system

Abstract

The system according to this embodiment aims to create attractive job postings at low cost and to provide appropriate follow-up. [Solution] The system according to the embodiment comprises a data extraction unit, a job posting information generation unit, and a follow-up unit. The data extraction unit extracts the attractiveness of companies. The job posting information generation unit generates job postings based on the information extracted by the data extraction unit. The follow-up unit delivers follow-up messages based on the job postings generated by the job posting information generation unit.

Description

Technical Field

[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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult to create attractive job offers at a low cost and perform appropriate follow-up. <00​​​​​​​​The system according to this embodiment comprises a data extraction unit, a job posting information generation unit, and a follow-up unit. The data extraction unit extracts the attractiveness of companies. The job posting information generation unit generates job postings based on the information extracted by the data extraction unit. The follow-up unit delivers follow-up messages based on the job postings generated by the job posting information generation unit. [Effects of the Invention]

[0007] The system according to this embodiment can create attractive job postings at low cost and provide appropriate follow-up. [Brief explanation of the drawing]

[0008] [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. [Modes for carrying out the invention]

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0010] First, let's explain the terminology used in the following explanation.

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0014] In the following embodiments, the labeled communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The regional job posting generation system according to an embodiment of the present invention is a system that solves the problem of labor shortages in rural areas by generating regional job postings at low cost using a generation AI and providing appropriate follow-up to job seekers. The regional job posting generation system uses the generation AI to converse with company recruiters and articulate the company's appeal. In this process, the generation AI conducts interviews with recruiters and extracts the company's appeal that even the recruiters themselves may not be aware of. This makes it possible to generate attractive job postings with virtually no costs for interviews or writing. For example, job postings are generated that specifically describe the company's strengths, ease of work, and growth opportunities. Next, a follow-up generation AI operates on a messaging app. By building the service on a messaging app, user IDs and users' job-seeking conditions are linked. The generation AI determines the access status of each user and delivers follow-up messages at the appropriate time. This eliminates the need for knowledge or experience for service operators and minimizes operational costs. For example, if a job seeker shows interest in a particular job posting, the generation AI sends additional information related to that job posting and application reminders. Furthermore, this system can be deployed to many regions. Many regions and municipalities are facing the challenge of industrial decline due to labor shortages, making the need for such a system extremely high. Because it is low-cost and requires no special skills to operate, it can be easily adopted by local businesses and municipalities. Furthermore, as it is an intermediary rather than a recruitment service, the licensing hurdles are low. This system allows job site operators to create attractive job postings at low cost, and makes it easier for companies to acquire talented personnel. Job seekers can more easily find jobs that suit them, and municipalities can increase the number of migrants. For example, a local small or medium-sized enterprise could use AI to create job postings and follow up with job seekers via a messaging app, thereby securing talented personnel and revitalizing local industries. Thus, a regional job posting generation system utilizing AI is expected to solve the labor shortage problem in rural areas and contribute to regional revitalization.

[0029] The regional job information generation system according to this embodiment comprises a data extraction unit, a job information generation unit, and a follow-up unit. The data extraction unit extracts the appeal of companies. For example, the data extraction unit engages in conversation with company recruiters to extract the appeal of companies. Using a generation AI, the data extraction unit can conduct interviews with company recruiters to extract specific information about the company's strengths, ease of work, and growth opportunities. For example, the data extraction unit can ask company recruiters, "What are your company's strengths?" to extract the company's appeal. The data extraction unit can also extract appeals that company recruiters are unaware of. For example, the data extraction unit can ask company recruiters, "Do you provide an environment where employees can work comfortably?" to extract the company's appeal. The job information generation unit generates job information based on the information extracted by the data extraction unit. The job information generation unit uses a generation AI to generate job information that specifically describes the appeal of companies. For example, the job information generation unit generates job information that specifically describes the company's strengths, ease of work, and growth opportunities. The job information generation unit can also use a generation AI to adjust the way the job information is presented. For example, the job posting generation unit adds detailed descriptions to emphasize the company's appeal. The follow-up unit delivers follow-up messages based on the job postings generated by the job posting generation unit. The follow-up unit uses generation AI to link user IDs with job search conditions, determines each user's access status, and delivers follow-up messages at the appropriate time. For example, if a job seeker shows interest in a particular job posting, the follow-up unit sends additional information related to that job posting and application reminders. Furthermore, the follow-up unit does not require any knowledge or experience from the service operator, minimizing operational costs. For example, the follow-up unit uses generation AI to analyze the job seeker's access status in real time and deliver follow-up messages at the appropriate time. As a result, the regional job posting generation system according to this embodiment can create and deliver job postings effectively and at low cost by highlighting the company's appeal, generating job postings, and delivering follow-up messages.

[0030] The extraction unit extracts the company's appeal. Specifically, the extraction unit engages in direct conversations with company recruiters to gather information on the company's strengths, work environment, and growth opportunities. Generative AI plays a crucial role in this process. Generative AI asks recruiters specific questions using pre-set prompts. For example, it extracts the company's appeal through questions such as, "What are your company's strengths?" or "Do you provide a comfortable working environment for employees?" The generative AI can analyze the recruiter's answers in real time and automatically generate further in-depth questions. This makes it possible to extract appeals and strengths that recruiters may not have been aware of. Furthermore, the extraction unit analyzes the company's past job postings and employee feedback to evaluate the company's appeal from multiple perspectives. For example, it can gain a concrete understanding of the company's work environment and growth opportunities based on employee satisfaction surveys and turnover rate data. As a result, the extraction unit can comprehensively extract the company's appeal and collect high-quality data to provide to the job posting generation unit.

