system

Abstract

We provide the system. [Solution] A means of collecting and standardizing job posting data and job seeker data, A means for analyzing the aforementioned job information data and job seeker data and calculating a match score, A means for generating a list of scout targets based on the aforementioned match score, A means for automatically generating a scouting email message corresponding to the aforementioned list of potential scouts, The means for sending the aforementioned scout email, A means for aggregating and analyzing responses to the aforementioned scout emails, A system that includes this.

Description

Technical Field

[0005]

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] The problem of manpower shortage in the medical and welfare fields is serious, and it is required to quickly and efficiently secure appropriate human resources. The current recruitment process involves a lot of manual work, wasting time and labor, resulting in delays in recruitment activities and many cases of failure to acquire the required human resources. For this reason, there is a need for a technology that enables companies to efficiently scout for human resources and optimize recruitment activities.

Means for Solving the Problems

[0005] This invention provides a system that includes means for collecting and standardizing job information data and job seeker data, and further means for analyzing this data to calculate a match score. By providing a system that automatically generates a list of candidates to scout based on the calculated match score and automatically creates personalized scout email text, the system automates everything from sending scout emails to aggregating and analyzing responses. As a result, companies can efficiently and quickly scout suitable personnel and effectively address labor shortages.

[0006] "Job posting data" refers to data that includes detailed information about job openings, such as the type of job a company is recruiting, job description, work location, and salary conditions.

[0007] "Job seeker data" refers to data that contains information about individual job seekers, such as their resume information, work history, skill set, and desired conditions.

[0008] "Standardization" is the process of organizing collected data into a unified format, making it easier to analyze and process.

[0009] "Analysis" is the act of classifying, evaluating, or interpreting information within data to extract useful insights or patterns for a specific purpose.

[0010] The "match score" is a numerical representation of the degree to which job posting data and job seeker data match, and is an indicator used to evaluate suitability.

[0011] The "Scout Candidate List" is a list of job seekers selected based on their match score, indicating they may potentially meet the company's requirements.

[0012] A "scout email" refers to the content of an email sent by a company to a job seeker, and includes personalized messages designed to encourage the job seeker to take an interest in the company's job openings.

[0013] "Automation" is the process of performing tasks using machines or computer programs instead of manual labor, with the aim of improving efficiency and accuracy.

[0014] "Response aggregation and analysis" refers to the process of organizing recipient response data to recruitment emails, evaluating their content, and classifying it. [Brief explanation of the drawing]

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

Modes for Carrying Out the Invention

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

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

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

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

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

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

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

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

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

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

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

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0036] This invention relates to an automated system that improves efficiency and speed in the recruitment process for personnel in the medical and welfare fields. The system is designed to allow companies to easily scout suitable personnel and is primarily operated using servers and terminals.

[0037] First, the server collects job postings and job seeker data from various data sources and standardizes them into an analyzable format. Next, the server uses natural language processing technology to analyze the job postings and job seeker profiles and calculates a match score to evaluate the suitability of both parties.

[0038] Based on this match score, the server generates a list of candidates to scout. Based on this list, the terminal automatically generates a recruitment email. The generated email includes a customized message tailored to each job seeker's background and experience, designed to maximize the effectiveness of the approach.

[0039] The recruiters at the companies using the service can review these automatically generated emails on their devices and edit them as needed. After final confirmation, the server sends the recruitment emails to the target candidates.

[0040] Furthermore, the server automatically aggregates and analyzes responses to sent emails. Users can view the response results in real time through their terminals and quickly take the next steps based on that information, such as scheduling an interview.

[0041] This system allows for the rapid and accurate connection of companies and job seekers while significantly reducing time and effort. For example, if a hospital in need of nurses uses this system, recruitment emails will be automatically sent to suitable nurse candidates, enabling efficient recruitment activities.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects job postings and job seeker data from external data sources and databases. This is done automatically via APIs, and the information includes job descriptions, required skills, experience, and work location.

[0045] Step 2:

[0046] The server standardizes the collected data into a unified format. This includes data cleaning and normalization. By preparing data from different sources to be comparable, the accuracy of the analysis can be improved.

[0047] Step 3:

[0048] The server analyzes standardized data using natural language processing techniques. This analysis calculates a match score to evaluate the degree of compatibility between each job seeker's profile and the job posting. This score is calculated based on the degree of match in skills, experience, and qualifications.

[0049] Step 4:

[0050] The server generates a list of potential candidates based on the calculated match score. The list prioritizes candidates who best match the company's requirements.

[0051] Step 5:

[0052] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails follow a template and are customized to be personalized according to the candidate's name and background information.

[0053] Step 6:

[0054] The user, who is the recruiter, can review the content of the recruitment email via their device. They can add or revise the content as needed and then give final approval.

[0055] Step 7:

[0056] The server, upon user approval, sends recruitment emails to the target recipients. The sending date, time, and frequency are optimized using a scheduling function.

[0057] Step 8:

[0058] The server automatically aggregates and analyzes responses to sent recruitment emails. Based on the content of the received responses, they are classified into categories such as "thank you," "not interested," and "request for additional information."

[0059] Step 9:

[0060] Users can view the aggregated response results through their terminals and quickly decide on their next action, such as scheduling a meeting appointment. Furthermore, the server continuously learns and improves the accuracy of its algorithms based on user feedback.

[0061] (Example 1)

[0062] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0063] In the modern medical and welfare fields, the recruitment process is often time-consuming and laborious. Companies are required to quickly find suitable personnel and contact them efficiently, but matching job openings with job seekers requires a tremendous amount of time and effort. Furthermore, personalizing email content and effectively delivering it to candidates to achieve a higher response rate is a challenge for companies. Therefore, the present invention aims to solve these problems and provide a system that enables appropriate and rapid talent scouting.

[0064] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0065] In this invention, the server includes means for storing job information data and job seeker data in a database, means for analyzing the job information data and job seeker data using natural language processing technology to calculate a match score, and means for adding candidates whose scores exceed a threshold to a list of candidates to be scouted. This enables accurate and efficient analysis of job information and job seeker data, and rapid scouting of suitable candidates. Furthermore, by including means for automatically generating scout email text using a generative AI model, and allowing users to review and edit this content, it becomes possible to realize personalized and effective recruiting communication.

[0066] "Job posting data" refers to data containing detailed information about job openings, including the required personnel conditions, job descriptions, and application requirements of companies.

[0067] "Job seeker data" refers to data containing information about individuals seeking employment, including their work history, skills, qualifications, and desired occupation.

[0068] A "database" is a collection of information that stores data in a structured format, allowing for efficient searching and management.

[0069] "Natural language processing technology" refers to technologies used to analyze, understand, and generate human language using computers, and is used for tasks such as text analysis and keyword extraction.

[0070] The "match score" is an index that quantifies the compatibility between job posting data and job seeker data, and is used to evaluate how well a job seeker matches the job requirements.

[0071] The "Scout Candidate List" is a list of candidates who have been selected based on their match score and are eligible to be scouted.

[0072] A "generative AI model" is a model that uses artificial intelligence and has the ability to generate text or data for a specific purpose.

[0073] A "prompt statement" is an instruction statement used to guide the operation of a generative AI model, and it plays a role in influencing the generated results.

[0074] This invention realizes an automated system that streamlines the recruitment process in the medical and welfare fields. The main components of the system include servers, terminals, and users who utilize them.

[0075] The server collects job postings and job seeker data using web scraping techniques and stores them in a database management system (e.g., PostgreSQL). This provides advanced accessibility and data management capabilities. The server standardizes the data using the Python pandas library, handling missing values ​​and adjusting data types. Using natural language processing techniques, the server analyzes this data and utilizes the NLTK or spaCy library to calculate a match score.

[0076] The terminal automatically generates recruitment emails using a generation AI model (e.g., OpenAI® GPT) based on the list of potential recruits received from the server. An example of a prompt used in this process is the instruction, "Create a recruitment email template to send to new nursing candidates. The email should highlight the candidate's experience in the nursing field and appeal to opportunities for growth at the hospital."

[0077] Users can review and edit automatically generated recruitment emails via their devices. This allows for a personalized approach tailored to each job seeker. After a final check, the server sends the finalized recruitment email using the SMTP protocol.

[0078] Furthermore, the server aggregates responses to sent emails in real time and provides the analysis results to the user. This system supports recruiters in quickly scheduling interviews and conducting follow-up activities. Thus, the invention aims to expedite the recruitment process and efficiently connect companies with job seekers.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects job postings and job seeker data from various job sites using web scraping techniques. It automatically crawls sites according to a specific schedule and extracts necessary information from HTML pages using BeautifulSoup. The input consists of multiple web pages, and the output is unstructured text data. This text data is in a preparatory stage before standardization.

[0082] Step 2:

[0083] The server converts the collected text data into a structured data format. It uses the Python pandas library to create a dataset, ensuring missing value imputation and data type consistency. The input is unstructured text data, and the output is in a format suitable for storage in a database. PostgreSQL is used as the storage destination.

[0084] Step 3:

[0085] The server analyzes stored job postings and job seeker data using natural language processing techniques. Using NLTK or spaCy, it extracts keywords and important phrases from the data and calculates a match score. This calculation uses an algorithm that evaluates text similarity. The input is structured data, and the output is the match score for each job seeker.

[0086] Step 4:

[0087] The server adds job seekers who exceed a certain threshold based on the calculated match score to a list of potential recruits. A decision tree algorithm is used to select candidates with high suitability based on the score. The input is the match score, and the output is a list of potential recruits.

[0088] Step 5:

[0089] The terminal automatically generates recruitment emails using an AI model based on a list of potential candidates. During this process, prompts such as "Generate a personalized message based on the job seeker's background" are provided. The input is a list of potential candidates, and the output is a customized recruitment email.

[0090] Step 6:

[0091] Users can review automatically generated recruitment emails via their devices and edit them as needed. They can modify content and adjust their approach using a browser-based editing interface. The input is the automatically generated email text, and the output is the final, reviewed email text.

[0092] Step 7:

[0093] The server sends the confirmed recruitment emails to each job seeker via the SMTP protocol. The input is the confirmed email text, and the output is the sent email. During this process, the email sending history is also recorded in the database.

[0094] Step 8:

[0095] The server aggregates and analyzes responses to sent emails in real time. It uses the pandas library to perform response rate and behavioral analysis, and saves the results to a database. The input is the received reply data, and the output is the analyzed response data.

[0096] Step 9:

[0097] Users review the analysis results via their device and proceed to the next recruitment step. For example, they might plan to quickly schedule interviews or initiate further communication. The input is the analyzed response data, and the output is the determined recruitment strategy.

[0098] (Application Example 1)

[0099] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0100] The recruitment process in the security field is complex and time-consuming, making it difficult to secure suitable personnel. In particular, recruiting personnel for nighttime or specialized work requires rapid and effective matching. This invention solves these problems, streamlining the recruitment process for security personnel and providing a means to quickly secure talent.

[0101] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0102] In this invention, the server includes means for collecting and standardizing employment information data and applicant information data, means for calculating suitability scores, and means for automatically generating message text according to the list of candidates to be selected. This makes it possible to support the recruitment process for personnel in the security field and to quickly secure suitable personnel.

[0103] "Employment information data" refers to information about job postings provided by companies and organizations, including details such as job title, job description, work location, working hours, and salary conditions.

[0104] "Applicant information data" refers to personal information about job seekers, as well as data such as work history, skills, and qualifications, which is used to determine their suitability for employment.

[0105] "Standardization" is the process of converting data with different forms and structures into a unified format, in order to facilitate analysis.

[0106] A "suitability score" is an index that quantifies the degree of compatibility between job postings and applicant information, and is used to evaluate the likelihood of hiring.

[0107] A "selection list" is a list compiled by a company based on suitability scores, listing candidates that it should consider scouting or interviewing.

[0108] "Automatically generating message text" means that the system automatically generates messages for individual applicants based on pre-configured templates, enabling efficient communication.

[0109] The "recruitment process for security personnel" refers to the entire process from searching for, selecting, and hiring individuals to engage in security work.

[0110] "Applications that can be installed on various devices" are software programs that can be downloaded and used on digital devices such as smartphones and tablets.

[0111] The system implementing this invention is a software program for companies to quickly and accurately select applicants in the security field and streamline the recruitment process. This program consists of a server and terminals, and a specific embodiment thereof is shown below.

[0112] The server first collects employment and applicant information data through the use of external databases and APIs. The collected data is then converted into an analyzable format through standardization. This standardization process includes filtering and format conversion to ensure data consistency.

[0113] Next, the server uses natural language processing technology to analyze employment information data and applicant information data. During this analysis, a suitability score is calculated, and a list of candidates for selection is generated based on this score. This list is optimized by the server's algorithm, enabling efficient talent selection.

[0114] Next, based on the list of selected candidates, the device automatically generates a message. In this process, individual information for each applicant is inserted into a template, creating a customized message. The generated message is then sent to the applicant via the application on the device.

[0115] The hardware used to run this system will be cloud servers (e.g., Amazon Web Services or Google Cloud Platform), which will handle the necessary computing and data storage. For software, Python libraries (e.g., NLTK and SpaCy) can be used for data analysis, and Flask or Django can be used as the UI platform.

[0116] As a concrete example, consider a company that needs personnel to handle nighttime security. This system collects relevant applicant information and automatically generates and sends messages to candidates who meet the hiring requirements. As a result, rapid and effective recruitment becomes possible.

[0117] Examples of prompts for the generating AI model include: "Calculate a suitability score for applicants suitable for the night security guard position based on the following requirements, and generate a customized email: flexibility in working hours, past security experience, and special skills."

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server collects employment and applicant information data from external databases and APIs. The input consists of raw data from multiple data sources. The server then performs data cleansing to convert this data into a consistent format and standardize it. This results in output data in a parseable format.

[0121] Step 2:

[0122] The server analyzes standardized employment and applicant data using natural language processing techniques. The input is standardized text data, and analysis is performed using a natural language processing library (e.g., SpaCy). This process quantifies the characteristics of job postings and applicant profiles and outputs a suitability score.

[0123] Step 3:

[0124] The server generates a list of candidates based on the calculated suitability score. The input is the suitability score, and the server's algorithm evaluates the score and lists candidates in descending order of suitability. As a result, a list of candidates to be scouted is output.

