candidates and selects a scouting email template based on this list. It generates customized scouting emails by filling in information based on each candidate's name, experience, and skills. The generated scouting emails are automatically sent to each candidate.

[1040] Prompt Sentence Examples

[1041] For example, to generate a prompt like this:

[1042] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[1043] Arranging interview schedules

[1044] The user (candidate) clicks on the link in the scout email and enters their available schedule for an interview. This information is sent to the server. Similarly, the company's human resources staff also enters the schedule of interviewers and sends it to the server.

[1045] The server collects the schedule data of candidates and interviewers, automatically arranges the optimal interview date, and notifies both the candidate and interviewer of the confirmed interview date.

[1046] Specific examples

[1047] A user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[1048] Work Experience: Software Engineer

[1049] Skill Set: Python, Machine Learning

[1050] Years of experience: 3 years or more

[1051] Industry Knowledge: Financial Technology

[1052] Based on this, the server searches each data source and creates a list of optimal candidates.

[1053] The server then generates a customized scouting email based on the selected candidates, like this:

[1054] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[1055] The user (candidate) clicks on the link in the scouting email and enters the date and time they are available for an interview. For example, they enter "May 1st, 2:00 PM to 4:00 PM." This information is sent to the server.

[1056] The company's human resources staff also enter the interviewer's schedule, for example, "May 1st, 1:00 PM to 5:00 PM."

[1057] The server compares the schedules of the candidate and interviewer and automatically adjusts the optimal interview date to "3:00 PM on May 1st." This confirmed interview date is notified to both parties.

[1058] As mentioned above, a company's recruitment process can be fully automated and made more efficient, improving the speed and accuracy of recruitment.

[1059] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1060] Step 1: User enters hiring requirements

[1061] The user (a company's human resources officer) accesses the web interface using a user terminal. On the interface, he / she enters the hiring requirements such as work history, skill set, years of experience, and industry knowledge, and clicks the "Submit" button. The entered hiring requirements are sent to the server.

[1062] Input: Work history, skill set, years of experience, industry knowledge

[1063] Output: The job requirements data is sent to the server.

[1064] Step 2: Server generates search query

[1065] The server analyzes the received recruitment requirements data and generates search queries corresponding to each data source (professional networking services, open source platforms, social media, educational institution databases, etc.).

[1066] Input: Recruitment requirements data

[1067] Output: Generated search query

[1068] Step 3: Data collection by the server

[1069] The server sends API requests to each data source using the generated search query, which returns candidate information that the server collects, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[1070] Input: Search query

[1071] Output: Candidate information data

[1072] Step 4: Server integrates and analyzes candidate data

[1073] The server consolidates the collected candidate information and analyzes the data based on the hiring requirements, sometimes using machine learning algorithms. As a result of the analysis, a list of the best candidates is generated.

[1074] Input: Candidate information data, recruitment requirements data

[1075] Output: A list of the best candidates

[1076] Step 5: Server generates scout email

[1077] The server selects a scouting email template based on the list of optimal candidates. The template includes an introduction to the company and details of the job opening. It then fills in information based on each candidate's name, experience, and skills.

[1078] Input: Best candidate list

[1079] Output: Customized scout email

[1080] Step 6: Server sends scout email

[1081] The server automatically sends customized scouting emails to each candidate, and the sending history is also recorded as a log.

[1082] Input: Customized Scout Email

[1083] Output: Scout email sending history

[1084] Step 7: Candidate schedule entry

[1085] The user (candidate) clicks the link in the scout email and enters their available interview schedule. For example, they might enter "May 1st, 2:00 PM to 4:00 PM." After entering the information, they click the "Submit" button and this information is sent to the server.

[1086] Input: Interview Schedule

[1087] Output: Candidate interview schedule data

[1088] Step 8: Company interviewer inputs schedule

[1089] The user (a company's human resources manager) inputs the interviewer's schedule and sends it to the server. For example, the user might input "May 1st, 1:00 PM to 5:00 PM." After inputting the information, the user clicks the "Submit" button and the information is sent to the server.

[1090] Input: Interviewer Schedule

[1091] Output: Company interviewer schedule data

[1092] Step 9: Server schedules interviews

[1093] The server collects and compares the schedule data of candidates and company interviewers, and automatically arranges the optimal interview date. For example, it determines that "3:00 PM on May 1st" is the optimal date based on the candidate and interviewer's schedules.

[1094] Input: Candidate interview schedule data, company interviewer schedule data

[1095] Output: Optimal interview dates

[1096] Step 10: Notification of confirmed interview date

[1097] The server notifies both the candidate and the company's interviewer of the confirmed optimal interview date. For example, it sends a notification such as "The interview will be held at 3:00 PM on May 1st." The sending history is also recorded as a log.

[1098] Input: Best interview date

[1099] Output: Interview schedule notification, notification sending history

[1100] (Application example 1)

[1101] 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."

[1102] The traditional recruitment process involves many manual tasks, from entering recruitment requirements to selecting candidates, generating scout emails, and arranging interview schedules, resulting in inefficiency. Furthermore, particularly in factories and other workplaces, personnel familiar with specific machines and technologies are required, and searching for candidates who meet these requirements requires a great deal of effort. Furthermore, the technology used in the recruitment process is not integrated into on-site operations, resulting in time and resources being dispersed and inefficiency being reduced. Against this backdrop, there is a growing need for a more efficient and automated recruitment system.

[1103] 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.

[1104] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements; a means for generating customized scouting emails and sending them to selected candidates; and a means for a robot used in the factory to support the recruitment process. This enables the entire recruitment process to be automated and candidates to be selected efficiently. Furthermore, integrating in-factory operations with the recruitment process is expected to enable the rapid recruitment of personnel who are familiar with specific technologies and machines.

[1105] A "corporate human resources officer" is a person in charge of recruiting, managing, and evaluating human resources within a company.

[1106] "Work history" refers to information about a candidate's past jobs and work history.

[1107] A "skill set" is a specific set of skills and knowledge that a candidate possesses.

[1108] "Years of experience" refers to the number of years of work experience a candidate has accumulated in a particular job field.

[1109] "Industry knowledge" refers to specialized knowledge and understanding of a particular industry.

[1110] "Data Sources" are the multiple information sources used to obtain candidate information.

[1111] "Candidate Information" refers to data relating to a candidate's background, skills, experience, etc., that is relevant to recruitment.

[1112] A "scout email" is an email sent to a company's desired talent, conveying the company's intention to hire them.

[1113] "Means for automatic adjustment" refers to a function in which the system automatically adjusts the optimal schedule without manual operation.

[1114] The "robot" is an automated device that assists in the recruitment process within a factory.

[1115] A "system" is an integrated device consisting of multiple functional elements designed to achieve a specific purpose.

[1116] The present invention is a system for streamlining and automating a company's recruitment process. This system is intended for use in factories and other workplaces, and works in conjunction with robots used in the workplace. The system of the present invention includes the following components:

[1117] 1. User Device

[1118] The user terminal is a computer or smartphone used by a company's human resources personnel, through which they can input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[1119] 2. Server

[1120] The server is the central computer system for the entire system. It is equipped with AI to collect and analyze candidate information from multiple data sources. This server generates appropriate search queries based on the recruitment requirements entered by HR personnel and sends API requests to multiple data sources (e.g., LinkedIn, GitHub, etc.).

[1121] 3. Robot

[1122] Robots are automated devices that assist with work in factories and are also involved in the recruitment process, particularly in selecting candidates with skills relevant to factory work and arranging interviews.

[1123] 4. Data Source

[1124] Data sources are multiple sources used to obtain candidate information, including LinkedIn, GitHub, university databases, social media, etc.

[1125] System Operation

[1126] The server receives the hiring requirements entered by the HR personnel through the user's device and generates a search query based on them. This query is used to collect and integrate candidate information from multiple data sources. The collected data is analyzed by AI on the server, and a list of candidates who best match the hiring requirements is generated.

[1127] The server then uses the candidate information to generate a customized scouting email containing the candidate's name, a company profile, details of the position, and instructions on the application process, which is then automatically sent to selected candidates.

[1128] Furthermore, when a candidate replies to a scouting email, that information is sent to the server. The server automatically adjusts the interview schedule between the candidate and the company and determines the optimal interview date and time. Once the interview date and time are decided, both the candidate and the company are notified.

[1129] Specific examples

[1130] For example, a human resources manager at a factory might use a smartphone to enter the following information about a "mechanical engineer" position:

[1131] Work Experience: Mechanical Engineer

[1132] Skill set: Machine maintenance, programming

[1133] Years of experience: 5 years or more

[1134] Industry knowledge: Automation technology

[1135] Based on this, the server searches for candidates from LinkedIn and GitHub, automatically generates a list of the best candidates, and then generates and sends customized scouting emails to the selected candidates, as follows:

[1136] "Hello [candidate's name],

[1137] After looking at your profile, we believe you may be interested in our mechanical engineer position, so we are sending you a scouting email.

[1138] Please consider applying.