[0125] Step 4:

[0126] The terminal automatically generates message text based on the list of selected individuals. The input consists of the list of selected individuals and a template message. Personalized information is inserted into the template to output a customized message. Users can edit and review this message.

[0127] Step 5:

[0128] The server sends the generated message to the applicant. The generated message is used as input, and the transmission operation is performed using the SMTP protocol. As a result of the transmission, a transmission status is output, which may indicate a response has been received.

[0129] Step 6:

[0130] The server aggregates and analyzes responses from applicants. Using the received responses as input, an analysis algorithm evaluates their content and outputs recommendations for the next step (e.g., scheduling an interview). Users can then use the aggregated results to make quick hiring decisions.

[0131] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0132] This invention combines an emotion engine with an automated system that enables efficient scouting activities in the recruitment process for the medical and welfare sectors. The system aims to provide a deeper understanding of the interaction between companies and job seekers and to offer a personalized approach.

[0133] The system operates on a server-terminal basis. First, the server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. Next, the server analyzes the data using natural language processing technology and calculates a match score. Based on this score, it generates a list of optimal candidates for recruitment.

[0134] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails include personalized information based on the candidate's name and background, facilitating more effective communication. Users, i.e., company recruiters, can review the emails via the device, make any necessary revisions, and then give final approval.

[0135] The server automatically sends approved emails according to a specified schedule. Furthermore, it uses an emotion engine to analyze recipient email responses in real time. The server leverages natural language processing and machine learning algorithms to identify the emotions expressed in the responses. Based on these results, users can then select the next steps, such as customized follow-up emails or interview approaches.

[0136] For example, if a hospital wants to hire nurses, this system can be used to automatically send recruitment emails to nurse candidates whose qualifications and experience meet the requirements. If the emotion engine identifies the response as positive, the system can quickly take more effective steps, such as proactively scheduling an interview. In this way, companies can conduct recruitment activities efficiently and precisely.

[0137] The following describes the processing flow.

[0138] Step 1:

[0139] The server automatically collects job postings and job seeker data from external databases. The data includes detailed information such as job title, skills, location, and salary.

[0140] Step 2:

[0141] The server standardizes the collected data into a unified format. Irrelevant information is removed, and the format is standardized to prepare the data for analysis.

[0142] Step 3:

[0143] The server analyzes standardized data using natural language processing techniques. This analysis compares job requirements with the skills and experience of job seekers to calculate a match score. This score is used to evaluate which job seeker is the best fit for the job posting.

[0144] Step 4:

[0145] The server generates a list of potential candidates based on the calculated match score. This list prioritizes candidates who best match the company's requirements.

[0146] Step 5:

[0147] The device uses AI to automatically generate recruitment emails based on a list of potential candidates. The emails are customized to match the job seeker's name and past experience.

[0148] Step 6:

[0149] The user reviews the generated recruitment email text via their device and edits it as needed. After final confirmation, the user approves sending the email.

[0150] Step 7:

[0151] The server sends recruitment emails to target individuals after receiving user approval. Sending is done according to an optimized schedule.

[0152] Step 8:

[0153] The server uses an emotion engine to analyze responses to recruitment emails. It uses natural language processing and machine learning to determine the user's emotions from the received responses. This analysis identifies whether the response is positive or negative.

[0154] Step 9:

[0155] Users can view the analysis results from the emotion engine via their device and decide on their next action based on the response. For example, if they receive a positive response, they can quickly take appropriate action, such as scheduling a meeting.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0158] A smooth matching process between job postings and job seekers is a crucial element in efficient recruitment. However, for companies, finding the right candidates with the required qualifications and experience from a large amount of data remains a time-consuming and resource-intensive task. Furthermore, personalizing recruitment emails for effective communication is also challenging. To address these challenges, there is a need for a system that automates the recruitment process and provides follow-up strategies through sentiment analysis.

[0159] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0160] In this invention, the server includes means for collecting job information data and job seeker data and converting them into a unified format; means for analyzing the job information data and job seeker data and calculating a suitability score; and means for generating a candidate list based on the suitability score. This makes it possible to quickly and accurately identify suitable personnel from a large amount of information and to efficiently personalize subsequent communication.

[0161] "Job posting data" refers to data provided by employers that includes details about the job, required skills, experience, salary range, and other relevant information.

[0162] "Job seeker data" refers to data that represents information provided by job seekers, including their personal work history, skills, qualifications, and desired conditions.

[0163] A "unified format" refers to a state where data acquired in different formats is converted into a consistent format, making comparison and analysis easier.

[0164] A "fit score" is an evaluation index that quantifies the compatibility between job postings and job seekers based on their information.

[0165] A "candidate list" refers to a set of job seekers selected based on their suitability score who best match a specific job opening.

[0166] "Communication text" refers to the content of emails or messages sent for the purpose of communicating with job seekers.

[0167] "Personalized information" refers to content that includes details based on an individual's name and professional background, tailored to a specific recipient.

[0168] "Identifying emotions" means analyzing the emotional tone of a recipient's response and classifying it into categories such as positive, negative, or neutral.

[0169] "Language analysis technology" refers to techniques that use natural language processing and machine learning to analyze text data and understand its meaning and intent.

[0170] The system of the present invention operates on a server and terminal basis and aims to streamline the personnel recruitment process in the medical and welfare fields. The following describes embodiments of this system.

[0171] Data collection and standardization:

[0172] The server first collects job postings and job seeker data from external data sources. This includes various job portals and company databases. Since the collected data may be in different formats, the server converts the data into a unified format. In this process, database languages ​​are used to organize the data and create a consistent dataset.

[0173] Data analysis and scoring:

[0174] Next, the server uses language analysis technology to analyze job seekers and job postings. This analysis utilizes natural language processing technology and machine learning algorithms. Specifically, it extracts the skills and qualifications of job seekers and quantifies how well they match the job requirements as a relevance score.

[0175] Generating a candidate list:

[0176] Based on the suitability score, the server generates a list of candidates. This list is stored in a format that can be accessed later by the company's recruiters.

[0177] Creating and sending recruitment emails:

[0178] The terminal automatically creates a message based on the generated candidate list. Here, it uses individualized information to adopt a communication style tailored to the recipient job seeker. This email is sent automatically according to a schedule.

[0179] Response collection and sentiment analysis:

[0180] When a reply is received, the server analyzes its content in real time. Software for identifying emotions analyzes the recipient's response tone to determine whether it is positive or negative. This provides information to decide on further follow-up and strategic actions.

[0181] As a concrete example, consider a scenario where a hospital is trying to recruit nurses. Using this system, nurses with the necessary qualifications and experience can be automatically listed, and personalized recruitment emails can be sent quickly. If a positive response is detected, interviews can be scheduled promptly, allowing for more effective recruitment activities.

[0182] An example of a prompt might be: "Generate a list of job seekers with nursing qualifications and experience, prepare and send recruitment emails, analyze the email responses, and suggest the next steps."

[0183] This system is a powerful tool for companies to deepen their interaction with job seekers and develop effective recruitment strategies.

[0184] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0185] Step 1:

[0186] The server collects job postings and job seeker data from external data sources. Its inputs include raw data obtained from job portals and company databases. The server processes this data into a consistent format and outputs a unified dataset. During this process, it uses a database language to standardize different categories and make them comparable.

[0187] Step 2:

[0188] The server analyzes a unified dataset using natural language processing techniques. The input consists of job postings and job seeker data standardized in Step 1. The server extracts job seekers' skills and qualifications and calculates a suitability score with the job postings. The output is a quantified suitability score, which is used as a matching criterion. Machine learning algorithms are utilized in this process.

[0189] Step 3:

[0190] The server generates a candidate list based on the suitability score. The inputs are the suitability score calculated in step 2 and the job posting. The server prioritizes adding high-scoring job seekers to the list and outputs the optimal list of candidates for recruitment. This list is saved in a format accessible to the company's recruiters.

[0191] Step 4:

[0192] The terminal automatically creates the text for recruitment emails using the generated candidate list. The candidate list obtained in step 3 is used as input. The terminal generates text that includes individual candidate information and outputs personalized email messages. Specifically, information based on the job seeker's name and work history is incorporated into the text.

[0193] Step 5:

[0194] The server sends the generated recruitment emails according to a pre-set schedule. The input is the communication text generated in step 4. The server automatically sends it, ensuring it reaches job seekers at the time desired by the company. The output is the timely sent email.

[0195] Step 6:

[0196] The server aggregates email responses from recipients and performs sentiment analysis. The input is the content of the reply emails. The server uses natural language processing and sentiment analysis algorithms to identify emotions and analyze the tone of the responses. The output provides information indicating whether the emotion is positive, negative, or neutral.

[0197] Step 7:

[0198] The user decides on the next action based on the server's analysis results. The input is the sentiment analysis results obtained in step 6. Based on the tone of the email, the user makes strategic decisions such as proactive follow-up or scheduling an interview. The output is a concrete action taken for the next step in the recruitment process.

[0199] (Application Example 2)

[0200] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0201] In modern digital communication, individuals and businesses send and receive a vast number of messages daily, some of which may contain fraud or spam. However, quickly identifying suspicious content from this large volume of messages and mitigating the associated risks is not easy. Furthermore, appropriately recognizing and responding to the tone of emotionally charged messages is also challenging. Therefore, to achieve safe and appropriate communication, technologies that simultaneously perform sentiment analysis and communication risk mitigation are required.

[0202] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0203] In this invention, the server includes means for collecting and standardizing job information data and job seeker data; means for analyzing the job information data and job seeker data and calculating a match score; and means for sentimentally analyzing the response content and calculating a sentiment score for the response. This makes it possible to evaluate the sentiment and content risks of messages in real time and to immediately issue warnings against suspicious communications.

[0204] "Job posting data" refers to information that includes details such as the type of job, skills, and work location that companies are looking for.

[0205] "Job seeker data" refers to personal information including the job seeker's name, experience, skills, and desired conditions.

[0206] "Means of standardization" refer to processes and technologies for converting data collected in different formats into a unified format.

[0207] "Means of analysis" refer to methods and techniques for analyzing information based on collected data and obtaining necessary insights.

[0208] The "match score" is an evaluation index that quantifies the compatibility between job postings and job seeker information.

[0209] The "Scout Target List" is a list of job seekers who are eligible for scouting, created based on their evaluated match score.

[0210] A "scout email" is an electronic message containing offers or information that companies send to job seekers they are interested in.

[0211] "Methods for automatic generation" refer to systems that use programs or algorithms to automatically create content based on specified conditions.

[0212] "Means for aggregating and analyzing responses" refers to the process of statistically summarizing received replies and analyzing trends and characteristics.

[0213] "Sentiment analysis" is a technology that identifies emotions and tone from text data and calculates an emotion score.

[0214] An "emotion score" is a numerical representation of the intensity and type of emotions contained in the text.

[0215] "Means for generating warnings or notifications" refers to functions that provide warnings or information to users when certain conditions are met.

[0216] This invention is implemented by a system mainly composed of three elements: a server, a terminal, and a user.

[0217] The server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. The standardized data is analyzed using natural language processing techniques and machine learning algorithms to calculate a match score between job postings and job seeker information. Based on this score, a list of potential candidates for recruitment is generated, and sentiment analysis is used to calculate sentiment scores for messages.

[0218] The terminal automatically generates personalized recruitment emails based on a list of potential candidates provided by the server. These emails contain information best suited to each candidate and can be reviewed and approved by the company's recruiters. After approval, the emails are automatically sent according to a specified schedule.

[0219] Users, i.e., corporate recruiters, can leverage the information provided by this system to conduct recruitment activities quickly and efficiently. The server performs real-time sentiment analysis of recipients' email responses and evaluates the tone of the response. This allows users to take swift and appropriate follow-up actions.

[0220] For example, if a company wants to recruit specialists for a new project, this system can be used to send personalized recruitment emails to candidates who meet the requirements. If the response is positively rated, an interview can be scheduled early on.

[0221] An example of a prompt used by a generative AI model would be, "Calculate the sentiment score of this message and check if it contains any suspicious content."

[0222] This system utilizes technologies such as Python, NLTK, and TENSORFLOW® to enable advanced data analysis and sentiment analysis, supporting users' recruitment activities.

[0223] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0224] Step 1:

[0225] The server collects job postings and job seeker data from external data sources. Input is raw data obtained from each database, and output is data converted to a unified format. Specifically, it standardizes data in different formats into JSON format and performs data cleansing to prepare it for subsequent analysis.

[0226] Step 2:

[0227] The server uses natural language processing techniques to analyze standardized data and calculate a match score between job postings and job seeker information. The input is the standardized data generated in step 1, and the output is the match score. Specifically, it uses NLTK for keyword extraction and contextual analysis, and then performs scoring using a machine learning algorithm.

[0228] Step 3:

[0229] The server generates a list of potential candidates based on the calculated match score. The input is the match score obtained in step 2, and the output is a list of highly suitable job seekers. Specifically, a score threshold is set, and job seekers with a score above that threshold are selected.

[0230] Step 4:

[0231] The device automatically generates recruitment email text based on a list of potential recruits. The input is the list generated in step 3, and the output is a personalized recruitment email. Specifically, it uses a generation AI model based on a template to input prompt text and automatically creates the optimal text.

[0232] Step 5:

[0233] The user reviews the generated recruitment email text via their device and makes corrections as needed. The input is the email text created in step 4, and the output is the final email text reflecting the user's feedback. Specifically, an interface is provided that allows for easy editing of the email content via a GUI.

[0234] Step 6:

[0235] The server automatically sends the confirmed recruitment emails according to the specified schedule. The input is the email text confirmed in step 5, and the output is a notification that the email has been sent. Specifically, it works in conjunction with the mail server to send emails according to the schedule.

[0236] Step 7:

[0237] The server performs real-time sentiment analysis on responses to recruitment emails and calculates sentiment scores for each response. The input is the received email response, and the output is the analyzed sentiment score. Specifically, TensorFlow is used to analyze the received text and identify positive, negative, and neutral sentiments.

[0238] Step 8:

[0239] The user selects the next step based on their emotional score. The input is the emotional score obtained in step 7, and the output is the choice of the next action. Specifically, for example, if a positive emotion is detected, a strategy such as offering an interview opportunity might be adopted.

[0240] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0241] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0242] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0246] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0247] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0248] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0249] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0250] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0251] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0252] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0253] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0254] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0255] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0256] This invention relates to an automated system that improves efficiency and speed in the recruitment process for personnel in the medical and welfare fields. The system is designed to allow companies to easily scout suitable personnel and is primarily operated using servers and terminals.

[0257] First, the server collects job postings and job seeker data from various data sources and standardizes them into an analyzable format. Next, the server uses natural language processing technology to analyze the job postings and job seeker profiles and calculates a match score to evaluate the suitability of both parties.

[0258] Based on this match score, the server generates a list of candidates to scout. Based on this list, the terminal automatically generates a recruitment email. The generated email includes a customized message tailored to each job seeker's background and experience, designed to maximize the effectiveness of the approach.

[0259] The recruiters at the companies using the service can review these automatically generated emails on their devices and edit them as needed. After final confirmation, the server sends the recruitment emails to the target candidates.

[0260] Furthermore, the server automatically aggregates and analyzes responses to sent emails. Users can view the response results in real time through their terminals and quickly take the next steps based on that information, such as scheduling an interview.

[0261] This system allows for the rapid and accurate connection of companies and job seekers while significantly reducing time and effort. For example, if a hospital in need of nurses uses this system, recruitment emails will be automatically sent to suitable nurse candidates, enabling efficient recruitment activities.

[0262] The following describes the processing flow.

[0263] Step 1:

[0264] The server collects job postings and job seeker data from external data sources and databases. This is done automatically via APIs, and the information includes job descriptions, required skills, experience, and work location.

[0265] Step 2:

[0266] The server standardizes the collected data into a unified format. This includes data cleaning and normalization. By preparing data from different sources to be comparable, the accuracy of the analysis can be improved.

[0267] Step 3:

[0268] The server analyzes standardized data using natural language processing techniques. This analysis calculates a match score to evaluate the degree of compatibility between each job seeker's profile and the job posting. This score is calculated based on the degree of match in skills, experience, and qualifications.

[0269] Step 4:

[0270] The server generates a list of potential candidates based on the calculated match score. The list prioritizes candidates who best match the company's requirements.

[0271] Step 5:

[0272] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails follow a template and are customized to be personalized according to the candidate's name and background information.

[0273] Step 6:

[0274] The user, who is the recruiter, can review the content of the recruitment email via their device. They can add or revise the content as needed and then give final approval.

[0275] Step 7:

[0276] The server, upon user approval, sends recruitment emails to the target recipients. The sending date, time, and frequency are optimized using a scheduling function.

[0277] Step 8:

[0278] The server automatically aggregates and analyzes the responses to the sent scout emails. Based on the received response content, they are classified into categories such as gratitude, no interest, and request for additional information.

[0279] Step 9:

[0280] The user checks the aggregation result of the responses through the terminal and quickly determines the next action, such as setting an interview appointment. Also, based on the user's feedback, the server continuously conducts learning to improve the accuracy of the algorithm.

[0281] (Example 1)

[0282] Next, Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0283] In the modern medical and welfare fields, the personnel recruitment process is often time-consuming and laborious. Enterprises are required to quickly discover suitable talents and contact them in a time-efficient manner, but a huge amount of time and effort are required for matching job offers and job seekers. Also, it is a challenge for enterprises to individualize the content of emails and effectively reach talents to obtain a higher response rate. Therefore, an object of the present invention is to solve such problems and provide a system that enables appropriate and rapid talent scouting.

[0284] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 1 is realized by the following respective means.

[0285] In this invention, the server includes means for storing job offer information data and job seeker data in a database, means for analyzing the job offer information data and the job seeker data using natural language processing technology to calculate a matching score, and means for adding candidates whose score exceeds a threshold to a scout target list. Thereby, accurate and efficient analysis of job offer information and job seeker data, and prompt scouting of appropriate candidates become possible. Further, by including means for automatically generating a scout email text using a generative AI model and allowing the user to confirm and edit this content, individualized and effective recruitment communication can be realized.

[0286] "Job offer information data" is data that includes detailed information about job offers, such as the talent requirements, job content, and recruitment terms required by a company.

[0287] "Job seeker data" is data that includes information about an individual seeking employment, such as that individual's work history, skills, qualifications, and desired job type.

[0288] A "database" is an aggregate of information that stores data in a structured format and enables efficient search and management.

[0289] "Natural language processing technology" is technology for analyzing, understanding, and generating human language using a computer, and is used for text analysis, keyword extraction, etc.

[0290] A "matching score" is an index that quantifies the compatibility between job offer information data and job seeker data, and is a score for evaluating the extent to which a job seeker meets the job requirements.

[0291] A "scout target list" is a list that indicates a set of candidates selected based on the matching score and targeted for scouting.

[0292] A "generative AI model" is a model that uses artificial intelligence and has the ability to generate text or data for a specific purpose.

[0293] A "prompt statement" is an instruction statement used to guide the operation of a generative AI model, and it plays a role in influencing the generated results.

[0294] This invention realizes an automated system that streamlines the recruitment process in the medical and welfare fields. The main components of the system include servers, terminals, and users who utilize them.

[0295] The server collects job postings and job seeker data using web scraping techniques and stores them in a database management system (e.g., PostgreSQL). This provides advanced accessibility and data management capabilities. The server standardizes the data using the Python pandas library, handling missing values ​​and adjusting data types. Using natural language processing techniques, the server analyzes this data and utilizes the NLTK or spaCy library to calculate a match score.

[0296] The terminal automatically generates recruitment emails using a generation AI model (e.g., OpenAI GPT) based on the list of potential recruits received from the server. An example of a prompt used in this process is the instruction, "Create a recruitment email template to send to new nursing candidates. The email should highlight the candidate's experience in the nursing field and appeal to their growth opportunities at the hospital."

[0297] Users can review and edit automatically generated recruitment emails via their devices. This allows for a personalized approach tailored to each job seeker. After a final check, the server sends the finalized recruitment email using the SMTP protocol.

[0298] Furthermore, the server aggregates responses to sent emails in real time and provides the analysis results to the user. This system supports recruiters in quickly scheduling interviews and conducting follow-up activities. Thus, the invention aims to expedite the recruitment process and efficiently connect companies with job seekers.

[0299] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0300] Step 1:

[0301] The server collects job postings and job seeker data from various job sites using web scraping techniques. It automatically crawls sites according to a specific schedule and extracts necessary information from HTML pages using BeautifulSoup. The input consists of multiple web pages, and the output is unstructured text data. This text data is in a preparatory stage before standardization.

[0302] Step 2:

[0303] The server converts the collected text data into a structured data format. It uses the Python pandas library to create a dataset, ensuring missing value imputation and data type consistency. The input is unstructured text data, and the output is in a format suitable for storage in a database. PostgreSQL is used as the storage destination.

[0304] Step 3:

[0305] The server analyzes stored job postings and job seeker data using natural language processing techniques. Using NLTK or spaCy, it extracts keywords and important phrases from the data and calculates a match score. This calculation uses an algorithm that evaluates text similarity. The input is structured data, and the output is the match score for each job seeker.

[0306] Step 4:

[0307] Based on the calculated matching score, the server adds job seekers who exceed a certain threshold to the scout target list. The decision tree algorithm is used to determine the score as the criterion to extract candidates with high fitness. The input is the matching score, and the output is the scout target list.

[0308] Step 5:

[0309] Based on the scout target list, the terminal uses the generated AI model to automatically generate the text of the scout email. In this process, prompts such as "Generate an individualized message based on the job seeker's resume" are given. The input is the scout target list, and the output is the customized text of the scout email.

[0310] Step 6:

[0311] The user checks the automatically generated scout email via the terminal and edits it if necessary. The content is modified and the approach is adjusted through the editing interface on the browser. The input is the automatically generated email text, and the output is the finally confirmed email text.

[0312] Step 7:

[0313] The server sends the confirmed scout email to each job seeker through the SMTP protocol. The input is the confirmed email text, and the output is the sent email. In this process, the email sending history is also recorded in the database simultaneously.

[0314] Step 8:

[0315] The server aggregates and analyzes the responses to the sent emails in real time. The pandas library is used to perform response rate and behavior analysis, and the results are saved in the database. The input is the received reply data, and the output is the analyzed response data.

[0316] Step 9:

[0317] Users review the analysis results via their device and proceed to the next recruitment step. For example, they might plan to quickly schedule interviews or initiate further communication. The input is the analyzed response data, and the output is the determined recruitment strategy.

[0318] (Application Example 1)

[0319] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0320] The recruitment process in the security field is complex and time-consuming, making it difficult to secure suitable personnel. In particular, recruiting personnel for nighttime or specialized work requires rapid and effective matching. This invention solves these problems, streamlining the recruitment process for security personnel and providing a means to quickly secure talent.

[0321] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0322] In this invention, the server includes means for collecting and standardizing employment information data and applicant information data, means for calculating suitability scores, and means for automatically generating message text according to the list of candidates to be selected. This makes it possible to support the recruitment process for personnel in the security field and to quickly secure suitable personnel.

[0323] "Employment information data" refers to information about job postings provided by companies and organizations, including details such as job title, job description, work location, working hours, and salary conditions.

[0324] "Applicant information data" refers to personal information about job seekers, as well as data such as work history, skills, and qualifications, which is used to determine their suitability for employment.

[0325] "Standardization" is the process of converting data with different forms and structures into a unified format, in order to facilitate analysis.

[0326] A "suitability score" is an index that quantifies the degree of compatibility between job postings and applicant information, and is used to evaluate the likelihood of hiring.

[0327] A "selection list" is a list compiled by a company based on suitability scores, listing candidates that it should consider scouting or interviewing.

[0328] "Automatically generating message text" means that the system automatically generates messages for individual applicants based on pre-configured templates, enabling efficient communication.

[0329] The "recruitment process for security personnel" refers to the entire process from searching for, selecting, and hiring individuals to engage in security work.

[0330] "Applications that can be installed on various devices" are software programs that can be downloaded and used on digital devices such as smartphones and tablets.

[0331] The system implementing this invention is a software program for companies to quickly and accurately select applicants in the security field and streamline the recruitment process. This program consists of a server and terminals, and a specific embodiment thereof is shown below.

[0332] The server first collects employment and applicant information data through the use of external databases and APIs. The collected data is then converted into an analyzable format through standardization. This standardization process includes filtering and format conversion to ensure data consistency.

[0333] Next, the server uses natural language processing technology to analyze employment information data and applicant information data. During this analysis, a suitability score is calculated, and a list of candidates for selection is generated based on this score. This list is optimized by the server's algorithm, enabling efficient talent selection.

[0334] Next, based on the list of selected candidates, the device automatically generates a message. In this process, individual information for each applicant is inserted into a template, creating a customized message. The generated message is then sent to the applicant via the application on the device.

[0335] The hardware used to run this system will be cloud servers (e.g., Amazon Web Services or Google Cloud Platform), which will handle the necessary computing and data storage. For software, Python libraries (e.g., NLTK or SpaCy) can be used for data analysis, and Flask or Django can be used as the UI platform.

[0336] As a concrete example, consider a company that needs personnel to handle nighttime security. This system collects relevant applicant information and automatically generates and sends messages to candidates who meet the hiring requirements. As a result, rapid and effective recruitment becomes possible.

[0337] Examples of prompts for the generating AI model include: "Calculate a suitability score for applicants suitable for the night security guard position based on the following requirements, and generate a customized email: flexibility in working hours, past security experience, and special skills."

[0338] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0339] Step 1:

[0340] The server collects employment and applicant information data from external databases and APIs. The input consists of raw data from multiple data sources. The server then performs data cleansing to convert this data into a consistent format and standardize it. This results in output data in a parseable format.

[0341] Step 2:

[0342] The server analyzes standardized employment and applicant data using natural language processing techniques. The input is standardized text data, and analysis is performed using a natural language processing library (e.g., SpaCy). This process quantifies the characteristics of job postings and applicant profiles and outputs a suitability score.

[0343] Step 3:

[0344] The server generates a list of candidates based on the calculated suitability score. The input is the suitability score, and the server's algorithm evaluates the score and lists candidates in descending order of suitability. As a result, a list of candidates to be scouted is output.

[0345] Step 4:

[0346] The terminal automatically generates message text based on the list of selected individuals. The input consists of the list of selected individuals and a template message. Personalized information is inserted into the template to output a customized message. Users can edit and review this message.

[0347] Step 5:

[0348] The server sends the generated message to the applicant. The generated message is used as input, and the transmission operation is performed using the SMTP protocol. As a result of the transmission, a transmission status is output, which may indicate a response has been received.

[0349] Step 6:

[0350] The server aggregates and analyzes responses from applicants. Using the received responses as input, an analysis algorithm evaluates their content and outputs recommendations for the next step (e.g., scheduling an interview). Users can then use the aggregated results to make quick hiring decisions.

[0351] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0352] This invention combines an emotion engine with an automated system that enables efficient scouting activities in the recruitment process for the medical and welfare sectors. The system aims to provide a deeper understanding of the interaction between companies and job seekers and to offer a personalized approach.

[0353] The system operates on a server-terminal basis. First, the server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. Next, the server analyzes the data using natural language processing technology and calculates a match score. Based on this score, it generates a list of optimal candidates for recruitment.

[0354] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails include personalized information based on the candidate's name and background, facilitating more effective communication. Users, i.e., company recruiters, can review the emails via the device, make any necessary revisions, and then give final approval.

[0355] The server automatically sends approved emails according to a specified schedule. Furthermore, it uses an emotion engine to analyze recipient email responses in real time. The server leverages natural language processing and machine learning algorithms to identify the emotions expressed in the responses. Based on these results, users can then select the next steps, such as customized follow-up emails or interview approaches.

[0356] For example, if a hospital wants to hire nurses, this system can be used to automatically send recruitment emails to nurse candidates whose qualifications and experience meet the requirements. If the emotion engine identifies the response as positive, the system can quickly take more effective steps, such as proactively scheduling an interview. In this way, companies can conduct recruitment activities efficiently and precisely.

[0357] The following describes the processing flow.