[1139] Application link: [Application link]

[1140] Available interview dates and times are automatically arranged by the server and notified to candidates and companies.

[1141] In this way, the system of the present invention streamlines a company's recruitment process, and enables the rapid recruitment of personnel who can immediately contribute to on-site operations in particular.

[1142] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1143] Step 1:

[1144] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. The input data is sent to the server in JSON format.

[1145] Input: Recruitment requirements (work history, skill set, years of experience, industry knowledge)

[1146] Output: Recruitment requirements data sent to the server

[1147] Step 2:

[1148] The server generates a search query based on the received job requirements data. This search query is used to send API requests to multiple data sources. Specifically, a query is generated to search for candidates that match the job requirements.

[1149] Input: Recruitment requirements data

[1150] Output: Search query

[1151] Step 3:

[1152] The server uses the generated search query to send API requests to multiple data sources, retrieving candidate information from LinkedIn, GitHub, university databases, etc.

[1153] Input: Search query

[1154] Output: Candidate information retrieved from the data source

[1155] Step 4:

[1156] The server integrates candidate information collected from multiple data sources and analyzes it based on the hiring requirements. This generates a list of optimal candidates. Specifically, the AI ​​model evaluates the candidate's work history and skill set and calculates the degree of match with the hiring requirements.

[1157] Input: Collected candidate information

[1158] Output: A list of the best candidates

[1159] Step 5:

[1160] The server generates a customized scouting email based on the best candidates list. The scouting email includes the candidate's name, company profile, details of the job position, and an explanation of the application process. The generated scouting email is automatically sent to the candidate.

[1161] Input: Best candidate list

[1162] Output: Scout email sent

[1163] Step 6:

[1164] When a candidate replies to a scouting email, the information is sent to the server, which receives the candidate's reply, checks available interview schedules, and collects the schedules of the company's interviewers.

[1165] Input: Candidate's reply

[1166] Output: Candidate and interviewer schedule data

[1167] Step 7:

[1168] The server adjusts the optimal interview date based on the schedule data of the candidate and the company's interviewers, automatically selecting a date and time that is convenient for both the candidate and the company.

[1169] Input: Candidate and interviewer schedule data

[1170] Output: Optimal interview dates

[1171] Step 8:

[1172] The server notifies both the candidate and the company's interviewer of the confirmed interview date via email or calendar notification.

[1173] Input: Best interview date

[1174] Output: Interview schedule notification

[1175] 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.

[1176] The present invention provides a system for streamlining a company's recruitment process and taking into account the emotional states of both candidates and companies. The system includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for combining an emotional engine to recognize emotional states and optimize the content of the scout emails and the interview schedules.

[1177] Specific Embodiments of the System

[1178] System Configuration

[1179] 1. User Device: A computer or mobile device used by a company's human resources personnel and candidates.

[1180] 2. Server: A computer system that provides AI-driven recruiting services, including an emotion engine.

[1181] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[1182] Program processing explanation

[1183] Candidate Matching

[1184] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[1185] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[1186] Scout email generation and emotion recognition

[1187] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state and optimize the email content based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[1188] Interview scheduling and emotion recognition

[1189] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[1190] The server collects both parties' schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. The server automatically schedules the optimal interview date to reduce stress and discomfort. The confirmed interview date is notified to both the candidate and the company's interviewer.

[1191] Specific examples

[1192] Candidate Matching Example

[1193] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[1194] Work Experience: Software Engineer

[1195] Skill Set: Python, Machine Learning

[1196] Years of experience: 3 years or more

[1197] Industry Knowledge: Financial Technology

[1198] Based on this, the server searches each data source and creates a list of optimal candidates.

[1199] Example of scout email generation and emotion recognition

[1200] The server generates a customized scouting email based on the selected candidate list, like this:

[1201] Candidate's name

[1202] Company name and brief introduction

[1203] Job details

[1204] Application procedure explanation

[1205] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[1206] Example of interview schedule adjustment and emotion recognition

[1207] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[1208] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[1209] The processing flow will be explained below.

[1210] Step 1:

[1211] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[1212] Step 2:

[1213] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[1214] Step 3:

[1215] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases) based on the received hiring requirements.

[1216] Step 4:

[1217] The server then sends an API request to each data source using the generated search query, which collects candidate information from each data source.

[1218] Step 5:

[1219] The server collects and consolidates the candidate information returned from each data source, including the candidate's work history, skill set, years of experience, contact details, and more.

[1220] Step 6:

[1221] The server analyzes the collected candidate information and generates a list of candidates who best fit the company's hiring requirements, using an algorithm to evaluate each candidate's suitability.

[1222] Step 7:

[1223] The server selects a scouting email template based on the best candidates list, which includes company information and details of the job opening.

[1224] Step 8:

[1225] The server uses an emotion engine to recognize the candidate's emotional state and optimizes the content of the scouting email based on the candidate's interest and reactions. For example, if a candidate has shown positive reactions in the past, the email content will reflect those characteristics.

[1226] Step 9:

[1227] The server automatically sends customized scouting emails to candidates, each containing candidate-specific information.

[1228] Step 10:

[1229] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[1230] Step 11:

[1231] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[1232] Step 12:

[1233] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[1234] Step 13:

[1235] The server collects schedule data for candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, and automatically arranges optimal interview dates to avoid stress or discomfort for either candidate or interviewer.

[1236] Step 14:

[1237] The server notifies the candidate and the company's interviewer of the confirmed interview date by email or other means, and the schedule is confirmed.

[1238] Example 2

[1239] 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."

[1240] In the traditional recruitment process, a company's human resources personnel must manage a huge amount of candidate information and spend a lot of time and effort to respond appropriately to each candidate. It is also difficult to conduct recruitment activities taking into account the emotional state of both the candidate and the company, which can lead to inappropriate interview schedules and inappropriate content in scouting emails. This can result in an inefficient recruitment process, leaving candidates and companies dissatisfied.

[1241] 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.

[1242] In this invention, the server includes: a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple sources and analyzing the candidates based on the recruitment requirements; a means for generating customized emails and sending them to selected candidates; a means for automatically coordinating interview schedules between candidates and companies; a means for recognizing the emotional states of candidates and companies using an emotion engine; and a means for optimizing the content of emails and interview schedules based on the emotional states. This makes it possible to automate the recruitment process and conduct smooth recruitment activities by taking into account the emotional states of both companies and candidates.

[1243] A "corporate human resources officer" is a person who is engaged in the job of selecting candidates and handling recruitment procedures within a company.

[1244] "Work history" refers to information about the job history and positions held by a candidate.

[1245] A "skill set" refers to the specific set of skills and abilities a candidate possesses.

[1246] "Years of experience" is information that indicates the number of years a candidate has worked in a particular job or industry.

[1247] "Industry knowledge" refers to the specialized knowledge a candidate has about a particular industry.

[1248] "Sources" are external databases or platforms from which data about candidates is obtained.

[1249] "Candidate Information" refers to information including data such as a candidate's work history, skill set, years of experience, and industry knowledge.

[1250] "Analysis" refers to the process of extracting, classifying, and evaluating the obtained data according to the purpose and making appropriate decisions.

[1251] "Customized email" refers to emails whose content is individually tailored based on the candidate's individual information.

[1252] An "interview schedule" is a plan that shows the dates, times, and locations of interviews between candidates and companies.

[1253] "Automatic adjustment" means that the system makes optimal adjustments without human intervention.

[1254] An "emotion engine" is technology or software that analyzes the emotional state of candidates and companies and responds based on that.

[1255] "Emotional state" refers to the psychological and emotional state of the candidate and the company, including factors such as stress, interest, and satisfaction.

[1256] "Optimization" means adjusting or improving something to be most effective or efficient for a given purpose.

[1257] A "system" is a structure in which multiple elements work together to achieve a specific purpose.

[1258] System Configuration

[1259] The present invention is a system for streamlining a company's recruitment process and taking into account the emotional state of both the candidate and the company. The system includes the following components:

[1260] User terminal

[1261] A computer or mobile device used by a company's recruiters and candidates. This includes PCs with a web browser, smartphones, tablets, etc.

[1262] server

[1263] A computer system that provides AI-driven recruiting services, including an emotion engine, and performs various data processing and analysis.

[1264] Data Source

[1265] Obtain candidate information from multiple sources (e.g., social media platforms, professional networking sites, university databases, etc.).

[1266] Program processing explanation

[1267] Candidate Matching

[1268] The user (a company's human resources officer) uses a user terminal to enter recruitment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The entered information is sent to the server, which generates a search query based on this information. The generated query is used to send an API request to multiple data sources. The candidate information returned from each data source is collected and integrated. The integrated data is analyzed based on the company's recruitment requirements, and a list of optimal candidates is generated.

[1269] Scout email generation and emotion recognition

[1270] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state. The content of the email is optimized based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[1271] Interview scheduling and emotion recognition

[1272] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff similarly enters the interviewer's schedule and sends it to the server. The server collects this schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. It then automatically arranges the optimal interview date to reduce stress and discomfort. The confirmed interview date is then notified to both the candidate and the company's interviewer.

[1273] Specific examples

[1274] Candidate Matching Example

[1275] The user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[1276] Work Experience: Software Engineer

[1277] Skill Set: Python, Machine Learning

[1278] Years of experience: 3 years or more

[1279] Industry Knowledge: Financial Technology

[1280] Based on this, the server searches each data source and creates a list of the best candidates.

[1281] Example of scout email generation and emotion recognition

[1282] The server generates a customized scouting email based on the selected candidate list, like this:

[1283] Candidate's name

[1284] Company name and brief introduction

[1285] Job details

[1286] Application procedure explanation

[1287] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[1288] Example of interview schedule adjustment and emotion recognition

[1289] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[1290] The present invention can be implemented by using a generative AI model to create example prompts as follows:

[1291] "Find a Software Engineer candidate with the following skill set: Python, Machine Learning, 3+ years of experience, Financial Technology industry"

[1292] "Generate the best scouting email from this list of candidates."

[1293] Please use the schedule below to schedule your interview.

[1294] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[1295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1296] Step 1:

[1297] The user uses a terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The input information is sent to the server. The input is the company's employment requirements, and the output is the employment requirements data saved on the server. The user's specific actions are to type the required information into the input form and click the "Submit" button.

[1298] Step 2:

[1299] The server generates a search query based on the job requirements received from the user. Here, it receives the job requirements data as input data and generates a search query as output. The specific operation of the server is to analyze the job requirements data and build a query string based on it.

[1300] Step 3:

[1301] The server uses the generated search query to send API requests to multiple data sources. The input is the search query, and the output is the candidate information collected from each data source. Specifically, the server sends an HTTP request to an API endpoint and receives the candidate information as a response.

[1302] Step 4:

[1303] The server consolidates the collected candidate information. The input is candidate information obtained from multiple data sources, and the output is consolidated candidate data. Specifically, it standardizes data in different formats and consolidates them into a single database.

[1304] Step 5:

[1305] The server analyzes the integrated candidate data based on the company's hiring requirements and generates a list of optimal candidates. The input is the integrated candidate data and hiring requirements data, and the output is a list of optimal candidates. The specific operation of the server is to analyze the data using machine learning algorithms and filtering technology.

[1306] Step 6:

[1307] The server selects a scout email template based on the list of optimal candidates and generates customized scout emails by embedding individual information for each candidate. The input is the list of optimal candidates and the scout email template, and the output is a customized scout email. Specifically, the server runs a template engine to embed individual information into the template.

[1308] Step 7:

[1309] The server uses an emotion engine to analyze the emotional state of each candidate. The input is the candidate's past activity data and reaction data, and the output is emotional state data. Specifically, the server uses an emotion analysis algorithm to evaluate the emotional state from the data.

[1310] Step 8:

[1311] The server optimizes the content of the scout email based on the emotional state data. The input is a customized scout email and the emotional state data, and the output is an optimized scout email. Specifically, the server corrects and edits the email content.

[1312] Step 9:

[1313] The server automatically sends optimized scout emails to each candidate. The input is the optimized scout email, and the output is a notification of completion of sending. The specific operation is to send the email through the mail server.

[1314] Step 10:

[1315] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is sent to the server. The input is the candidate's schedule information, and the output is the schedule information saved on the server. Specifically, the schedule information is entered into a web form and sent.

[1316] Step 11:

[1317] Similarly, the user (a company's human resources officer) also enters the interviewer's schedule and sends it to the server. The input is the company's interviewer's schedule information, and the output is the schedule information saved on the server. Specifically, the human resources officer enters information into a web form and submits it.

[1318] Step 12:

[1319] The server collects both parties' schedule data and automatically arranges the optimal interview schedule using an emotion engine. The input is the candidate's and interviewer's schedule information and emotional state data, and the output is the optimal interview schedule. The specific operation of the server is to analyze the schedule data and calculate the optimal schedule.

[1320] Step 13:

[1321] The server notifies both the candidate and the company's interviewer of the confirmed interview date. The input is the optimal interview date, and the output is a notification message. Specifically, the server sends the notification via email or a messaging system.

[1322] Through the above steps, the present invention fully automates and streamlines a company's recruitment process, realizing smooth recruitment activities that take into account the emotional states of both candidates and companies.

[1323] (Application example 2)

[1324] 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."

[1325] In the recruitment process, companies are required to efficiently find suitable candidates who meet requirements such as work history, skill set, years of experience, and industry knowledge. In delivery operations, it is also important to consider the emotional state of delivery personnel and customers to improve service quality. Conventional methods have difficulty simultaneously optimizing recruitment and delivery schedules, and this issue needs to be addressed.

[1326] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1327] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, and a means for generating customized scouting emails and sending them to selected candidates. This makes it possible to streamline the recruitment process and further evaluate the emotional states of delivery personnel and customers in delivery work and optimize delivery schedules.

[1328] "Work history" refers to a candidate's professional history and work experience.

[1329] A "skill set" refers to the collection of skills, knowledge, and abilities required for a specific job or function.

[1330] "Years of experience" refers to the length of time a candidate has actually worked in a particular occupation or industry.

[1331] "Industry knowledge" refers to specialized knowledge and information about a particular industry.

[1332] "Data Sources" are sources for collecting candidate information, including, for example, professional networking sites and university databases.

[1333] "Candidate analysis" refers to the process of evaluating and comparing the suitability and capabilities of candidates based on the recruitment requirements entered.

[1334] A "scouting email" refers to a job information email customized for a specific candidate.

[1335] "Interview scheduling" refers to the process of coordinating the schedules of the candidate and the company's interviewer and determining the optimal interview date and time.

[1336] "Delivery services" refers to the delivery of goods and services to customers.

[1337] "Delivery Person" refers to a worker who is responsible for delivering goods to customers.

[1338] "Customer" means any person or entity that receives goods or services.

[1339] "Emotional state" refers to the current emotional or mental state of an individual or group.

[1340] "Schedule optimization" refers to the process of arranging various schedules in the most efficient way, making the most of time and effort.

[1341] This invention is a system for optimizing a company's recruitment process and delivery operations. The system's main components are a server, a user terminal, multiple data sources, and an emotion engine. The specific operation of each component and the overall system configuration are described below.

[1342] System Configuration

[1343] User terminal

[1344] User terminals are devices such as computers and smartphones used by human resources personnel and candidates. They can input recruitment requirements and arrange interview schedules via the user terminals.

[1345] server

[1346] The server is a computer system that provides the core AI-driven recruiting service and delivery operation management. It includes multiple modules, such as an emotion engine, a data analysis engine, and a schedule optimization engine. This server is composed of Python programs that collect information from data sources, analyze it, recognize emotions, and send notifications.

[1347] Data Source

[1348] Data sources are the multiple sources used to gather candidate information, such as professional networking sites, project management tools, email data, and university databases.

[1349] Program processing

[1350] Data Collection and Query Generation

[1351] The server receives recruitment requirements such as work history, skill set, years of experience, and industry knowledge from a user's device. Based on this information, the server generates a search query and sends API requests to multiple data sources. The server then integrates the candidate information obtained and creates a list of optimal candidates that match the recruitment requirements.

[1352] sentiment analysis

[1353] The server uses an emotion engine such as the TextBlob library to analyze the emotional states of the scout email, delivery personnel, and customers. Based on the analysis results, the server optimizes the content of the scout email and the delivery schedule.

[1354] Generate scout emails

[1355] The server generates a customized scouting email based on the candidate list. The scouting email includes the candidate's name, company name, details of the job position, and an explanation of the application process. Based on the evaluation by the emotion engine, the content is optimized based on the candidate's interest and suitability.

[1356] Arranging interview schedules

[1357] The server collects interview schedules provided by candidates and company interviewers, and uses an emotion engine to automatically determine the optimal interview dates that minimize stress and discomfort.

[1358] Optimizing delivery schedules

[1359] The emotion engine analyzes the emotional state of delivery personnel and customers and automatically adjusts optimal delivery schedules to reduce stress and fatigue, thereby improving service quality and maximizing labor efficiency.

[1360] Specific examples

[1361] Specific examples of candidate matching

[1362] For example, a company's HR representative enters the following hiring requirements:

[1363] Work Experience: Software Engineer

[1364] Skill Set: Python, Machine Learning

[1365] Years of experience: 3 years or more

[1366] Industry Knowledge: Financial Technology

[1367] Based on this, the server searches each data source and creates a list of the most suitable candidates.

[1368] Example of scout email generation

[1369] Generate a customized scout email like this:

[1370] Candidate's name

[1371] Company name and brief introduction

[1372] Job details

[1373] Application procedure explanation

[1374] It uses an emotion engine to assess candidate interest and reactions and optimize email content accordingly.

[1375] Specific examples of interview schedule adjustments

[1376] For example, a candidate inputs the date and time they are available for an interview, and the server collects the schedules of the company's interviewers. The server then automatically determines the optimal interview date using an emotion engine and notifies both parties.