[0358] Step 1:

[0359] The server automatically collects job postings and job seeker data from external databases. The data includes detailed information such as job title, skills, location, and salary.

[0360] Step 2:

[0361] The server standardizes the collected data into a unified format. Irrelevant information is removed, and the format is standardized to prepare the data for analysis.

[0362] Step 3:

[0363] The server analyzes standardized data using natural language processing techniques. This analysis compares job requirements with the skills and experience of job seekers to calculate a match score. This score is used to evaluate which job seeker is the best fit for the job posting.

[0364] Step 4:

[0365] The server generates a list of potential candidates based on the calculated match score. This list prioritizes candidates who best match the company's requirements.

[0366] Step 5:

[0367] The device uses AI to automatically generate recruitment emails based on a list of potential candidates. The emails are customized to match the job seeker's name and past experience.

[0368] Step 6:

[0369] The user reviews the generated recruitment email text via their device and edits it as needed. After final confirmation, the user approves sending the email.

[0370] Step 7:

[0371] The server sends recruitment emails to target individuals after receiving user approval. Sending is done according to an optimized schedule.

[0372] Step 8:

[0373] The server uses an emotion engine to analyze responses to recruitment emails. It uses natural language processing and machine learning to determine the user's emotions from the received responses. This analysis identifies whether the response is positive or negative.

[0374] Step 9:

[0375] Users can view the analysis results from the emotion engine via their device and decide on their next action based on the response. For example, if they receive a positive response, they can quickly take appropriate action, such as scheduling a meeting.

[0376] (Example 2)

[0377] Next, we will describe Example 2. 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".

[0378] A smooth matching process between job postings and job seekers is a crucial element in efficient recruitment. However, for companies, finding the right candidates with the required qualifications and experience from a large amount of data remains a time-consuming and resource-intensive task. Furthermore, personalizing recruitment emails for effective communication is also challenging. To address these challenges, there is a need for a system that automates the recruitment process and provides follow-up strategies through sentiment analysis.

[0379] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0380] In this invention, the server includes means for collecting job information data and job seeker data and converting them into a unified format; means for analyzing the job information data and job seeker data and calculating a suitability score; and means for generating a candidate list based on the suitability score. This makes it possible to quickly and accurately identify suitable personnel from a large amount of information and to efficiently personalize subsequent communication.

[0381] "Job posting data" refers to data provided by employers that includes details about the job, required skills, experience, salary range, and other relevant information.

[0382] "Job seeker data" refers to data that represents information provided by job seekers, including their personal work history, skills, qualifications, and desired conditions.

[0383] A "unified format" refers to a state where data acquired in different formats is converted into a consistent format, making comparison and analysis easier.

[0384] A "fit score" is an evaluation index that quantifies the compatibility between job postings and job seekers based on their information.

[0385] A "candidate list" refers to a set of job seekers selected based on their suitability score who best match a specific job opening.

[0386] "Communication text" refers to the content of emails or messages sent for the purpose of communicating with job seekers.

[0387] "Personalized information" refers to content that includes details based on an individual's name and professional background, tailored to a specific recipient.

[0388] "Identifying emotions" means analyzing the emotional tone of a recipient's response and classifying it into categories such as positive, negative, or neutral.

[0389] "Language analysis technology" refers to techniques that use natural language processing and machine learning to analyze text data and understand its meaning and intent.

[0390] The system of the present invention operates on a server and terminal basis and aims to streamline the personnel recruitment process in the medical and welfare fields. The following describes embodiments of this system.

[0391] Data collection and standardization:

[0392] The server first collects job postings and job seeker data from external data sources. This includes various job portals and company databases. Since the collected data may be in different formats, the server converts the data into a unified format. In this process, database languages ​​are used to organize the data and create a consistent dataset.

[0393] Data analysis and scoring:

[0394] Next, the server uses language analysis technology to analyze job seekers and job postings. This analysis utilizes natural language processing technology and machine learning algorithms. Specifically, it extracts the skills and qualifications of job seekers and quantifies how well they match the job requirements as a relevance score.

[0395] Generating a candidate list:

[0396] Based on the suitability score, the server generates a list of candidates. This list is stored in a format that can be accessed later by the company's recruiters.

[0397] Creating and sending recruitment emails:

[0398] The terminal automatically creates a message based on the generated candidate list. Here, it uses individualized information to adopt a communication style tailored to the recipient job seeker. This email is sent automatically according to a schedule.

[0399] Response collection and sentiment analysis:

[0400] When a reply is received, the server analyzes its content in real time. Software for identifying emotions analyzes the recipient's response tone to determine whether it is positive or negative. This provides information to decide on further follow-up and strategic actions.

[0401] As a concrete example, consider a scenario where a hospital is trying to recruit nurses. Using this system, nurses with the necessary qualifications and experience can be automatically listed, and personalized recruitment emails can be sent quickly. If a positive response is detected, interviews can be scheduled promptly, allowing for more effective recruitment activities.

[0402] An example of a prompt might be: "Generate a list of job seekers with nursing qualifications and experience, prepare and send recruitment emails, analyze the email responses, and suggest the next steps."

[0403] This system is a powerful tool for companies to deepen their interaction with job seekers and develop effective recruitment strategies.

[0404] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0405] Step 1:

[0406] The server collects job postings and job seeker data from external data sources. Its inputs include raw data obtained from job portals and company databases. The server processes this data into a consistent format and outputs a unified dataset. During this process, it uses a database language to standardize different categories and make them comparable.

[0407] Step 2:

[0408] The server analyzes a unified dataset using natural language processing techniques. The input consists of job postings and job seeker data standardized in Step 1. The server extracts job seekers' skills and qualifications and calculates a suitability score with the job postings. The output is a quantified suitability score, which is used as a matching criterion. Machine learning algorithms are utilized in this process.

[0409] Step 3:

[0410] The server generates a candidate list based on the suitability score. The inputs are the suitability score calculated in step 2 and the job posting. The server prioritizes adding high-scoring job seekers to the list and outputs the optimal list of candidates for recruitment. This list is saved in a format accessible to the company's recruiters.

[0411] Step 4:

[0412] The terminal automatically creates the text for recruitment emails using the generated candidate list. The candidate list obtained in step 3 is used as input. The terminal generates text that includes individual candidate information and outputs personalized email messages. Specifically, information based on the job seeker's name and work history is incorporated into the text.

[0413] Step 5:

[0414] The server sends the generated recruitment emails according to a pre-set schedule. The input is the communication text generated in step 4. The server automatically sends it, ensuring it reaches job seekers at the time desired by the company. The output is the timely sent email.

[0415] Step 6:

[0416] The server aggregates email responses from recipients and performs sentiment analysis. The input is the content of the reply emails. The server uses natural language processing and sentiment analysis algorithms to identify emotions and analyze the tone of the responses. The output provides information indicating whether the emotion is positive, negative, or neutral.

[0417] Step 7:

[0418] The user decides on the next action based on the server's analysis results. The input is the sentiment analysis results obtained in step 6. Based on the tone of the email, the user makes strategic decisions such as proactive follow-up or scheduling an interview. The output is a concrete action taken for the next step in the recruitment process.

[0419] (Application Example 2)

[0420] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0421] In modern digital communication, individuals and businesses send and receive a vast number of messages daily, some of which may contain fraud or spam. However, quickly identifying suspicious content from this large volume of messages and mitigating the associated risks is not easy. Furthermore, appropriately recognizing and responding to the tone of emotionally charged messages is also challenging. Therefore, to achieve safe and appropriate communication, technologies that simultaneously perform sentiment analysis and communication risk mitigation are required.

[0422] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0423] In this invention, the server includes means for collecting and standardizing job information data and job seeker data; means for analyzing the job information data and job seeker data and calculating a match score; and means for sentimentally analyzing the response content and calculating a sentiment score for the response. This makes it possible to evaluate the sentiment and content risks of messages in real time and to immediately issue warnings against suspicious communications.

[0424] "Job posting data" refers to information that includes details such as the type of job, skills, and work location that companies are looking for.

[0425] "Job seeker data" refers to personal information including the job seeker's name, experience, skills, and desired conditions.

[0426] "Means of standardization" refer to processes and technologies for converting data collected in different formats into a unified format.

[0427] "Means of analysis" refer to methods and techniques for analyzing information based on collected data and obtaining necessary insights.

[0428] The "match score" is an evaluation index that quantifies the compatibility between job postings and job seeker information.

[0429] The "Scout Target List" is a list of job seekers who are eligible for scouting, created based on their evaluated match score.

[0430] A "scout email" is an electronic message containing offers or information that companies send to job seekers they are interested in.

[0431] "Methods for automatic generation" refer to systems that use programs or algorithms to automatically create content based on specified conditions.

[0432] "Means for aggregating and analyzing responses" refers to the process of statistically summarizing received replies and analyzing trends and characteristics.

[0433] "Sentiment analysis" is a technology that identifies emotions and tone from text data and calculates an emotion score.

[0434] An "emotion score" is a numerical representation of the intensity and type of emotions contained in the text.

[0435] "Means for generating warnings or notifications" refers to functions that provide warnings or information to users when certain conditions are met.

[0436] This invention is implemented by a system mainly composed of three elements: a server, a terminal, and a user.

[0437] The server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. The standardized data is analyzed using natural language processing techniques and machine learning algorithms to calculate a match score between job postings and job seeker information. Based on this score, a list of potential candidates for recruitment is generated, and sentiment analysis is used to calculate sentiment scores for messages.

[0438] The terminal automatically generates personalized recruitment emails based on a list of potential candidates provided by the server. These emails contain information best suited to each candidate and can be reviewed and approved by the company's recruiters. After approval, the emails are automatically sent according to a specified schedule.

[0439] Users, i.e., corporate recruiters, can leverage the information provided by this system to conduct recruitment activities quickly and efficiently. The server performs real-time sentiment analysis of recipients' email responses and evaluates the tone of the response. This allows users to take swift and appropriate follow-up actions.

[0440] For example, if a company wants to recruit specialists for a new project, this system can be used to send personalized recruitment emails to candidates who meet the requirements. If the response is positively rated, an interview can be scheduled early on.

[0441] An example of a prompt used by a generative AI model would be, "Calculate the sentiment score of this message and check if it contains any suspicious content."

[0442] This system utilizes technologies such as Python, NLTK, and TensorFlow to enable advanced data analysis and sentiment analysis, supporting users' recruitment activities.

[0443] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0444] Step 1:

[0445] The server collects job postings and job seeker data from external data sources. Input is raw data obtained from each database, and output is data converted to a unified format. Specifically, it standardizes data in different formats into JSON format and performs data cleansing to prepare it for subsequent analysis.

[0446] Step 2:

[0447] The server uses natural language processing techniques to analyze standardized data and calculate a match score between job postings and job seeker information. The input is the standardized data generated in step 1, and the output is the match score. Specifically, it uses NLTK for keyword extraction and contextual analysis, and then performs scoring using a machine learning algorithm.

[0448] Step 3:

[0449] The server generates a list of potential candidates based on the calculated match score. The input is the match score obtained in step 2, and the output is a list of highly suitable job seekers. Specifically, a score threshold is set, and job seekers with a score above that threshold are selected.

[0450] Step 4:

[0451] The device automatically generates recruitment email text based on a list of potential recruits. The input is the list generated in step 3, and the output is a personalized recruitment email. Specifically, it uses a generation AI model based on a template to input prompt text and automatically creates the optimal text.

[0452] Step 5:

[0453] The user reviews the generated recruitment email text via their device and makes corrections as needed. The input is the email text created in step 4, and the output is the final email text reflecting the user's feedback. Specifically, an interface is provided that allows for easy editing of the email content via a GUI.

[0454] Step 6:

[0455] The server automatically sends the confirmed recruitment emails according to the specified schedule. The input is the email text confirmed in step 5, and the output is a notification that the email has been sent. Specifically, it works in conjunction with the mail server to send emails according to the schedule.

[0456] Step 7:

[0457] The server performs real-time sentiment analysis on responses to recruitment emails and calculates sentiment scores for each response. The input is the received email response, and the output is the analyzed sentiment score. Specifically, TensorFlow is used to analyze the received text and identify positive, negative, and neutral sentiments.

[0458] Step 8:

[0459] The user selects the next step based on their emotional score. The input is the emotional score obtained in step 7, and the output is the choice of the next action. Specifically, for example, if a positive emotion is detected, a strategy such as offering an interview opportunity might be adopted.

[0460] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0461] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0462] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0463] [Third Embodiment]

[0464] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0465] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0466] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0467] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0468] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0469] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0470] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0471] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0472] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0473] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0474] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0475] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0476] This invention relates to an automated system that improves efficiency and speed in the recruitment process for personnel in the medical and welfare fields. The system is designed to allow companies to easily scout suitable personnel and is primarily operated using servers and terminals.

[0477] First, the server collects job postings and job seeker data from various data sources and standardizes them into an analyzable format. Next, the server uses natural language processing technology to analyze the job postings and job seeker profiles and calculates a match score to evaluate the suitability of both parties.

[0478] Based on this match score, the server generates a list of candidates to scout. Based on this list, the terminal automatically generates a recruitment email. The generated email includes a customized message tailored to each job seeker's background and experience, designed to maximize the effectiveness of the approach.

[0479] The recruiters at the companies using the service can review these automatically generated emails on their devices and edit them as needed. After final confirmation, the server sends the recruitment emails to the target candidates.

[0480] Furthermore, the server automatically aggregates and analyzes responses to sent emails. Users can view the response results in real time through their terminals and quickly take the next steps based on that information, such as scheduling an interview.

[0481] This system allows for the rapid and accurate connection of companies and job seekers while significantly reducing time and effort. For example, if a hospital in need of nurses uses this system, recruitment emails will be automatically sent to suitable nurse candidates, enabling efficient recruitment activities.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] The server collects job postings and job seeker data from external data sources and databases. This is done automatically via APIs, and the information includes job descriptions, required skills, experience, and work location.

[0485] Step 2:

[0486] The server standardizes the collected data into a unified format. This includes data cleaning and normalization. By preparing data from different sources to be comparable, the accuracy of the analysis can be improved.