[1377] Prompt Sentence Examples

[1378] "Job Requirements: Hiring delivery drivers with at least one year of delivery experience. Skill Set: Customer service, lifesaving. Years of Experience: At least one year. Industry Knowledge: Food delivery."

[1379] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1380] Step 1:

[1381] A company's human resources staff inputs hiring requirements such as work history, skill set, years of experience, and industry knowledge into the user terminal. The user terminal then sends the hiring requirements data to the server. Once the input hiring requirements data reaches the server, the next processing step begins.

[1382] Step 2:

[1383] The server generates a search query based on the job requirements data received in the previous step. The server uses Python to generate this query and then sends API requests to multiple data sources (e.g., career networking sites, university databases, etc.) to gather candidate information.

[1384] Step 3:

[1385] The server consolidates the collected candidate information and analyzes the candidates based on the hiring requirements. This analysis process uses statistical analysis and machine learning models to select the most suitable candidates. The analysis results in a list of the best candidates, which is then passed on to the next processing step.

[1386] Step 4:

[1387] The server creates a customized scouting email for each candidate based on the generated candidate list. It uses an emotion engine (e.g., TextBlob library) to analyze the candidate's emotional state and optimize the email content based on the candidate's interest level. The optimized scouting email is then automatically sent to the candidate.

[1388] Step 5:

[1389] If a candidate receives a scouting email and is interested, they click the link in the email and enter the date and time they are available for an interview. This input data is sent from the user's terminal to the server.

[1390] Step 6:

[1391] The server collects interview schedules provided by candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, determines the optimal interview date to minimize stress and discomfort, and notifies both parties.

[1392] Step 7:

[1393] The server analyzes the emotional state of the delivery person and the customer during food delivery work. The emotion engine evaluates the delivery person using information entered by the delivery person and feedback data from the customer. Based on the evaluation results, the delivery schedule is optimized and the optimal delivery route and time slot are automatically adjusted to reduce stress.

[1394] Step 8:

[1395] The server notifies the delivery staff and customers of the optimized delivery schedule. Notifications are sent via smartphone application and email. The delivery staff delivers based on the optimized schedule and route, improving customer satisfaction.

[1396] 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.

[1397] 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.

[1398] 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.

[1399] [Fourth embodiment]

[1400] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1401] 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.

[1402] 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).

[1403] 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.

[1404] 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.

[1405] 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).

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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.

[1411] 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.

[1412] 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."

[1413] The present invention is a system for streamlining a company's recruitment process, and includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for receiving candidate replies to the customized scout emails and a means for integrating the interview schedules of companies and candidates to determine optimal interview dates, thereby achieving a smooth and effective recruitment process.

[1414] Specific Embodiments of the System

[1415] System Configuration

[1416] 1. User Device: A computer or mobile device used by a company's HR personnel.

[1417] 2. Server: A computer system that provides AI-driven recruiting services.

[1418] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[1419] Program processing explanation

[1420] Candidate Matching

[1421] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[1422] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[1423] Generate and send scout emails

[1424] The server selects a scouting email template for the listed candidates and generates customized scouting emails by filling in the individual information of each candidate. The generated emails are automatically sent to each candidate.

[1425] Arranging interview schedules

[1426] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[1427] The server collects schedule data from both parties and automatically arranges the optimal interview date. The confirmed interview date is notified to both the candidate and the company interviewer.

[1428] Specific examples

[1429] Candidate Matching Example

[1430] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[1431] Work Experience: Software Engineer

[1432] Skill Set: Python, Machine Learning

[1433] Years of experience: 3 years or more

[1434] Industry Knowledge: Financial Technology

[1435] Based on this, the server searches each data source and creates a list of optimal candidates.

[1436] Example of generating a scout email

[1437] The server generates a customized scouting email based on the selected candidate list, like this:

[1438] Candidate's name

[1439] Company name and brief introduction

[1440] Job details

[1441] Application procedure explanation

[1442] The server sends the generated scout email to the candidate.

[1443] Example of adjusting interview schedule

[1444] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date. The confirmed interview date is notified to both parties.

[1445] In this way, the present invention can fully automate and streamline a company's recruitment process, improving the speed and accuracy of recruitment.

[1446] The processing flow will be explained below.

[1447] Step 1:

[1448] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[1449] Step 2:

[1450] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[1451] Step 3:

[1452] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases, etc.) based on the received hiring requirements.

[1453] Step 4:

[1454] The server sends an API request to each data source using the generated search query.

[1455] Step 5:

[1456] The server collects candidate information returned from each data source, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[1457] Step 6:

[1458] The server integrates the collected candidate information and analyzes it based on the company's hiring requirements, selecting candidates with the highest suitability and generating an optimal candidate list.

[1459] Step 7:

[1460] The server selects a template for a customized scouting email containing individual information of the candidates based on the list of optimal candidates.

[1461] Step 8:

[1462] The server embeds the candidate's name, company information, details of the job position, and other information into the template to generate a customized scouting email.

[1463] Step 9:

[1464] The server automatically sends the generated scout email to each candidate.

[1465] Step 10:

[1466] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[1467] Step 11:

[1468] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[1469] Step 12:

[1470] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[1471] Step 13:

[1472] The server collects schedule data for candidates and company interviewers, compares the schedules of both parties, and automatically arranges the optimal interview date.

[1473] Step 14:

[1474] The server notifies both the candidate and the company's interviewer of the determined interview date.

[1475] Example 1

[1476] 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."

[1477] Traditionally, companies' recruitment processes have involved a lot of manual work, which has made it time-consuming and labor-intensive, and it has been difficult to find suitable candidates. Furthermore, generating scouting emails and arranging interview schedules has also been time-consuming, making it difficult to conduct efficient recruitment activities. For this reason, companies have been seeking a way to select candidates more quickly and accurately and streamline the entire recruitment process.

[1478] 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.

[1479] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scouting emails and sending them to selected candidates, and a means for comparing candidates with company interview schedules and automatically arranging optimal interview dates. This enables companies to quickly and accurately select excellent candidates from a wide range of data sources and efficiently arrange scouting activities and interview schedules.

[1480] The "recruitment requirement input means" is a means for a company's human resources personnel to input the desired candidate conditions such as work history, skill set, years of experience, and industry knowledge.

[1481] "Data Collection Methods" means methods for collecting candidate information from multiple data sources, including online professional networking services, open source platforms, social media, and educational institution databases.

[1482] "Candidate analysis means" refers to the means of analyzing collected candidate information based on the company's recruitment requirements and selecting the most suitable candidates. This uses machine learning algorithms and filtering technology.

[1483] The "scout email generation means" is a means for generating a customized scout email incorporating individual information for a selected candidate. This means uses a template including an introduction to the company and details of the job opening.

[1484] The "scout mail sending means" is a means for automatically sending the generated customized scout mail to the candidate.

[1485] The "interview schedule adjustment means" is a means for automatically adjusting interview schedules between candidates and companies. This means compares the schedule data of both parties to determine the optimal interview date.

[1486] The "interview schedule comparison means" is a means for comparing the interview schedules of candidates and companies and automatically arranging the most suitable interview date.

[1487] The "schedule notification means" is a means for notifying the candidate and the company's interviewer of the confirmed interview date.

[1488] The present invention is a system for improving the efficiency of a company's recruitment process, and is implemented using the following hardware and software.

[1489] System Configuration

[1490] The system consists of the following elements:

[1491] 1. User Device: A computer or mobile device used by a company's HR personnel.

[1492] 2. Server: A computer system that provides AI-driven recruiting services.

[1493] 3. Data sources: Multiple online platforms (e.g., professional networking services, open source platforms, social media, educational institution databases, etc.).

[1494] Program processing explanation

[1495] Enter recruitment requirements

[1496] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server.

[1497] Data collection and analysis

[1498] The server generates a search query based on the received hiring requirements. The server then uses the generated query to send API requests to multiple data sources and collects the candidate information returned from each data source. The collected candidate information is then integrated and analyzed based on the company's hiring requirements. This analysis may involve the use of machine learning algorithms.

[1499] Generate and send scout emails

[1500] The server generates a list of optimal candidates and selects a scouting email template based on this list. It generates customized scouting emails by filling in information based on each candidate's name, experience, and skills. The generated scouting emails are automatically sent to each candidate.

[1501] Prompt Sentence Examples

[1502] For example, to generate a prompt like this:

[1503] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[1504] Arranging interview schedules

[1505] The user (candidate) clicks on the link in the scout email and enters their available schedule for an interview. This information is sent to the server. Similarly, the company's human resources staff also enters the schedule of interviewers and sends it to the server.

[1506] The server collects the schedule data of candidates and interviewers, automatically arranges the optimal interview date, and notifies both the candidate and interviewer of the confirmed interview date.

[1507] Specific examples

[1508] A user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[1509] Work Experience: Software Engineer

[1510] Skill Set: Python, Machine Learning

[1511] Years of experience: 3 years or more

[1512] Industry Knowledge: Financial Technology

[1513] Based on this, the server searches each data source and creates a list of optimal candidates.

[1514] The server then generates a customized scouting email based on the selected candidates, like this:

[1515] "Dear XX, our company XX is interested in your Python and machine learning skills. Please see the following link for details."

[1516] The user (candidate) clicks on the link in the scouting email and enters the date and time they are available for an interview. For example, they enter "May 1st, 2:00 PM to 4:00 PM." This information is sent to the server.

[1517] The company's human resources staff also enter the interviewer's schedule, for example, "May 1st, 1:00 PM to 5:00 PM."

[1518] The server compares the schedules of the candidate and interviewer and automatically adjusts the optimal interview date to "3:00 PM on May 1st." This confirmed interview date is notified to both parties.

[1519] As mentioned above, a company's recruitment process can be fully automated and made more efficient, improving the speed and accuracy of recruitment.

[1520] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1521] Step 1: User enters hiring requirements

[1522] The user (a company's human resources officer) accesses the web interface using a user terminal. On the interface, he / she enters the hiring requirements such as work history, skill set, years of experience, and industry knowledge, and clicks the "Submit" button. The entered hiring requirements are sent to the server.

[1523] Input: Work history, skill set, years of experience, industry knowledge

[1524] Output: The job requirements data is sent to the server.

[1525] Step 2: Server generates search query

[1526] The server analyzes the received recruitment requirements data and generates search queries corresponding to each data source (professional networking services, open source platforms, social media, educational institution databases, etc.).

[1527] Input: Recruitment requirements data

[1528] Output: Generated search query

[1529] Step 3: Data collection by the server

[1530] The server sends API requests to each data source using the generated search query, which returns candidate information that the server collects, including the candidate's work history, skill set, years of experience, industry knowledge, etc.

[1531] Input: Search query

[1532] Output: Candidate information data

[1533] Step 4: Server integrates and analyzes candidate data

[1534] The server consolidates the collected candidate information and analyzes the data based on the hiring requirements, sometimes using machine learning algorithms. As a result of the analysis, a list of the best candidates is generated.

[1535] Input: Candidate information data, recruitment requirements data

[1536] Output: A list of the best candidates

[1537] Step 5: Server generates scout email

[1538] The server selects a scouting email template based on the list of optimal candidates. The template includes an introduction to the company and details of the job opening. It then fills in information based on each candidate's name, experience, and skills.

[1539] Input: Best candidate list

[1540] Output: Customized scout email

[1541] Step 6: Server sends scout email

[1542] The server automatically sends customized scouting emails to each candidate, and the sending history is also recorded as a log.

[1543] Input: Customized Scout Email

[1544] Output: Scout email sending history

[1545] Step 7: Candidate schedule entry

[1546] The user (candidate) clicks the link in the scout email and enters their available interview schedule. For example, they might enter "May 1st, 2:00 PM to 4:00 PM." After entering the information, they click the "Submit" button and this information is sent to the server.

[1547] Input: Interview Schedule

[1548] Output: Candidate interview schedule data

[1549] Step 8: Company interviewer inputs schedule

[1550] The user (a company's human resources manager) inputs the interviewer's schedule and sends it to the server. For example, the user might input "May 1st, 1:00 PM to 5:00 PM." After inputting the information, the user clicks the "Submit" button and the information is sent to the server.

[1551] Input: Interviewer Schedule

[1552] Output: Company interviewer schedule data

[1553] Step 9: Server schedules interviews

[1554] The server collects and compares the schedule data of candidates and company interviewers, and automatically arranges the optimal interview date. For example, it determines that "3:00 PM on May 1st" is the optimal date based on the candidate and interviewer's schedules.

[1555] Input: Candidate interview schedule data, company interviewer schedule data

[1556] Output: Optimal interview dates

[1557] Step 10: Notification of confirmed interview date

[1558] The server notifies both the candidate and the company's interviewer of the confirmed optimal interview date. For example, it sends a notification such as "The interview will be held at 3:00 PM on May 1st." The sending history is also recorded as a log.

[1559] Input: Best interview date

[1560] Output: Interview schedule notification, notification sending history

[1561] (Application example 1)

[1562] 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."

[1563] The traditional recruitment process involves many manual tasks, from entering recruitment requirements to selecting candidates, generating scout emails, and arranging interview schedules, resulting in inefficiency. Furthermore, particularly in factories and other workplaces, personnel familiar with specific machines and technologies are required, and searching for candidates who meet these requirements requires a great deal of effort. Furthermore, the technology used in the recruitment process is not integrated into on-site operations, resulting in time and resources being dispersed and inefficiency being reduced. Against this backdrop, there is a growing need for a more efficient and automated recruitment system.

[1564] 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.

[1565] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements; a means for generating customized scouting emails and sending them to selected candidates; and a means for a robot used in the factory to support the recruitment process. This enables the entire recruitment process to be automated and candidates to be selected efficiently. Furthermore, integrating in-factory operations with the recruitment process is expected to enable the rapid recruitment of personnel who are familiar with specific technologies and machines.

[1566] A "corporate human resources officer" is a person in charge of recruiting, managing, and evaluating human resources within a company.

[1567] "Work history" refers to information about a candidate's past jobs and work history.

[1568] A "skill set" is a specific set of skills and knowledge that a candidate possesses.

[1569] "Years of experience" refers to the number of years of work experience a candidate has accumulated in a particular job field.

[1570] "Industry knowledge" refers to specialized knowledge and understanding of a particular industry.

[1571] "Data Sources" are the multiple information sources used to obtain candidate information.

[1572] "Candidate Information" refers to data relating to a candidate's background, skills, experience, etc., that is relevant to recruitment.

[1573] A "scout email" is an email sent to a company's desired talent, conveying the company's intention to hire them.

[1574] "Means for automatic adjustment" refers to a function in which the system automatically adjusts the optimal schedule without manual operation.

[1575] The "robot" is an automated device that assists in the recruitment process within a factory.

[1576] A "system" is an integrated device consisting of multiple functional elements designed to achieve a specific purpose.

[1577] The present invention is a system for streamlining and automating a company's recruitment process. This system is intended for use in factories and other workplaces, and works in conjunction with robots used in the workplace. The system of the present invention includes the following components:

[1578] 1. User Device

[1579] The user terminal is a computer or smartphone used by a company's human resources personnel, through which they can input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[1580] 2. Server

[1581] The server is the central computer system for the entire system. It is equipped with AI to collect and analyze candidate information from multiple data sources. This server generates appropriate search queries based on the recruitment requirements entered by HR personnel and sends API requests to multiple data sources (e.g., LinkedIn, GitHub, etc.).

[1582] 3. Robot

[1583] Robots are automated devices that assist with work in factories and are also involved in the recruitment process, particularly in selecting candidates with skills relevant to factory work and arranging interviews.

[1584] 4. Data Source

[1585] Data sources are multiple sources used to obtain candidate information, including LinkedIn, GitHub, university databases, social media, etc.

[1586] System Operation

[1587] The server receives the hiring requirements entered by the HR personnel through the user's device and generates a search query based on them. This query is used to collect and integrate candidate information from multiple data sources. The collected data is analyzed by AI on the server, and a list of candidates who best match the hiring requirements is generated.

[1588] The server then uses the candidate information to generate a customized scouting email containing the candidate's name, a company profile, details of the position, and instructions on the application process, which is then automatically sent to selected candidates.

[1589] Furthermore, when a candidate replies to a scouting email, that information is sent to the server. The server automatically adjusts the interview schedule between the candidate and the company and determines the optimal interview date and time. Once the interview date and time are decided, both the candidate and the company are notified.

[1590] Specific examples

[1591] For example, a human resources manager at a factory might use a smartphone to enter the following information about a "mechanical engineer" position:

[1592] Work Experience: Mechanical Engineer

[1593] Skill set: Machine maintenance, programming

[1594] Years of experience: 5 years or more

[1595] Industry knowledge: Automation technology

[1596] Based on this, the server searches for candidates from LinkedIn and GitHub, automatically generates a list of the best candidates, and then generates and sends customized scouting emails to the selected candidates, as follows:

[1597] "Hello [candidate's name],

[1598] After looking at your profile, we believe you may be interested in our mechanical engineer position, so we are sending you a scouting email.

[1599] Please consider applying.

[1600] Application link: [Application link]

[1601] Available interview dates and times are automatically arranged by the server and notified to candidates and companies.

[1602] In this way, the system of the present invention streamlines a company's recruitment process, and enables the rapid recruitment of personnel who can immediately contribute to on-site operations in particular.

[1603] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1604] Step 1:

[1605] The user (a company's human resources officer) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. The input data is sent to the server in JSON format.

[1606] Input: Recruitment requirements (work history, skill set, years of experience, industry knowledge)

[1607] Output: Recruitment requirements data sent to the server

[1608] Step 2:

[1609] The server generates a search query based on the received job requirements data. This search query is used to send API requests to multiple data sources. Specifically, a query is generated to search for candidates that match the job requirements.