[0487] Step 3:

[0488] The server analyzes standardized data using natural language processing techniques. This analysis calculates a match score to evaluate the degree of compatibility between each job seeker's profile and the job posting. This score is calculated based on the degree of match in skills, experience, and qualifications.

[0489] Step 4:

[0490] The server generates a list of potential candidates based on the calculated match score. The list prioritizes candidates who best match the company's requirements.

[0491] Step 5:

[0492] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails follow a template and are customized to be personalized according to the candidate's name and background information.

[0493] Step 6:

[0494] The user, who is the recruiter, can review the content of the recruitment email via their device. They can add or revise the content as needed and then give final approval.

[0495] Step 7:

[0496] The server, upon user approval, sends recruitment emails to the target recipients. The sending date, time, and frequency are optimized using a scheduling function.

[0497] Step 8:

[0498] The server automatically aggregates and analyzes responses to sent recruitment emails. Based on the content of the received responses, they are classified into categories such as "thank you," "not interested," and "request for additional information."

[0499] Step 9:

[0500] Users can view the aggregated response results through their terminals and quickly decide on their next action, such as scheduling a meeting appointment. Furthermore, the server continuously learns and improves the accuracy of its algorithms based on user feedback.

[0501] (Example 1)

[0502] Next, we will describe Example 1. 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."

[0503] In the modern medical and welfare fields, the recruitment process is often time-consuming and laborious. Companies are required to quickly find suitable personnel and contact them efficiently, but matching job openings with job seekers requires a tremendous amount of time and effort. Furthermore, personalizing email content and effectively delivering it to candidates to achieve a higher response rate is a challenge for companies. Therefore, the present invention aims to solve these problems and provide a system that enables appropriate and rapid talent scouting.

[0504] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0505] In this invention, the server includes means for storing job information data and job seeker data in a database, means for analyzing the job information data and job seeker data using natural language processing technology to calculate a match score, and means for adding candidates whose scores exceed a threshold to a list of candidates to be scouted. This enables accurate and efficient analysis of job information and job seeker data, and rapid scouting of suitable candidates. Furthermore, by including means for automatically generating scout email text using a generative AI model, and allowing users to review and edit this content, it becomes possible to realize personalized and effective recruiting communication.

[0506] "Job posting data" refers to data containing detailed information about job openings, including the required personnel conditions, job descriptions, and application requirements of companies.

[0507] "Job seeker data" refers to data containing information about individuals seeking employment, including their work history, skills, qualifications, and desired occupation.

[0508] A "database" is a collection of information that stores data in a structured format, allowing for efficient searching and management.

[0509] "Natural language processing technology" refers to technologies used to analyze, understand, and generate human language using computers, and is used for tasks such as text analysis and keyword extraction.

[0510] The "match score" is an index that quantifies the compatibility between job posting data and job seeker data, and is used to evaluate how well a job seeker matches the job requirements.

[0511] The "Scout Candidate List" is a list of candidates who have been selected based on their match score and are eligible to be scouted.

[0512] A "generative AI model" is a model that uses artificial intelligence and has the ability to generate text or data for a specific purpose.

[0513] A "prompt statement" is an instruction statement used to guide the operation of a generative AI model, and it plays a role in influencing the generated results.

[0514] This invention realizes an automated system that streamlines the recruitment process in the medical and welfare fields. The main components of the system include servers, terminals, and users who utilize them.

[0515] The server collects job postings and job seeker data using web scraping techniques and stores them in a database management system (e.g., PostgreSQL). This provides advanced accessibility and data management capabilities. The server standardizes the data using the Python pandas library, handling missing values ​​and adjusting data types. Using natural language processing techniques, the server analyzes this data and utilizes the NLTK or spaCy library to calculate a match score.

[0516] The terminal automatically generates recruitment emails using a generation AI model (e.g., OpenAI GPT) based on the list of potential recruits received from the server. An example of a prompt used in this process is the instruction, "Create a recruitment email template to send to new nursing candidates. The email should highlight the candidate's experience in the nursing field and appeal to their growth opportunities at the hospital."

[0517] Users can review and edit automatically generated recruitment emails via their devices. This allows for a personalized approach tailored to each job seeker. After a final check, the server sends the finalized recruitment email using the SMTP protocol.

[0518] Furthermore, the server aggregates responses to sent emails in real time and provides the analysis results to the user. This system supports recruiters in quickly scheduling interviews and conducting follow-up activities. Thus, the invention aims to expedite the recruitment process and efficiently connect companies with job seekers.

[0519] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0520] Step 1:

[0521] The server collects job postings and job seeker data from various job sites using web scraping techniques. It automatically crawls sites according to a specific schedule and extracts necessary information from HTML pages using BeautifulSoup. The input consists of multiple web pages, and the output is unstructured text data. This text data is in a preparatory stage before standardization.

[0522] Step 2:

[0523] The server converts the collected text data into a structured data format. It uses the Python pandas library to create a dataset, ensuring missing value imputation and data type consistency. The input is unstructured text data, and the output is in a format suitable for storage in a database. PostgreSQL is used as the storage destination.

[0524] Step 3:

[0525] The server analyzes stored job postings and job seeker data using natural language processing techniques. Using NLTK or spaCy, it extracts keywords and important phrases from the data and calculates a match score. This calculation uses an algorithm that evaluates text similarity. The input is structured data, and the output is the match score for each job seeker.

[0526] Step 4:

[0527] The server adds job seekers who exceed a certain threshold based on the calculated match score to a list of potential recruits. A decision tree algorithm is used to select candidates with high suitability based on the score. The input is the match score, and the output is a list of potential recruits.

[0528] Step 5:

[0529] The terminal automatically generates recruitment emails using an AI model based on a list of potential candidates. During this process, prompts such as "Generate a personalized message based on the job seeker's background" are provided. The input is a list of potential candidates, and the output is a customized recruitment email.

[0530] Step 6:

[0531] Users can review automatically generated recruitment emails via their devices and edit them as needed. They can modify content and adjust their approach using a browser-based editing interface. The input is the automatically generated email text, and the output is the final, reviewed email text.

[0532] Step 7:

[0533] The server sends the confirmed recruitment emails to each job seeker via the SMTP protocol. The input is the confirmed email text, and the output is the sent email. During this process, the email sending history is also recorded in the database.

[0534] Step 8:

[0535] The server aggregates and analyzes responses to sent emails in real time. It uses the pandas library to perform response rate and behavioral analysis, and saves the results to a database. The input is the received reply data, and the output is the analyzed response data.

[0536] Step 9:

[0537] Users review the analysis results via their device and proceed to the next recruitment step. For example, they might plan to quickly schedule interviews or initiate further communication. The input is the analyzed response data, and the output is the determined recruitment strategy.

[0538] (Application Example 1)

[0539] Next, we will explain Application Example 1. In the following explanation, 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."

[0540] The recruitment process in the security field is complex and time-consuming, making it difficult to secure suitable personnel. In particular, recruiting personnel for nighttime or specialized work requires rapid and effective matching. This invention solves these problems, streamlining the recruitment process for security personnel and providing a means to quickly secure talent.

[0541] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0542] In this invention, the server includes means for collecting and standardizing employment information data and applicant information data, means for calculating suitability scores, and means for automatically generating message text according to the list of candidates to be selected. This makes it possible to support the recruitment process for personnel in the security field and to quickly secure suitable personnel.

[0543] "Employment information data" refers to information about job postings provided by companies and organizations, including details such as job title, job description, work location, working hours, and salary conditions.

[0544] "Applicant information data" refers to personal information about job seekers, as well as data such as work history, skills, and qualifications, which is used to determine their suitability for employment.

[0545] "Standardization" is the process of converting data with different forms and structures into a unified format, in order to facilitate analysis.

[0546] A "suitability score" is an index that quantifies the degree of compatibility between job postings and applicant information, and is used to evaluate the likelihood of hiring.

[0547] A "selection list" is a list compiled by a company based on suitability scores, listing candidates that it should consider scouting or interviewing.

[0548] "Automatically generating message text" means that the system automatically generates messages for individual applicants based on pre-configured templates, enabling efficient communication.

[0549] The "recruitment process for security personnel" refers to the entire process from searching for, selecting, and hiring individuals to engage in security work.

[0550] "Applications that can be installed on various devices" are software programs that can be downloaded and used on digital devices such as smartphones and tablets.

[0551] The system implementing this invention is a software program for companies to quickly and accurately select applicants in the security field and streamline the recruitment process. This program consists of a server and terminals, and a specific embodiment thereof is shown below.

[0552] The server first collects employment and applicant information data through the use of external databases and APIs. The collected data is then converted into an analyzable format through standardization. This standardization process includes filtering and format conversion to ensure data consistency.

[0553] Next, the server uses natural language processing technology to analyze employment information data and applicant information data. During this analysis, a suitability score is calculated, and a list of candidates for selection is generated based on this score. This list is optimized by the server's algorithm, enabling efficient talent selection.

[0554] Next, based on the list of selected candidates, the device automatically generates a message. In this process, individual information for each applicant is inserted into a template, creating a customized message. The generated message is then sent to the applicant via the application on the device.

[0555] The hardware used to run this system will be cloud servers (e.g., Amazon Web Services or Google Cloud Platform), which will handle the necessary computing and data storage. For software, Python libraries (e.g., NLTK or SpaCy) can be used for data analysis, and Flask or Django can be used as the UI platform.

[0556] As a concrete example, consider a company that needs personnel to handle nighttime security. This system collects relevant applicant information and automatically generates and sends messages to candidates who meet the hiring requirements. As a result, rapid and effective recruitment becomes possible.

[0557] Examples of prompts for the generating AI model include: "Calculate a suitability score for applicants suitable for the night security guard position based on the following requirements, and generate a customized email: flexibility in working hours, past security experience, and special skills."

[0558] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0559] Step 1:

[0560] The server collects employment and applicant information data from external databases and APIs. The input consists of raw data from multiple data sources. The server then performs data cleansing to convert this data into a consistent format and standardize it. This results in output data in a parseable format.

[0561] Step 2:

[0562] The server analyzes standardized employment and applicant data using natural language processing techniques. The input is standardized text data, and analysis is performed using a natural language processing library (e.g., SpaCy). This process quantifies the characteristics of job postings and applicant profiles and outputs a suitability score.

[0563] Step 3:

[0564] The server generates a list of candidates based on the calculated suitability score. The input is the suitability score, and the server's algorithm evaluates the score and lists candidates in descending order of suitability. As a result, a list of candidates to be scouted is output.

[0565] Step 4:

[0566] The terminal automatically generates message text based on the list of selected individuals. The input consists of the list of selected individuals and a template message. Personalized information is inserted into the template to output a customized message. Users can edit and review this message.

[0567] Step 5:

[0568] The server sends the generated message to the applicant. The generated message is used as input, and the transmission operation is performed using the SMTP protocol. As a result of the transmission, a transmission status is output, which may indicate a response has been received.

[0569] Step 6:

[0570] The server aggregates and analyzes responses from applicants. Using the received responses as input, an analysis algorithm evaluates their content and outputs recommendations for the next step (e.g., scheduling an interview). Users can then use the aggregated results to make quick hiring decisions.

[0571] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0572] This invention combines an emotion engine with an automated system that enables efficient scouting activities in the recruitment process for the medical and welfare sectors. The system aims to provide a deeper understanding of the interaction between companies and job seekers and to offer a personalized approach.

[0573] The system operates on a server-terminal basis. First, the server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. Next, the server analyzes the data using natural language processing technology and calculates a match score. Based on this score, it generates a list of optimal candidates for recruitment.

[0574] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails include personalized information based on the candidate's name and background, facilitating more effective communication. Users, i.e., company recruiters, can review the emails via the device, make any necessary revisions, and then give final approval.

[0575] The server automatically sends approved emails according to a specified schedule. Furthermore, it uses an emotion engine to analyze recipient email responses in real time. The server leverages natural language processing and machine learning algorithms to identify the emotions expressed in the responses. Based on these results, users can then select the next steps, such as customized follow-up emails or interview approaches.

[0576] For example, if a hospital wants to hire nurses, this system can be used to automatically send recruitment emails to nurse candidates whose qualifications and experience meet the requirements. If the emotion engine identifies the response as positive, the system can quickly take more effective steps, such as proactively scheduling an interview. In this way, companies can conduct recruitment activities efficiently and precisely.

[0577] The following describes the processing flow.

[0578] Step 1:

[0579] The server automatically collects job postings and job seeker data from external databases. The data includes detailed information such as job title, skills, location, and salary.

[0580] Step 2:

[0581] The server standardizes the collected data into a unified format. Irrelevant information is removed, and the format is standardized to prepare the data for analysis.

[0582] Step 3:

[0583] The server analyzes standardized data using natural language processing techniques. This analysis compares job requirements with the skills and experience of job seekers to calculate a match score. This score is used to evaluate which job seeker is the best fit for the job posting.

[0584] Step 4:

[0585] The server generates a list of potential candidates based on the calculated match score. This list prioritizes candidates who best match the company's requirements.

[0586] Step 5:

[0587] The device uses AI to automatically generate recruitment emails based on a list of potential candidates. The emails are customized to match the job seeker's name and past experience.

[0588] Step 6:

[0589] The user reviews the generated recruitment email text via their device and edits it as needed. After final confirmation, the user approves sending the email.

[0590] Step 7:

[0591] The server sends recruitment emails to target individuals after receiving user approval. Sending is done according to an optimized schedule.

[0592] Step 8:

[0593] The server uses an emotion engine to analyze responses to recruitment emails. It uses natural language processing and machine learning to determine the user's emotions from the received responses. This analysis identifies whether the response is positive or negative.

[0594] Step 9:

[0595] Users can view the analysis results from the emotion engine via their device and decide on their next action based on the response. For example, if they receive a positive response, they can quickly take appropriate action, such as scheduling a meeting.

[0596] (Example 2)

[0597] Next, we will describe Example 2. 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."

[0598] A smooth matching process between job postings and job seekers is a crucial element in efficient recruitment. However, for companies, finding the right candidates with the required qualifications and experience from a large amount of data remains a time-consuming and resource-intensive task. Furthermore, personalizing recruitment emails for effective communication is also challenging. To address these challenges, there is a need for a system that automates the recruitment process and provides follow-up strategies through sentiment analysis.

[0599] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0600] In this invention, the server includes means for collecting job information data and job seeker data and converting them into a unified format; means for analyzing the job information data and job seeker data and calculating a suitability score; and means for generating a candidate list based on the suitability score. This makes it possible to quickly and accurately identify suitable personnel from a large amount of information and to efficiently personalize subsequent communication.

[0601] "Job posting data" refers to data provided by employers that includes details about the job, required skills, experience, salary range, and other relevant information.

[0602] "Job seeker data" refers to data that represents information provided by job seekers, including their personal work history, skills, qualifications, and desired conditions.

[0603] A "unified format" refers to a state where data acquired in different formats is converted into a consistent format, making comparison and analysis easier.

[0604] A "fit score" is an evaluation index that quantifies the compatibility between job postings and job seekers based on their information.

[0605] A "candidate list" refers to a set of job seekers selected based on their suitability score who best match a specific job opening.

[0606] "Communication text" refers to the content of emails or messages sent for the purpose of communicating with job seekers.

[0607] "Personalized information" refers to content that includes details based on an individual's name and professional background, tailored to a specific recipient.

[0608] "Identifying emotions" means analyzing the emotional tone of a recipient's response and classifying it into categories such as positive, negative, or neutral.

[0609] "Language analysis technology" refers to techniques that use natural language processing and machine learning to analyze text data and understand its meaning and intent.

[0610] The system of the present invention operates on a server and terminal basis and aims to streamline the personnel recruitment process in the medical and welfare fields. The following describes embodiments of this system.

[0611] Data collection and standardization:

[0612] The server first collects job postings and job seeker data from external data sources. This includes various job portals and company databases. Since the collected data may be in different formats, the server converts the data into a unified format. In this process, database languages ​​are used to organize the data and create a consistent dataset.

[0613] Data analysis and scoring:

[0614] Next, the server uses language analysis technology to analyze job seekers and job postings. This analysis utilizes natural language processing technology and machine learning algorithms. Specifically, it extracts the skills and qualifications of job seekers and quantifies how well they match the job requirements as a relevance score.

[0615] Generating a candidate list:

[0616] Based on the suitability score, the server generates a list of candidates. This list is stored in a format that can be accessed later by the company's recruiters.

[0617] Creating and sending recruitment emails:

[0618] The terminal automatically creates a message based on the generated candidate list. Here, it uses individualized information to adopt a communication style tailored to the recipient job seeker. This email is sent automatically according to a schedule.

[0619] Response collection and sentiment analysis:

[0620] When a reply is received, the server analyzes its content in real time. Software for identifying emotions analyzes the recipient's response tone to determine whether it is positive or negative. This provides information to decide on further follow-up and strategic actions.

[0621] As a concrete example, consider a scenario where a hospital is trying to recruit nurses. Using this system, nurses with the necessary qualifications and experience can be automatically listed, and personalized recruitment emails can be sent quickly. If a positive response is detected, interviews can be scheduled promptly, allowing for more effective recruitment activities.

[0622] An example of a prompt might be: "Generate a list of job seekers with nursing qualifications and experience, prepare and send recruitment emails, analyze the email responses, and suggest the next steps."

[0623] This system is a powerful tool for companies to deepen their interaction with job seekers and develop effective recruitment strategies.

[0624] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0625] Step 1:

[0626] The server collects job postings and job seeker data from external data sources. Its inputs include raw data obtained from job portals and company databases. The server processes this data into a consistent format and outputs a unified dataset. During this process, it uses a database language to standardize different categories and make them comparable.

[0627] Step 2:

[0628] The server analyzes a unified dataset using natural language processing techniques. The input consists of job postings and job seeker data standardized in Step 1. The server extracts job seekers' skills and qualifications and calculates a suitability score with the job postings. The output is a quantified suitability score, which is used as a matching criterion. Machine learning algorithms are utilized in this process.

[0629] Step 3:

[0630] The server generates a candidate list based on the suitability score. The inputs are the suitability score calculated in step 2 and the job posting. The server prioritizes adding high-scoring job seekers to the list and outputs the optimal list of candidates for recruitment. This list is saved in a format accessible to the company's recruiters.

[0631] Step 4:

[0632] The terminal automatically creates the text for recruitment emails using the generated candidate list. The candidate list obtained in step 3 is used as input. The terminal generates text that includes individual candidate information and outputs personalized email messages. Specifically, information based on the job seeker's name and work history is incorporated into the text.

[0633] Step 5:

[0634] The server sends the generated recruitment emails according to a pre-set schedule. The input is the communication text generated in step 4. The server automatically sends it, ensuring it reaches job seekers at the time desired by the company. The output is the timely sent email.

[0635] Step 6:

[0636] The server aggregates email responses from recipients and performs sentiment analysis. The input is the content of the reply emails. The server uses natural language processing and sentiment analysis algorithms to identify emotions and analyze the tone of the responses. The output provides information indicating whether the emotion is positive, negative, or neutral.

[0637] Step 7:

[0638] The user decides on the next action based on the server's analysis results. The input is the sentiment analysis results obtained in step 6. Based on the tone of the email, the user makes strategic decisions such as proactive follow-up or scheduling an interview. The output is a concrete action taken for the next step in the recruitment process.

[0639] (Application Example 2)

[0640] Next, we will explain application example 2. In the following explanation, 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."

[0641] In modern digital communication, individuals and businesses send and receive a vast number of messages daily, some of which may contain fraud or spam. However, quickly identifying suspicious content from this large volume of messages and mitigating the associated risks is not easy. Furthermore, appropriately recognizing and responding to the tone of emotionally charged messages is also challenging. Therefore, to achieve safe and appropriate communication, technologies that simultaneously perform sentiment analysis and communication risk mitigation are required.

[0642] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0643] In this invention, the server includes means for collecting and standardizing job information data and job seeker data; means for analyzing the job information data and job seeker data and calculating a match score; and means for sentimentally analyzing the response content and calculating a sentiment score for the response. This makes it possible to evaluate the sentiment and content risks of messages in real time and to immediately issue warnings against suspicious communications.

[0644] "Job posting data" refers to information that includes details such as the type of job, skills, and work location that companies are looking for.

[0645] "Job seeker data" refers to personal information including the job seeker's name, experience, skills, and desired conditions.

[0646] "Means of standardization" refer to processes and technologies for converting data collected in different formats into a unified format.

[0647] "Means of analysis" refer to methods and techniques for analyzing information based on collected data and obtaining necessary insights.

[0648] The "match score" is an evaluation index that quantifies the compatibility between job postings and job seeker information.

[0649] The "Scout Target List" is a list of job seekers who are eligible for scouting, created based on their evaluated match score.

[0650] A "scout email" is an electronic message containing offers or information that companies send to job seekers they are interested in.

[0651] "Methods for automatic generation" refer to systems that use programs or algorithms to automatically create content based on specified conditions.

[0652] "Means for aggregating and analyzing responses" refers to the process of statistically summarizing received replies and analyzing trends and characteristics.

[0653] "Sentiment analysis" is a technology that identifies emotions and tone from text data and calculates an emotion score.

[0654] An "emotion score" is a numerical representation of the intensity and type of emotions contained in the text.

[0655] "Means for generating warnings or notifications" refers to functions that provide warnings or information to users when certain conditions are met.

[0656] This invention is implemented by a system mainly composed of three elements: a server, a terminal, and a user.

[0657] The server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. The standardized data is analyzed using natural language processing techniques and machine learning algorithms to calculate a match score between job postings and job seeker information. Based on this score, a list of potential candidates for recruitment is generated, and sentiment analysis is used to calculate sentiment scores for messages.

[0658] The terminal automatically generates personalized recruitment emails based on a list of potential candidates provided by the server. These emails contain information best suited to each candidate and can be reviewed and approved by the company's recruiters. After approval, the emails are automatically sent according to a specified schedule.

[0659] Users, i.e., corporate recruiters, can leverage the information provided by this system to conduct recruitment activities quickly and efficiently. The server performs real-time sentiment analysis of recipients' email responses and evaluates the tone of the response. This allows users to take swift and appropriate follow-up actions.

[0660] For example, if a company wants to recruit specialists for a new project, this system can be used to send personalized recruitment emails to candidates who meet the requirements. If the response is positively rated, an interview can be scheduled early on.

[0661] An example of a prompt used by a generative AI model would be, "Calculate the sentiment score of this message and check if it contains any suspicious content."

[0662] This system utilizes technologies such as Python, NLTK, and TensorFlow to enable advanced data analysis and sentiment analysis, supporting users' recruitment activities.

[0663] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0664] Step 1:

[0665] The server collects job postings and job seeker data from external data sources. Input is raw data obtained from each database, and output is data converted to a unified format. Specifically, it standardizes data in different formats into JSON format and performs data cleansing to prepare it for subsequent analysis.

[0666] Step 2:

[0667] The server uses natural language processing techniques to analyze standardized data and calculate a match score between job postings and job seeker information. The input is the standardized data generated in step 1, and the output is the match score. Specifically, it uses NLTK for keyword extraction and contextual analysis, and then performs scoring using a machine learning algorithm.

[0668] Step 3:

[0669] The server generates a list of potential candidates based on the calculated match score. The input is the match score obtained in step 2, and the output is a list of highly suitable job seekers. Specifically, a score threshold is set, and job seekers with a score above that threshold are selected.

[0670] Step 4:

[0671] The device automatically generates recruitment email text based on a list of potential recruits. The input is the list generated in step 3, and the output is a personalized recruitment email. Specifically, it uses a generation AI model based on a template to input prompt text and automatically creates the optimal text.

[0672] Step 5:

[0673] The user reviews the generated recruitment email text via their device and makes corrections as needed. The input is the email text created in step 4, and the output is the final email text reflecting the user's feedback. Specifically, an interface is provided that allows for easy editing of the email content via a GUI.

[0674] Step 6:

[0675] The server automatically sends the confirmed recruitment emails according to the specified schedule. The input is the email text confirmed in step 5, and the output is a notification that the email has been sent. Specifically, it works in conjunction with the mail server to send emails according to the schedule.

[0676] Step 7:

[0677] The server performs real-time sentiment analysis on responses to recruitment emails and calculates sentiment scores for each response. The input is the received email response, and the output is the analyzed sentiment score. Specifically, TensorFlow is used to analyze the received text and identify positive, negative, and neutral sentiments.

[0678] Step 8:

[0679] The user selects the next step based on their emotional score. The input is the emotional score obtained in step 7, and the output is the choice of the next action. Specifically, for example, if a positive emotion is detected, a strategy such as offering an interview opportunity might be adopted.

[0680] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0681] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0682] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0683] [Fourth Embodiment]

[0684] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0685] As shown in Figure 7, the 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.

[0686] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0687] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0688] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0689] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0690] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0691] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive 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 robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0692] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0693] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0694] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0695] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0696] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0697] This invention relates to an automated system that improves efficiency and speed in the recruitment process for personnel in the medical and welfare fields. The system is designed to allow companies to easily scout suitable personnel and is primarily operated using servers and terminals.

[0698] First, the server collects job postings and job seeker data from various data sources and standardizes them into an analyzable format. Next, the server uses natural language processing technology to analyze the job postings and job seeker profiles and calculates a match score to evaluate the suitability of both parties.

[0699] Based on this match score, the server generates a list of candidates to scout. Based on this list, the terminal automatically generates a recruitment email. The generated email includes a customized message tailored to each job seeker's background and experience, designed to maximize the effectiveness of the approach.

[0700] The recruiters at the companies using the service can review these automatically generated emails on their devices and edit them as needed. After final confirmation, the server sends the recruitment emails to the target candidates.

[0701] Furthermore, the server automatically aggregates and analyzes responses to sent emails. Users can view the response results in real time through their terminals and quickly take the next steps based on that information, such as scheduling an interview.

[0702] This system allows for the rapid and accurate connection of companies and job seekers while significantly reducing time and effort. For example, if a hospital in need of nurses uses this system, recruitment emails will be automatically sent to suitable nurse candidates, enabling efficient recruitment activities.

[0703] The following describes the processing flow.

[0704] Step 1:

[0705] The server collects job postings and job seeker data from external data sources and databases. This is done automatically via APIs, and the information includes job descriptions, required skills, experience, and work location.

[0706] Step 2:

[0707] The server standardizes the collected data into a unified format. This includes data cleaning and normalization. By preparing data from different sources to be comparable, the accuracy of the analysis can be improved.

[0708] Step 3:

[0709] The server analyzes standardized data using natural language processing techniques. This analysis calculates a match score to evaluate the degree of compatibility between each job seeker's profile and the job posting. This score is calculated based on the degree of match in skills, experience, and qualifications.

[0710] Step 4:

[0711] The server generates a list of potential candidates based on the calculated match score. The list prioritizes candidates who best match the company's requirements.

[0712] Step 5:

[0713] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails follow a template and are customized to be personalized according to the candidate's name and background information.

[0714] Step 6:

[0715] The user, who is the recruiter, can review the content of the recruitment email via their device. They can add or revise the content as needed and then give final approval.

[0716] Step 7:

[0717] The server, upon user approval, sends recruitment emails to the target recipients. The sending date, time, and frequency are optimized using a scheduling function.

[0718] Step 8:

[0719] The server automatically aggregates and analyzes responses to sent recruitment emails. Based on the content of the received responses, they are classified into categories such as "thank you," "not interested," and "request for additional information."

[0720] Step 9:

[0721] Users can view the aggregated response results through their terminals and quickly decide on their next action, such as scheduling a meeting appointment. Furthermore, the server continuously learns and improves the accuracy of its algorithms based on user feedback.

[0722] (Example 1)

[0723] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0724] In the modern medical and welfare fields, the recruitment process is often time-consuming and laborious. Companies are required to quickly find suitable personnel and contact them efficiently, but matching job openings with job seekers requires a tremendous amount of time and effort. Furthermore, personalizing email content and effectively delivering it to candidates to achieve a higher response rate is a challenge for companies. Therefore, the present invention aims to solve these problems and provide a system that enables appropriate and rapid talent scouting.