[1610] Input: Recruitment requirements data

[1611] Output: Search query

[1612] Step 3:

[1613] The server uses the generated search query to send API requests to multiple data sources, retrieving candidate information from LinkedIn, GitHub, university databases, etc.

[1614] Input: Search query

[1615] Output: Candidate information retrieved from the data source

[1616] Step 4:

[1617] The server integrates candidate information collected from multiple data sources and analyzes it based on the hiring requirements. This generates a list of optimal candidates. Specifically, the AI ​​model evaluates the candidate's work history and skill set and calculates the degree of match with the hiring requirements.

[1618] Input: Collected candidate information

[1619] Output: A list of the best candidates

[1620] Step 5:

[1621] The server generates a customized scouting email based on the best candidates list. The scouting email includes the candidate's name, company profile, details of the job position, and an explanation of the application process. The generated scouting email is automatically sent to the candidate.

[1622] Input: Best candidate list

[1623] Output: Scout email sent

[1624] Step 6:

[1625] When a candidate replies to a scouting email, the information is sent to the server, which receives the candidate's reply, checks available interview schedules, and collects the schedules of the company's interviewers.

[1626] Input: Candidate's reply

[1627] Output: Candidate and interviewer schedule data

[1628] Step 7:

[1629] The server adjusts the optimal interview date based on the schedule data of the candidate and the company's interviewers, automatically selecting a date and time that is convenient for both the candidate and the company.

[1630] Input: Candidate and interviewer schedule data

[1631] Output: Optimal interview dates

[1632] Step 8:

[1633] The server notifies both the candidate and the company's interviewer of the confirmed interview date via email or calendar notification.

[1634] Input: Best interview date

[1635] Output: Interview schedule notification

[1636] 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.

[1637] The present invention provides a system for streamlining a company's recruitment process and taking into account the emotional states of both candidates and companies. The system includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge, a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, a means for generating customized scout emails and sending them to selected candidates, and a means for automatically coordinating interview schedules between candidates and companies. The system also includes a means for combining an emotional engine to recognize emotional states and optimize the content of the scout emails and the interview schedules.

[1638] Specific Embodiments of the System

[1639] System Configuration

[1640] 1. User Device: A computer or mobile device used by a company's human resources personnel and candidates.

[1641] 2. Server: A computer system that provides AI-driven recruiting services, including an emotion engine.

[1642] 3. Data sources: Multiple platforms (LinkedIn, GitHub, Twitter, university databases, etc.).

[1643] Program processing explanation

[1644] Candidate Matching

[1645] A user (a company's human resources manager) uses a user terminal to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. through a web interface. The input information is sent to the server, which then generates a search query based on this information.

[1646] The server uses the generated query to send API requests to multiple data sources, collects and consolidates the candidate information returned from each data source, and analyzes the consolidated data based on the company's hiring requirements to generate a list of optimal candidates.

[1647] Scout email generation and emotion recognition

[1648] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state and optimize the email content based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[1649] Interview scheduling and emotion recognition

[1650] The user (an interested candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff also enters the schedule of interviewers and sends it to the server.

[1651] The server collects both parties' schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. The server automatically schedules the optimal interview date to reduce stress and discomfort. The confirmed interview date is notified to both the candidate and the company's interviewer.

[1652] Specific examples

[1653] Candidate Matching Example

[1654] A user (a company's human resources manager) uses a user terminal to input the following hiring requirements:

[1655] Work Experience: Software Engineer

[1656] Skill Set: Python, Machine Learning

[1657] Years of experience: 3 years or more

[1658] Industry Knowledge: Financial Technology

[1659] Based on this, the server searches each data source and creates a list of optimal candidates.

[1660] Example of scout email generation and emotion recognition

[1661] The server generates a customized scouting email based on the selected candidate list, like this:

[1662] Candidate's name

[1663] Company name and brief introduction

[1664] Job details

[1665] Application procedure explanation

[1666] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[1667] Example of interview schedule adjustment and emotion recognition

[1668] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[1669] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[1670] The processing flow will be explained below.

[1671] Step 1:

[1672] A user (a human resources officer of a company) accesses a web interface using a user terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge.

[1673] Step 2:

[1674] The terminal (user terminal) transmits the input recruitment requirement data to the server, which includes work history, skill set, years of experience, industry knowledge, etc.

[1675] Step 3:

[1676] The server generates search queries against multiple data sources (e.g., LinkedIn, GitHub, Twitter, university databases) based on the received hiring requirements.

[1677] Step 4:

[1678] The server then sends an API request to each data source using the generated search query, which collects candidate information from each data source.

[1679] Step 5:

[1680] The server collects and consolidates the candidate information returned from each data source, including the candidate's work history, skill set, years of experience, contact details, and more.

[1681] Step 6:

[1682] The server analyzes the collected candidate information and generates a list of candidates who best fit the company's hiring requirements, using an algorithm to evaluate each candidate's suitability.

[1683] Step 7:

[1684] The server selects a scouting email template based on the best candidates list, which includes company information and details of the job opening.

[1685] Step 8:

[1686] The server uses an emotion engine to recognize the candidate's emotional state and optimizes the content of the scouting email based on the candidate's interest and reactions. For example, if a candidate has shown positive reactions in the past, the email content will reflect those characteristics.

[1687] Step 9:

[1688] The server automatically sends customized scouting emails to candidates, each containing candidate-specific information.

[1689] Step 10:

[1690] The user (candidate) clicks on the link in the scouting email they received and accesses a web interface to enter the date and time they are available for an interview.

[1691] Step 11:

[1692] The terminal (candidate's terminal) transmits the input available interview date and time data to the server.

[1693] Step 12:

[1694] The terminal (the terminal of the company's human resources manager) inputs the interviewer's available dates and times for the interview and transmits them to the server.

[1695] Step 13:

[1696] The server collects schedule data for candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, and automatically arranges optimal interview dates to avoid stress or discomfort for either candidate or interviewer.

[1697] Step 14:

[1698] The server notifies the candidate and the company's interviewer of the confirmed interview date by email or other means, and the schedule is confirmed.

[1699] Example 2

[1700] 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."

[1701] In the traditional recruitment process, a company's human resources personnel must manage a huge amount of candidate information and spend a lot of time and effort to respond appropriately to each candidate. It is also difficult to conduct recruitment activities taking into account the emotional state of both the candidate and the company, which can lead to inappropriate interview schedules and inappropriate content in scouting emails. This can result in an inefficient recruitment process, leaving candidates and companies dissatisfied.

[1702] 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.

[1703] In this invention, the server includes: a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, and industry knowledge; a means for collecting candidate information from multiple sources and analyzing the candidates based on the recruitment requirements; a means for generating customized emails and sending them to selected candidates; a means for automatically coordinating interview schedules between candidates and companies; a means for recognizing the emotional states of candidates and companies using an emotion engine; and a means for optimizing the content of emails and interview schedules based on the emotional states. This makes it possible to automate the recruitment process and conduct smooth recruitment activities by taking into account the emotional states of both companies and candidates.

[1704] A "corporate human resources officer" is a person who is engaged in the job of selecting candidates and handling recruitment procedures within a company.

[1705] "Work history" refers to information about the job history and positions held by a candidate.

[1706] A "skill set" refers to the specific set of skills and abilities a candidate possesses.

[1707] "Years of experience" is information that indicates the number of years a candidate has worked in a particular job or industry.

[1708] "Industry knowledge" refers to the specialized knowledge a candidate has about a particular industry.

[1709] "Sources" are external databases or platforms from which data about candidates is obtained.

[1710] "Candidate Information" refers to information including data such as a candidate's work history, skill set, years of experience, and industry knowledge.

[1711] "Analysis" refers to the process of extracting, classifying, and evaluating the obtained data according to the purpose and making appropriate decisions.

[1712] "Customized email" refers to emails whose content is individually tailored based on the candidate's individual information.

[1713] An "interview schedule" is a plan that shows the dates, times, and locations of interviews between candidates and companies.

[1714] "Automatic adjustment" means that the system makes optimal adjustments without human intervention.

[1715] An "emotion engine" is technology or software that analyzes the emotional state of candidates and companies and responds based on that.

[1716] "Emotional state" refers to the psychological and emotional state of the candidate and the company, including factors such as stress, interest, and satisfaction.

[1717] "Optimization" means adjusting or improving something to be most effective or efficient for a given purpose.

[1718] A "system" is a structure in which multiple elements work together to achieve a specific purpose.

[1719] System Configuration

[1720] The present invention is a system for streamlining a company's recruitment process and taking into account the emotional state of both the candidate and the company. The system includes the following components:

[1721] User terminal

[1722] A computer or mobile device used by a company's recruiters and candidates. This includes PCs with a web browser, smartphones, tablets, etc.

[1723] server

[1724] A computer system that provides AI-driven recruiting services, including an emotion engine, and performs various data processing and analysis.

[1725] Data Source

[1726] Obtain candidate information from multiple sources (e.g., social media platforms, professional networking sites, university databases, etc.).

[1727] Program processing explanation

[1728] Candidate Matching

[1729] The user (a company's human resources officer) uses a user terminal to enter recruitment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The entered information is sent to the server, which generates a search query based on this information. The generated query is used to send an API request to multiple data sources. The candidate information returned from each data source is collected and integrated. The integrated data is analyzed based on the company's recruitment requirements, and a list of optimal candidates is generated.

[1730] Scout email generation and emotion recognition

[1731] The server selects a scouting email template for the listed candidates and generates customized scouting emails by embedding each candidate's individual information. At this time, an emotion engine is used to analyze the candidate's emotional state. The content of the email is optimized based on the candidate's level of interest and reaction. The generated scouting emails are automatically sent to each candidate.

[1732] Interview scheduling and emotion recognition

[1733] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is then sent to the server. The company's human resources staff similarly enters the interviewer's schedule and sends it to the server. The server collects this schedule data and uses an emotion engine to evaluate the emotional state of the candidate and interviewer. It then automatically arranges the optimal interview date to reduce stress and discomfort. The confirmed interview date is then notified to both the candidate and the company's interviewer.

[1734] Specific examples

[1735] Candidate Matching Example

[1736] The user (a company's human resources officer) uses a user terminal to input the following hiring requirements:

[1737] Work Experience: Software Engineer

[1738] Skill Set: Python, Machine Learning

[1739] Years of experience: 3 years or more

[1740] Industry Knowledge: Financial Technology

[1741] Based on this, the server searches each data source and creates a list of the best candidates.

[1742] Example of scout email generation and emotion recognition

[1743] The server generates a customized scouting email based on the selected candidate list, like this:

[1744] Candidate's name

[1745] Company name and brief introduction

[1746] Job details

[1747] Application procedure explanation

[1748] The server uses an emotion engine to evaluate the candidate's interest and reaction, and optimizes the email content accordingly. The server then sends the generated scouting email to the candidate.

[1749] Example of interview schedule adjustment and emotion recognition

[1750] The user (candidate) clicks on the link in the scout email and enters the date and time they are available for an interview. The server also collects the schedules of the company's interviewers and determines the optimal interview date using an emotion engine. The confirmed interview date is notified to both parties.

[1751] The present invention can be implemented by using a generative AI model to create example prompts as follows:

[1752] "Find a Software Engineer candidate with the following skill set: Python, Machine Learning, 3+ years of experience, Financial Technology industry"

[1753] "Generate the best scouting email from this list of candidates."

[1754] Please use the schedule below to schedule your interview.

[1755] In this way, the present invention can fully automate and streamline a company's recruitment process, and by using an emotion engine, it can improve the smoothness of recruitment and the satisfaction of both candidates and companies.

[1756] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1757] Step 1:

[1758] The user uses a terminal to input employment requirements such as work history, skill set, years of experience, and industry knowledge through a web interface. The input information is sent to the server. The input is the company's employment requirements, and the output is the employment requirements data saved on the server. The user's specific actions are to type the required information into the input form and click the "Submit" button.

[1759] Step 2:

[1760] The server generates a search query based on the job requirements received from the user. Here, it receives the job requirements data as input data and generates a search query as output. The specific operation of the server is to analyze the job requirements data and build a query string based on it.

[1761] Step 3:

[1762] The server uses the generated search query to send API requests to multiple data sources. The input is the search query, and the output is the candidate information collected from each data source. Specifically, the server sends an HTTP request to an API endpoint and receives the candidate information as a response.

[1763] Step 4:

[1764] The server consolidates the collected candidate information. The input is candidate information obtained from multiple data sources, and the output is consolidated candidate data. Specifically, it standardizes data in different formats and consolidates them into a single database.

[1765] Step 5:

[1766] The server analyzes the integrated candidate data based on the company's hiring requirements and generates a list of optimal candidates. The input is the integrated candidate data and hiring requirements data, and the output is a list of optimal candidates. The specific operation of the server is to analyze the data using machine learning algorithms and filtering technology.

[1767] Step 6:

[1768] The server selects a scout email template based on the list of optimal candidates and generates customized scout emails by embedding individual information for each candidate. The input is the list of optimal candidates and the scout email template, and the output is a customized scout email. Specifically, the server runs a template engine to embed individual information into the template.

[1769] Step 7:

[1770] The server uses an emotion engine to analyze the emotional state of each candidate. The input is the candidate's past activity data and reaction data, and the output is emotional state data. Specifically, the server uses an emotion analysis algorithm to evaluate the emotional state from the data.

[1771] Step 8:

[1772] The server optimizes the content of the scout email based on the emotional state data. The input is a customized scout email and the emotional state data, and the output is an optimized scout email. Specifically, the server corrects and edits the email content.

[1773] Step 9:

[1774] The server automatically sends optimized scout emails to each candidate. The input is the optimized scout email, and the output is a notification of completion of sending. The specific operation is to send the email through the mail server.

[1775] Step 10:

[1776] The user (candidate) clicks on the link in the scout email they received and enters their available interview schedule. This schedule is sent to the server. The input is the candidate's schedule information, and the output is the schedule information saved on the server. Specifically, the schedule information is entered into a web form and sent.

[1777] Step 11:

[1778] Similarly, the user (a company's human resources officer) also enters the interviewer's schedule and sends it to the server. The input is the company's interviewer's schedule information, and the output is the schedule information saved on the server. Specifically, the human resources officer enters information into a web form and submits it.

[1779] Step 12:

[1780] The server collects both parties' schedule data and automatically arranges the optimal interview schedule using an emotion engine. The input is the candidate's and interviewer's schedule information and emotional state data, and the output is the optimal interview schedule. The specific operation of the server is to analyze the schedule data and calculate the optimal schedule.

[1781] Step 13:

[1782] The server notifies both the candidate and the company's interviewer of the confirmed interview date. The input is the optimal interview date, and the output is a notification message. Specifically, the server sends the notification via email or a messaging system.

[1783] Through the above steps, the present invention fully automates and streamlines a company's recruitment process, realizing smooth recruitment activities that take into account the emotional states of both candidates and companies.

[1784] (Application example 2)

[1785] 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."

[1786] In the recruitment process, companies are required to efficiently find suitable candidates who meet requirements such as work history, skill set, years of experience, and industry knowledge. In delivery operations, it is also important to consider the emotional state of delivery personnel and customers to improve service quality. Conventional methods have difficulty simultaneously optimizing recruitment and delivery schedules, and this issue needs to be addressed.

[1787] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1788] In this invention, the server includes a means for a company's human resources personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc., a means for collecting candidate information from multiple data sources and analyzing the candidates based on the recruitment requirements, and a means for generating customized scouting emails and sending them to selected candidates. This makes it possible to streamline the recruitment process and further evaluate the emotional states of delivery personnel and customers in delivery work and optimize delivery schedules.

[1789] "Work history" refers to a candidate's professional history and work experience.

[1790] A "skill set" refers to the collection of skills, knowledge, and abilities required for a specific job or function.

[1791] "Years of experience" refers to the length of time a candidate has actually worked in a particular occupation or industry.

[1792] "Industry knowledge" refers to specialized knowledge and information about a particular industry.

[1793] "Data Sources" are sources for collecting candidate information, including, for example, professional networking sites and university databases.

[1794] "Candidate analysis" refers to the process of evaluating and comparing the suitability and capabilities of candidates based on the recruitment requirements entered.

[1795] A "scouting email" refers to a job information email customized for a specific candidate.

[1796] "Interview scheduling" refers to the process of coordinating the schedules of the candidate and the company's interviewer and determining the optimal interview date and time.

[1797] "Delivery services" refers to the delivery of goods and services to customers.

[1798] "Delivery Person" refers to a worker who is responsible for delivering goods to customers.

[1799] "Customer" means any person or entity that receives goods or services.

[1800] "Emotional state" refers to the current emotional or mental state of an individual or group.

[1801] "Schedule optimization" refers to the process of arranging various schedules in the most efficient way, making the most of time and effort.

[1802] This invention is a system for optimizing a company's recruitment process and delivery operations. The system's main components are a server, a user terminal, multiple data sources, and an emotion engine. The specific operation of each component and the overall system configuration are described below.

[1803] System Configuration

[1804] User terminal

[1805] User terminals are devices such as computers and smartphones used by human resources personnel and candidates. They can input recruitment requirements and arrange interview schedules via the user terminals.

[1806] server

[1807] The server is a computer system that provides the core AI-driven recruiting service and delivery operation management. It includes multiple modules, such as an emotion engine, a data analysis engine, and a schedule optimization engine. This server is composed of Python programs that collect information from data sources, analyze it, recognize emotions, and send notifications.

[1808] Data Source

[1809] Data sources are the multiple sources used to gather candidate information, such as professional networking sites, project management tools, email data, and university databases.

[1810] Program processing

[1811] Data Collection and Query Generation

[1812] The server receives recruitment requirements such as work history, skill set, years of experience, and industry knowledge from a user's device. Based on this information, the server generates a search query and sends API requests to multiple data sources. The server then integrates the candidate information obtained and creates a list of optimal candidates that match the recruitment requirements.