[0725] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0726] In this invention, the server includes means for storing job information data and job seeker data in a database, means for analyzing the job information data and job seeker data using natural language processing technology to calculate a match score, and means for adding candidates whose scores exceed a threshold to a list of candidates to be scouted. This enables accurate and efficient analysis of job information and job seeker data, and rapid scouting of suitable candidates. Furthermore, by including means for automatically generating scout email text using a generative AI model, and allowing users to review and edit this content, it becomes possible to realize personalized and effective recruiting communication.

[0727] "Job posting data" refers to data containing detailed information about job openings, including the required personnel conditions, job descriptions, and application requirements of companies.

[0728] "Job seeker data" refers to data containing information about individuals seeking employment, including their work history, skills, qualifications, and desired occupation.

[0729] A "database" is a collection of information that stores data in a structured format, allowing for efficient searching and management.

[0730] "Natural language processing technology" refers to technologies used to analyze, understand, and generate human language using computers, and is used for tasks such as text analysis and keyword extraction.

[0731] The "match score" is an index that quantifies the compatibility between job posting data and job seeker data, and is used to evaluate how well a job seeker matches the job requirements.

[0732] The "Scout Candidate List" is a list of candidates who have been selected based on their match score and are eligible to be scouted.

[0733] A "generative AI model" is a model that uses artificial intelligence and has the ability to generate text or data for a specific purpose.

[0734] A "prompt statement" is an instruction statement used to guide the operation of a generative AI model, and it plays a role in influencing the generated results.

[0735] This invention realizes an automated system that streamlines the recruitment process in the medical and welfare fields. The main components of the system include servers, terminals, and users who utilize them.

[0736] The server collects job postings and job seeker data using web scraping techniques and stores them in a database management system (e.g., PostgreSQL). This provides advanced accessibility and data management capabilities. The server standardizes the data using the Python pandas library, handling missing values ​​and adjusting data types. Using natural language processing techniques, the server analyzes this data and utilizes the NLTK or spaCy library to calculate a match score.

[0737] The terminal automatically generates recruitment emails using a generation AI model (e.g., OpenAI GPT) based on the list of potential recruits received from the server. An example of a prompt used in this process is the instruction, "Create a recruitment email template to send to new nursing candidates. The email should highlight the candidate's experience in the nursing field and appeal to their growth opportunities at the hospital."

[0738] Users can review and edit automatically generated recruitment emails via their devices. This allows for a personalized approach tailored to each job seeker. After a final check, the server sends the finalized recruitment email using the SMTP protocol.

[0739] Furthermore, the server aggregates responses to sent emails in real time and provides the analysis results to the user. This system supports recruiters in quickly scheduling interviews and conducting follow-up activities. Thus, the invention aims to expedite the recruitment process and efficiently connect companies with job seekers.

[0740] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0741] Step 1:

[0742] The server collects job postings and job seeker data from various job sites using web scraping techniques. It automatically crawls sites according to a specific schedule and extracts necessary information from HTML pages using BeautifulSoup. The input consists of multiple web pages, and the output is unstructured text data. This text data is in a preparatory stage before standardization.

[0743] Step 2:

[0744] The server converts the collected text data into a structured data format. It uses the Python pandas library to create a dataset, ensuring missing value imputation and data type consistency. The input is unstructured text data, and the output is in a format suitable for storage in a database. PostgreSQL is used as the storage destination.

[0745] Step 3:

[0746] The server analyzes stored job postings and job seeker data using natural language processing techniques. Using NLTK or spaCy, it extracts keywords and important phrases from the data and calculates a match score. This calculation uses an algorithm that evaluates text similarity. The input is structured data, and the output is the match score for each job seeker.

[0747] Step 4:

[0748] The server adds job seekers who exceed a certain threshold based on the calculated match score to a list of potential recruits. A decision tree algorithm is used to select candidates with high suitability based on the score. The input is the match score, and the output is a list of potential recruits.

[0749] Step 5:

[0750] The terminal automatically generates recruitment emails using an AI model based on a list of potential candidates. During this process, prompts such as "Generate a personalized message based on the job seeker's background" are provided. The input is a list of potential candidates, and the output is a customized recruitment email.

[0751] Step 6:

[0752] Users can review automatically generated recruitment emails via their devices and edit them as needed. They can modify content and adjust their approach using a browser-based editing interface. The input is the automatically generated email text, and the output is the final, reviewed email text.

[0753] Step 7:

[0754] The server sends the confirmed recruitment emails to each job seeker via the SMTP protocol. The input is the confirmed email text, and the output is the sent email. During this process, the email sending history is also recorded in the database.

[0755] Step 8:

[0756] The server aggregates and analyzes responses to sent emails in real time. It uses the pandas library to perform response rate and behavioral analysis, and saves the results to a database. The input is the received reply data, and the output is the analyzed response data.

[0757] Step 9:

[0758] Users review the analysis results via their device and proceed to the next recruitment step. For example, they might plan to quickly schedule interviews or initiate further communication. The input is the analyzed response data, and the output is the determined recruitment strategy.

[0759] (Application Example 1)

[0760] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0761] The recruitment process in the security field is complex and time-consuming, making it difficult to secure suitable personnel. In particular, recruiting personnel for nighttime or specialized work requires rapid and effective matching. This invention solves these problems, streamlining the recruitment process for security personnel and providing a means to quickly secure talent.

[0762] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0763] In this invention, the server includes means for collecting and standardizing employment information data and applicant information data, means for calculating suitability scores, and means for automatically generating message text according to the list of candidates to be selected. This makes it possible to support the recruitment process for personnel in the security field and to quickly secure suitable personnel.

[0764] "Employment information data" refers to information about job postings provided by companies and organizations, including details such as job title, job description, work location, working hours, and salary conditions.

[0765] "Applicant information data" refers to personal information about job seekers, as well as data such as work history, skills, and qualifications, which is used to determine their suitability for employment.

[0766] "Standardization" is the process of converting data with different forms and structures into a unified format, in order to facilitate analysis.

[0767] A "suitability score" is an index that quantifies the degree of compatibility between job postings and applicant information, and is used to evaluate the likelihood of hiring.

[0768] A "selection list" is a list compiled by a company based on suitability scores, listing candidates that it should consider scouting or interviewing.

[0769] "Automatically generating message text" means that the system automatically generates messages for individual applicants based on pre-configured templates, enabling efficient communication.

[0770] The "recruitment process for security personnel" refers to the entire process from searching for, selecting, and hiring individuals to engage in security work.

[0771] "Applications that can be installed on various devices" are software programs that can be downloaded and used on digital devices such as smartphones and tablets.

[0772] The system implementing this invention is a software program for companies to quickly and accurately select applicants in the security field and streamline the recruitment process. This program consists of a server and terminals, and a specific embodiment thereof is shown below.

[0773] The server first collects employment and applicant information data through the use of external databases and APIs. The collected data is then converted into an analyzable format through standardization. This standardization process includes filtering and format conversion to ensure data consistency.

[0774] Next, the server uses natural language processing technology to analyze employment information data and applicant information data. During this analysis, a suitability score is calculated, and a list of candidates for selection is generated based on this score. This list is optimized by the server's algorithm, enabling efficient talent selection.

[0775] Next, based on the list of selected candidates, the device automatically generates a message. In this process, individual information for each applicant is inserted into a template, creating a customized message. The generated message is then sent to the applicant via the application on the device.

[0776] The hardware used to run this system will be cloud servers (e.g., Amazon Web Services or Google Cloud Platform), which will handle the necessary computing and data storage. For software, Python libraries (e.g., NLTK or SpaCy) can be used for data analysis, and Flask or Django can be used as the UI platform.

[0777] As a concrete example, consider a company that needs personnel to handle nighttime security. This system collects relevant applicant information and automatically generates and sends messages to candidates who meet the hiring requirements. As a result, rapid and effective recruitment becomes possible.

[0778] Examples of prompts for the generating AI model include: "Calculate a suitability score for applicants suitable for the night security guard position based on the following requirements, and generate a customized email: flexibility in working hours, past security experience, and special skills."

[0779] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0780] Step 1:

[0781] The server collects employment and applicant information data from external databases and APIs. The input consists of raw data from multiple data sources. The server then performs data cleansing to convert this data into a consistent format and standardize it. This results in output data in a parseable format.

[0782] Step 2:

[0783] The server analyzes standardized employment and applicant data using natural language processing techniques. The input is standardized text data, and analysis is performed using a natural language processing library (e.g., SpaCy). This process quantifies the characteristics of job postings and applicant profiles and outputs a suitability score.

[0784] Step 3:

[0785] The server generates a list of candidates based on the calculated suitability score. The input is the suitability score, and the server's algorithm evaluates the score and lists candidates in descending order of suitability. As a result, a list of candidates to be scouted is output.

[0786] Step 4:

[0787] The terminal automatically generates message text based on the list of selected individuals. The input consists of the list of selected individuals and a template message. Personalized information is inserted into the template to output a customized message. Users can edit and review this message.

[0788] Step 5:

[0789] The server sends the generated message to the applicant. The generated message is used as input, and the transmission operation is performed using the SMTP protocol. As a result of the transmission, a transmission status is output, which may indicate a response has been received.

[0790] Step 6:

[0791] The server aggregates and analyzes responses from applicants. Using the received responses as input, an analysis algorithm evaluates their content and outputs recommendations for the next step (e.g., scheduling an interview). Users can then use the aggregated results to make quick hiring decisions.

[0792] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0793] This invention combines an emotion engine with an automated system that enables efficient scouting activities in the recruitment process for the medical and welfare sectors. The system aims to provide a deeper understanding of the interaction between companies and job seekers and to offer a personalized approach.

[0794] The system operates on a server-terminal basis. First, the server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. Next, the server analyzes the data using natural language processing technology and calculates a match score. Based on this score, it generates a list of optimal candidates for recruitment.

[0795] The device automatically generates recruitment emails based on the generated list of potential candidates. The emails include personalized information based on the candidate's name and background, facilitating more effective communication. Users, i.e., company recruiters, can review the emails via the device, make any necessary revisions, and then give final approval.

[0796] The server automatically sends approved emails according to a specified schedule. Furthermore, it uses an emotion engine to analyze recipient email responses in real time. The server leverages natural language processing and machine learning algorithms to identify the emotions expressed in the responses. Based on these results, users can then select the next steps, such as customized follow-up emails or interview approaches.

[0797] For example, if a hospital wants to hire nurses, this system can be used to automatically send recruitment emails to nurse candidates whose qualifications and experience meet the requirements. If the emotion engine identifies the response as positive, the system can quickly take more effective steps, such as proactively scheduling an interview. In this way, companies can conduct recruitment activities efficiently and precisely.

[0798] The following describes the processing flow.

[0799] Step 1:

[0800] The server automatically collects job postings and job seeker data from external databases. The data includes detailed information such as job title, skills, location, and salary.

[0801] Step 2:

[0802] The server standardizes the collected data into a unified format. Irrelevant information is removed, and the format is standardized to prepare the data for analysis.

[0803] Step 3:

[0804] The server analyzes standardized data using natural language processing techniques. This analysis compares job requirements with the skills and experience of job seekers to calculate a match score. This score is used to evaluate which job seeker is the best fit for the job posting.

[0805] Step 4:

[0806] The server generates a list of potential candidates based on the calculated match score. This list prioritizes candidates who best match the company's requirements.

[0807] Step 5:

[0808] The device uses AI to automatically generate recruitment emails based on a list of potential candidates. The emails are customized to match the job seeker's name and past experience.

[0809] Step 6:

[0810] The user reviews the generated recruitment email text via their device and edits it as needed. After final confirmation, the user approves sending the email.

[0811] Step 7:

[0812] The server sends recruitment emails to target individuals after receiving user approval. Sending is done according to an optimized schedule.

[0813] Step 8:

[0814] The server uses an emotion engine to analyze responses to recruitment emails. It uses natural language processing and machine learning to determine the user's emotions from the received responses. This analysis identifies whether the response is positive or negative.

[0815] Step 9:

[0816] Users can view the analysis results from the emotion engine via their device and decide on their next action based on the response. For example, if they receive a positive response, they can quickly take appropriate action, such as scheduling a meeting.

[0817] (Example 2)

[0818] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0819] A smooth matching process between job postings and job seekers is a crucial element in efficient recruitment. However, for companies, finding the right candidates with the required qualifications and experience from a large amount of data remains a time-consuming and resource-intensive task. Furthermore, personalizing recruitment emails for effective communication is also challenging. To address these challenges, there is a need for a system that automates the recruitment process and provides follow-up strategies through sentiment analysis.

[0820] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0821] In this invention, the server includes means for collecting job information data and job seeker data and converting them into a unified format; means for analyzing the job information data and job seeker data and calculating a suitability score; and means for generating a candidate list based on the suitability score. This makes it possible to quickly and accurately identify suitable personnel from a large amount of information and to efficiently personalize subsequent communication.

[0822] "Job posting data" refers to data provided by employers that includes details about the job, required skills, experience, salary range, and other relevant information.

[0823] "Job seeker data" refers to data that represents information provided by job seekers, including their personal work history, skills, qualifications, and desired conditions.

[0824] A "unified format" refers to a state where data acquired in different formats is converted into a consistent format, making comparison and analysis easier.

[0825] A "fit score" is an evaluation index that quantifies the compatibility between job postings and job seekers based on their information.

[0826] A "candidate list" refers to a set of job seekers selected based on their suitability score who best match a specific job opening.

[0827] "Communication text" refers to the content of emails or messages sent for the purpose of communicating with job seekers.

[0828] "Personalized information" refers to content that includes details based on an individual's name and professional background, tailored to a specific recipient.

[0829] "Identifying emotions" means analyzing the emotional tone of a recipient's response and classifying it into categories such as positive, negative, or neutral.

[0830] "Language analysis technology" refers to techniques that use natural language processing and machine learning to analyze text data and understand its meaning and intent.

[0831] The system of the present invention operates on a server and terminal basis and aims to streamline the personnel recruitment process in the medical and welfare fields. The following describes embodiments of this system.

[0832] Data collection and standardization:

[0833] The server first collects job postings and job seeker data from external data sources. This includes various job portals and company databases. Since the collected data may be in different formats, the server converts the data into a unified format. In this process, database languages ​​are used to organize the data and create a consistent dataset.

[0834] Data analysis and scoring:

[0835] Next, the server uses language analysis technology to analyze job seekers and job postings. This analysis utilizes natural language processing technology and machine learning algorithms. Specifically, it extracts the skills and qualifications of job seekers and quantifies how well they match the job requirements as a relevance score.

[0836] Generating a candidate list:

[0837] Based on the suitability score, the server generates a list of candidates. This list is stored in a format that can be accessed later by the company's recruiters.

[0838] Creating and sending recruitment emails:

[0839] The terminal automatically creates a message based on the generated candidate list. Here, it uses individualized information to adopt a communication style tailored to the recipient job seeker. This email is sent automatically according to a schedule.

[0840] Response collection and sentiment analysis:

[0841] When a reply is received, the server analyzes its content in real time. Software for identifying emotions analyzes the recipient's response tone to determine whether it is positive or negative. This provides information to decide on further follow-up and strategic actions.

[0842] As a concrete example, consider a scenario where a hospital is trying to recruit nurses. Using this system, nurses with the necessary qualifications and experience can be automatically listed, and personalized recruitment emails can be sent quickly. If a positive response is detected, interviews can be scheduled promptly, allowing for more effective recruitment activities.

[0843] An example of a prompt might be: "Generate a list of job seekers with nursing qualifications and experience, prepare and send recruitment emails, analyze the email responses, and suggest the next steps."

[0844] This system is a powerful tool for companies to deepen their interaction with job seekers and develop effective recruitment strategies.

[0845] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0846] Step 1:

[0847] The server collects job postings and job seeker data from external data sources. Its inputs include raw data obtained from job portals and company databases. The server processes this data into a consistent format and outputs a unified dataset. During this process, it uses a database language to standardize different categories and make them comparable.

[0848] Step 2:

[0849] The server analyzes a unified dataset using natural language processing techniques. The input consists of job postings and job seeker data standardized in Step 1. The server extracts job seekers' skills and qualifications and calculates a suitability score with the job postings. The output is a quantified suitability score, which is used as a matching criterion. Machine learning algorithms are utilized in this process.

[0850] Step 3:

[0851] The server generates a candidate list based on the suitability score. The inputs are the suitability score calculated in step 2 and the job posting. The server prioritizes adding high-scoring job seekers to the list and outputs the optimal list of candidates for recruitment. This list is saved in a format accessible to the company's recruiters.

[0852] Step 4:

[0853] The terminal automatically creates the text for recruitment emails using the generated candidate list. The candidate list obtained in step 3 is used as input. The terminal generates text that includes individual candidate information and outputs personalized email messages. Specifically, information based on the job seeker's name and work history is incorporated into the text.

[0854] Step 5:

[0855] The server sends the generated recruitment emails according to a pre-set schedule. The input is the communication text generated in step 4. The server automatically sends it, ensuring it reaches job seekers at the time desired by the company. The output is the timely sent email.

[0856] Step 6:

[0857] The server aggregates email responses from recipients and performs sentiment analysis. The input is the content of the reply emails. The server uses natural language processing and sentiment analysis algorithms to identify emotions and analyze the tone of the responses. The output provides information indicating whether the emotion is positive, negative, or neutral.

[0858] Step 7:

[0859] The user decides on the next action based on the server's analysis results. The input is the sentiment analysis results obtained in step 6. Based on the tone of the email, the user makes strategic decisions such as proactive follow-up or scheduling an interview. The output is a concrete action taken for the next step in the recruitment process.

[0860] (Application Example 2)

[0861] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0862] In modern digital communication, individuals and businesses send and receive a vast number of messages daily, some of which may contain fraud or spam. However, quickly identifying suspicious content from this large volume of messages and mitigating the associated risks is not easy. Furthermore, appropriately recognizing and responding to the tone of emotionally charged messages is also challenging. Therefore, to achieve safe and appropriate communication, technologies that simultaneously perform sentiment analysis and communication risk mitigation are required.

[0863] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0864] In this invention, the server includes means for collecting and standardizing job information data and job seeker data; means for analyzing the job information data and job seeker data and calculating a match score; and means for sentimentally analyzing the response content and calculating a sentiment score for the response. This makes it possible to evaluate the sentiment and content risks of messages in real time and to immediately issue warnings against suspicious communications.

[0865] "Job posting data" refers to information that includes details such as the type of job, skills, and work location that companies are looking for.

[0866] "Job seeker data" refers to personal information including the job seeker's name, experience, skills, and desired conditions.

[0867] "Means of standardization" refer to processes and technologies for converting data collected in different formats into a unified format.

[0868] "Means of analysis" refer to methods and techniques for analyzing information based on collected data and obtaining necessary insights.

[0869] The "match score" is an evaluation index that quantifies the compatibility between job postings and job seeker information.

[0870] The "Scout Target List" is a list of job seekers who are eligible for scouting, created based on their evaluated match score.

[0871] A "scout email" is an electronic message containing offers or information that companies send to job seekers they are interested in.

[0872] "Methods for automatic generation" refer to systems that use programs or algorithms to automatically create content based on specified conditions.

[0873] "Means for aggregating and analyzing responses" refers to the process of statistically summarizing received replies and analyzing trends and characteristics.

[0874] "Sentiment analysis" is a technology that identifies emotions and tone from text data and calculates an emotion score.

[0875] An "emotion score" is a numerical representation of the intensity and type of emotions contained in the text.

[0876] "Means for generating warnings or notifications" refers to functions that provide warnings or information to users when certain conditions are met.

[0877] This invention is implemented by a system mainly composed of three elements: a server, a terminal, and a user.

[0878] The server automatically collects job postings and job seeker data from external data sources and standardizes them into a unified format. The standardized data is analyzed using natural language processing techniques and machine learning algorithms to calculate a match score between job postings and job seeker information. Based on this score, a list of potential candidates for recruitment is generated, and sentiment analysis is used to calculate sentiment scores for messages.

[0879] The terminal automatically generates personalized recruitment emails based on a list of potential candidates provided by the server. These emails contain information best suited to each candidate and can be reviewed and approved by the company's recruiters. After approval, the emails are automatically sent according to a specified schedule.

[0880] Users, i.e., corporate recruiters, can leverage the information provided by this system to conduct recruitment activities quickly and efficiently. The server performs real-time sentiment analysis of recipients' email responses and evaluates the tone of the response. This allows users to take swift and appropriate follow-up actions.

[0881] For example, if a company wants to recruit specialists for a new project, this system can be used to send personalized recruitment emails to candidates who meet the requirements. If the response is positively rated, an interview can be scheduled early on.

[0882] An example of a prompt used by a generative AI model would be, "Calculate the sentiment score of this message and check if it contains any suspicious content."

[0883] This system utilizes technologies such as Python, NLTK, and TensorFlow to enable advanced data analysis and sentiment analysis, supporting users' recruitment activities.

[0884] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0885] Step 1:

[0886] The server collects job postings and job seeker data from external data sources. Input is raw data obtained from each database, and output is data converted to a unified format. Specifically, it standardizes data in different formats into JSON format and performs data cleansing to prepare it for subsequent analysis.

[0887] Step 2:

[0888] The server uses natural language processing techniques to analyze standardized data and calculate a match score between job postings and job seeker information. The input is the standardized data generated in step 1, and the output is the match score. Specifically, it uses NLTK for keyword extraction and contextual analysis, and then performs scoring using a machine learning algorithm.

[0889] Step 3:

[0890] The server generates a list of potential candidates based on the calculated match score. The input is the match score obtained in step 2, and the output is a list of highly suitable job seekers. Specifically, a score threshold is set, and job seekers with a score above that threshold are selected.

[0891] Step 4:

[0892] The device automatically generates recruitment email text based on a list of potential recruits. The input is the list generated in step 3, and the output is a personalized recruitment email. Specifically, it uses a generation AI model based on a template to input prompt text and automatically creates the optimal text.

[0893] Step 5:

[0894] The user reviews the generated recruitment email text via their device and makes corrections as needed. The input is the email text created in step 4, and the output is the final email text reflecting the user's feedback. Specifically, an interface is provided that allows for easy editing of the email content via a GUI.

[0895] Step 6:

[0896] The server automatically sends the confirmed recruitment emails according to the specified schedule. The input is the email text confirmed in step 5, and the output is a notification that the email has been sent. Specifically, it works in conjunction with the mail server to send emails according to the schedule.

[0897] Step 7:

[0898] The server performs real-time sentiment analysis on responses to recruitment emails and calculates sentiment scores for each response. The input is the received email response, and the output is the analyzed sentiment score. Specifically, TensorFlow is used to analyze the received text and identify positive, negative, and neutral sentiments.

[0899] Step 8:

[0900] The user selects the next step based on their emotional score. The input is the emotional score obtained in step 7, and the output is the choice of the next action. Specifically, for example, if a positive emotion is detected, a strategy such as offering an interview opportunity might be adopted.

[0901] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0902] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0903] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0904] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0905] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0906] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0907] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0908] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0909] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0910] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0911] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0912] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0913] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0914] 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.

[0915] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0916] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0917] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0918] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0919] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0920] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0921] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0922] The following is further disclosed regarding the embodiments described above.

[0923] (Claim 1)

[0924] A means of collecting and standardizing job posting data and job seeker data,

[0925] A means for analyzing the aforementioned job information data and job seeker data and calculating a match score,

[0926] A means for generating a list of scout targets based on the aforementioned match score,

[0927] A means for automatically generating a scouting email message corresponding to the aforementioned list of potential scouts,

[0928] The means for sending the aforementioned scout email,

[0929] A means for aggregating and analyzing responses to the aforementioned scout emails,

[0930] A system that includes this.

[0931] (Claim 2)

[0932] The system according to claim 1, characterized in that the means for calculating the match score uses natural language processing technology to analyze job posting data and job seeker data.

[0933] (Claim 3)

[0934] The system according to claim 1, characterized in that it includes personalized information when customizing the text of the recruitment email.

[0935] "Example 1"

[0936] (Claim 1)

[0937] A means of collecting job posting data and job seeker data and storing it in a database,

[0938] A means for analyzing the aforementioned job information data and job seeker data using natural language processing technology and calculating a match score,

[0939] A means for adding candidates whose scores exceed a threshold to the list of scouts, based on the aforementioned match score,

[0940] A means for automatically generating recruitment email text corresponding to the aforementioned list of potential recruits using an AI model,

[0941] Means for providing an interface that allows the user to review and edit the generated scout email text,

[0942] The means for sending the confirmed scout email,

[0943] A means for collecting and analyzing responses to the aforementioned scout emails in real time,

[0944] A system that includes this.

[0945] (Claim 2)

[0946] The system according to claim 1, characterized in that it uses natural language processing technology to extract important keywords and phrases when analyzing the aforementioned job information data and job seeker data.

[0947] (Claim 3)

[0948] The system according to claim 1, characterized in that when generating the aforementioned recruitment email text, it includes personalized information based on the job seeker's background using prompt text.

[0949] "Application Example 1"

[0950] (Claim 1)

[0951] Means for collecting and standardizing employment information data and applicant information data,

[0952] A means for analyzing the aforementioned employment information data and applicant information data and calculating a suitability score,

[0953] A means for generating a list of candidates to be selected based on the aforementioned suitability score,

[0954] A means for automatically generating message text corresponding to the aforementioned list of selected individuals,

[0955] means for sending the aforementioned message,

[0956] A means for aggregating and analyzing the responses to the aforementioned message,

[0957] To support the recruitment process for personnel in the security field, a means of providing applications that can be installed on various devices,

[0958] A system that includes this.

[0959] (Claim 2)

[0960] The system according to claim 1, characterized in that the means for calculating the suitability score uses natural language processing technology to analyze employment information data and applicant information data.

[0961] (Claim 3)

[0962] The system according to claim 1, characterized in that it includes personalized information when customizing the message text.

[0963] "Example 2 of combining an emotion engine"

[0964] (Claim 1)

[0965] A means for collecting job posting data and job seeker data and converting them into a standardized format,

[0966] A means for analyzing the aforementioned job information data and job seeker data and calculating a goodness-of-fit score,

[0967] Means for generating a list of candidates based on the aforementioned suitability score,

[0968] A means for automatically generating a communication message based on the aforementioned list of candidates,

[0969] means for transmitting the aforementioned message,

[0970] A means for aggregating the responses to the aforementioned communication and analyzing them to identify emotions,

[0971] A system that includes this.

[0972] (Claim 2)

[0973] The system according to claim 1, characterized in that the means for calculating the suitability score uses language analysis technology to analyze job posting data and job seeker data.

[0974] (Claim 3)

[0975] The system according to claim 1, characterized in that it includes individualized information when customizing the aforementioned communication text.

[0976] "Application example 2 when combining with an emotional engine"

[0977] (Claim 1)

[0978] A means of collecting and standardizing job posting data and job seeker data,

[0979] A means for analyzing the aforementioned job information data and job seeker data and calculating a match score,

[0980] A means for generating a list of scout targets based on the aforementioned match score,

[0981] A means for automatically generating a scouting email message corresponding to the aforementioned list of potential scouts,

[0982] The means for sending the aforementioned scout email,

[0983] A means for aggregating and analyzing responses to the aforementioned scout emails,

[0984] A means for performing emotional analysis on the response content and calculating an emotional score for the response,

[0985] Means for generating a warning or notification based on the aforementioned sentiment score,

[0986] A system that includes this.

[0987] (Claim 2)

[0988] The system according to claim 1, characterized in that the means for calculating the match score uses natural language processing technology to analyze job posting data and job seeker data.

[0989] (Claim 3)

[0990] The system according to claim 1, characterized in that it includes personalized information when customizing the text of the recruitment email. [Explanation of Symbols]

[0991] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of collecting and standardizing job posting data and job seeker data, A means for analyzing the aforementioned job information data and job seeker data and calculating a match score, A means for generating a list of scout targets based on the aforementioned match score, A means for automatically generating a scouting email message corresponding to the aforementioned list of potential scouts, The means for sending the aforementioned scout email, A means for aggregating and analyzing responses to the aforementioned scout emails, A system that includes this.

2. The system according to claim 1, wherein the means for calculating the match score is characterized by using natural language processing technology to analyze job posting data and job seeker data.

3. The system according to claim 1, characterized in that it includes personalized information when customizing the text of the recruitment email.

Images