[1813] sentiment analysis

[1814] The server uses an emotion engine such as the TextBlob library to analyze the emotional states of the scout email, delivery personnel, and customers. Based on the analysis results, the server optimizes the content of the scout email and the delivery schedule.

[1815] Generate scout emails

[1816] The server generates a customized scouting email based on the candidate list. The scouting email includes the candidate's name, company name, details of the job position, and an explanation of the application process. Based on the evaluation by the emotion engine, the content is optimized based on the candidate's interest and suitability.

[1817] Arranging interview schedules

[1818] The server collects interview schedules provided by candidates and company interviewers, and uses an emotion engine to automatically determine the optimal interview dates that minimize stress and discomfort.

[1819] Optimizing delivery schedules

[1820] The emotion engine analyzes the emotional state of delivery personnel and customers and automatically adjusts optimal delivery schedules to reduce stress and fatigue, thereby improving service quality and maximizing labor efficiency.

[1821] Specific examples

[1822] Specific examples of candidate matching

[1823] For example, a company's HR representative enters the following hiring requirements:

[1824] Work Experience: Software Engineer

[1825] Skill Set: Python, Machine Learning

[1826] Years of experience: 3 years or more

[1827] Industry Knowledge: Financial Technology

[1828] Based on this, the server searches each data source and creates a list of the most suitable candidates.

[1829] Example of scout email generation

[1830] Generate a customized scout email like this:

[1831] Candidate's name

[1832] Company name and brief introduction

[1833] Job details

[1834] Application procedure explanation

[1835] It uses an emotion engine to assess candidate interest and reactions and optimize email content accordingly.

[1836] Specific examples of interview schedule adjustments

[1837] For example, a candidate inputs the date and time they are available for an interview, and the server collects the schedules of the company's interviewers. The server then automatically determines the optimal interview date using an emotion engine and notifies both parties.

[1838] Prompt Sentence Examples

[1839] "Job Requirements: Hiring delivery drivers with at least one year of delivery experience. Skill Set: Customer service, lifesaving. Years of Experience: At least one year. Industry Knowledge: Food delivery."

[1840] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1841] Step 1:

[1842] A company's human resources staff inputs hiring requirements such as work history, skill set, years of experience, and industry knowledge into the user terminal. The user terminal then sends the hiring requirements data to the server. Once the input hiring requirements data reaches the server, the next processing step begins.

[1843] Step 2:

[1844] The server generates a search query based on the job requirements data received in the previous step. The server uses Python to generate this query and then sends API requests to multiple data sources (e.g., career networking sites, university databases, etc.) to gather candidate information.

[1845] Step 3:

[1846] The server consolidates the collected candidate information and analyzes the candidates based on the hiring requirements. This analysis process uses statistical analysis and machine learning models to select the most suitable candidates. The analysis results in a list of the best candidates, which is then passed on to the next processing step.

[1847] Step 4:

[1848] The server creates a customized scouting email for each candidate based on the generated candidate list. It uses an emotion engine (e.g., TextBlob library) to analyze the candidate's emotional state and optimize the email content based on the candidate's interest level. The optimized scouting email is then automatically sent to the candidate.

[1849] Step 5:

[1850] If a candidate receives a scouting email and is interested, they click the link in the email and enter the date and time they are available for an interview. This input data is sent from the user's terminal to the server.

[1851] Step 6:

[1852] The server collects interview schedules provided by candidates and company interviewers, evaluates the emotional state of both parties using an emotion engine, determines the optimal interview date to minimize stress and discomfort, and notifies both parties.

[1853] Step 7:

[1854] The server analyzes the emotional state of the delivery person and the customer during food delivery work. The emotion engine evaluates the delivery person using information entered by the delivery person and feedback data from the customer. Based on the evaluation results, the delivery schedule is optimized and the optimal delivery route and time slot are automatically adjusted to reduce stress.

[1855] Step 8:

[1856] The server notifies the delivery staff and customers of the optimized delivery schedule. Notifications are sent via smartphone application and email. The delivery staff delivers based on the optimized schedule and route, improving customer satisfaction.

[1857] 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.

[1858] 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.

[1859] 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 robot 414.

[1860] 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.

[1861] FIG. 9 illustrates 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 behaviors 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.

[1862] 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.

[1863] 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).

[1864] 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.

[1865] 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."

[1866] 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.

[1867] 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).

[1868] 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.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] 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.

[1873] 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.

[1874] 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.

[1875] 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.

[1876] 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.

[1877] 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.

[1878] The following is further disclosed regarding the above embodiment.

[1879] (Claim 1)

[1880] A way for company HR personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc.

[1881] means for collecting candidate information from a plurality of data sources and analyzing the candidates based on said recruitment requirements;

[1882] A means for generating and sending customized scouting emails to selected candidates;

[1883] A way to automatically schedule interviews between candidates and companies,

[1884] A system including:

[1885] (Claim 2)

[1886] 10. The system of claim 1, further comprising means for receiving a candidate's response to the customized scouting email.

[1887] (Claim 3)

[1888] 2. The system according to claim 1, further comprising means for integrating interview schedules provided by a company's human resources personnel and the candidate to determine an optimal interview date.

[1889] "Example 1"

[1890] (Claim 1)

[1891] A way for company HR personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc.

[1892] means for collecting candidate information from a plurality of data sources and analyzing the candidates based on said recruitment requirements;

[1893] A means for generating and sending customized scouting emails to selected candidates;

[1894] A way to automatically schedule interviews between candidates and companies,

[1895] A method to automatically arrange the best interview date by comparing the candidate's and company's interview schedules, and

[1896] A system including:

[1897] (Claim 2)

[1898] 10. The system of claim 1, further comprising means for receiving a candidate's response to the customized scouting email.

[1899] (Claim 3)

[1900] 2. The system according to claim 1, further comprising means for integrating interview schedules provided by a company's human resources personnel and the candidate to determine an optimal interview date.

[1901] "Application Example 1"

[1902] (Claim 1)

[1903] A way for company HR personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc.

[1904] means for collecting candidate information from a plurality of data sources and analyzing the candidates based on said recruitment requirements;

[1905] A means for generating and sending customized scouting emails to selected candidates;

[1906] A way to automatically schedule interviews between candidates and companies,

[1907] A means for robots to be used in factories to assist in the recruitment process;

[1908] A system including:

[1909] (Claim 2)

[1910] 10. The system of claim 1, further comprising means for receiving a candidate's response to the customized scouting email.

[1911] (Claim 3)

[1912] 2. The system according to claim 1, further comprising means for integrating interview schedules provided by a company's human resources personnel and the candidate to determine an optimal interview date.

[1913] "Example 2: Combining Emotion Engines"

[1914] (Claim 1)

[1915] A way for company HR personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc.

[1916] means for collecting candidate information from multiple sources and analyzing the candidates based on the recruitment requirements;

[1917] a means for generating and sending customized emails to selected candidates;

[1918] A way to automatically schedule interviews between candidates and companies,

[1919] a means for recognizing the emotional state of the candidate and the company using an emotion engine;

[1920] means for optimizing email content and interview schedules based on said emotional state;

[1921] A system including:

[1922] (Claim 2)

[1923] 10. The system of claim 1, further comprising means for receiving the candidate's response to the customized email.

[1924] (Claim 3)

[1925] 2. The system according to claim 1, further comprising means for integrating interview schedules provided by a company's human resources personnel and the candidate to determine an optimal interview date.

[1926] "Application example 2 when combining emotion engines"

[1927] (Claim 1)

[1928] A way for company HR personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc.

[1929] means for collecting candidate information from a plurality of data sources and analyzing the candidates based on said recruitment requirements;

[1930] A means for generating and sending customized scouting emails to selected candidates;

[1931] A way to automatically schedule interviews between candidates and companies,

[1932] A means for evaluating the emotional states of delivery personnel and customers during delivery operations and optimizing delivery schedules;

[1933] A system including:

[1934] (Claim 2)

[1935] 10. The system of claim 1, further comprising means for analyzing an emotional state of a selected candidate and optimizing the content of the scouting email based thereon.

[1936] (Claim 3)

[1937] 2. The system according to claim 1, further comprising means for integrating interview schedules provided by a company's human resources personnel and the candidate to determine an optimal interview date.

[1938] (Claim 4)

[1939] The system according to claim 1, further comprising means for analyzing the emotional states of delivery personnel and customers and automatically adjusting optimal delivery personnel allocation and delivery schedules. [Explanation of symbols]

[1940] 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 way for company HR personnel to input recruitment requirements such as work history, skill set, years of experience, industry knowledge, etc. means for collecting candidate information from a plurality of data sources and analyzing the candidates based on said recruitment requirements; A means for generating and sending customized scouting emails to selected candidates; A way to automatically schedule interviews between candidates and companies, A system including:

2. 10. The system of claim 1, further comprising means for receiving a candidate's reply to the customized scouting mail.

3. 2. The system according to claim 1, further comprising means for integrating interview schedules provided by a company's human resources personnel and the candidate to determine an optimal interview date.

Images