[0031] The job posting generation unit generates job postings based on the information extracted by the data extraction unit. By using generation AI, it can automatically create job postings that specifically describe the attractiveness of a company. For example, it can generate attractive job postings for job seekers by describing in detail the company's strengths, work environment, and growth opportunities. The generation AI can use natural language processing technology to adjust the expression to emphasize the company's attractiveness. For example, it can add specific examples and data to highlight the company's strengths. The generation AI can also automatically generate catchy phrases and headlines to attract the attention of job seekers. Furthermore, the job posting generation unit can output the generated job postings in multiple formats. For example, it can generate job postings compatible with various media, such as HTML format for websites and PDF format for printing. As a result, the job posting generation unit can provide job postings that maximize the attractiveness of companies and effectively appeal to job seekers.

[0032] The Follow-Up Department delivers follow-up messages based on job postings generated by the Job Posting Generation Department. Using generation AI, it can link user IDs with job search criteria and analyze user access in real time. For example, if a job seeker shows interest in a particular job posting, it automatically sends additional information related to that posting and application reminders. The generation AI analyzes the job seeker's behavior history and access patterns to deliver follow-up messages at the optimal time. For example, if a job seeker views a job posting but does not apply after a certain period, it sends a reminder message. Furthermore, the Follow-Up Department can collect feedback from job seekers and continuously improve the content of job postings and the effectiveness of follow-up messages. For example, it can review the wording of job postings and the content of follow-up messages based on feedback from job seekers. In addition, the Follow-Up Department can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information using not only smartphone notifications but also voice calls, SMS, and email. This allows the Follow-Up Department to provide job seekers with quick and reliable follow-up messages, improving the application rate.

[0033] The information extraction unit can converse with company recruiters and extract information about the company's appeal. For example, the information extraction unit can converse with company recruiters face-to-face to extract information about the company. Alternatively, the information extraction unit can converse with company recruiters via telephone or chatbot to extract information about the company's appeal. For example, the information extraction unit can ask a company recruiter by phone, "What are your company's strengths?" to extract information about the company. Alternatively, the information extraction unit can use a chatbot to ask a company recruiter, "Do you provide a comfortable working environment for employees?" to extract information about the company's appeal. In this way, the information extraction unit can effectively extract information about the company's appeal through conversations with company recruiters. Some or all of the above processing in the information extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information extraction unit can input the content of the conversation with a company recruiter into a generative AI, which can then generate questions to extract information about the company's appeal.

[0034] The follow-up unit can link user IDs and job search criteria on the messaging app, determine each user's access status, and deliver follow-up messages at the appropriate time. For example, the follow-up unit can link user IDs and job search criteria on the messaging app. For example, when a user logs into the messaging app, the follow-up unit can automatically link user IDs and job search criteria. The follow-up unit can also determine each user's access status and deliver follow-up messages at the appropriate time. For example, when a user accesses a specific job posting, the follow-up unit will deliver a follow-up message related to that job posting. The follow-up unit can also deliver a reminder message if a user has not accessed the app for a certain period of time. This allows for the effective provision of job information by determining each user's access status and delivering follow-up messages at the appropriate time. Some or all of the above processing in the follow-up unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the follow-up unit can input user access status data into a generation AI, which can then generate follow-up messages at the appropriate time.

[0035] The follow-up unit can send additional information and application reminders related to a job posting when a job seeker shows interest in that posting. For example, when a job seeker accesses a specific job posting, the follow-up unit can send additional information related to that posting. For example, when a job seeker accesses a specific job posting, the follow-up unit can send detailed information about the company related to that posting. The follow-up unit can also send application reminders when a job seeker shows interest in a specific job posting. For example, when a job seeker shows interest in a specific job posting, the follow-up unit can send a message reminding them of the application deadline. The follow-up unit can also send interview tips related to a specific job posting when a job seeker shows interest in that posting. This helps maintain the job seeker's interest and encourages applications by sending them additional relevant information and application reminders when they show interest in a specific job posting. Some or all of the above processing in the follow-up unit may be performed using generative AI or not. For example, the follow-up unit can input job seeker access data into a generating AI, which can then generate relevant additional information and application reminders.

[0036] The follow-up department requires no knowledge or experience from service operators, minimizing operational costs. For example, the follow-up department uses generative AI to analyze job seekers' access patterns in real time and deliver follow-up messages at the appropriate time. This allows service operators to perform effective follow-up without special knowledge or experience. For instance, the follow-up department's generative AI automatically analyzes job seekers' access patterns and generates follow-up messages at the optimal time. Furthermore, the follow-up department can use generative AI to generate customized messages based on job seekers' interests. This allows service operators to perform effective follow-up with job seekers without significant effort. Additionally, the follow-up department can use generative AI to collect job seeker feedback and use it to improve the service. For example, the follow-up department's generative AI analyzes job seeker feedback and suggests areas for service improvement. This eliminates the need for knowledge or experience from service operators and minimizes operational costs. Some or all of the above-described processes in the follow-up department may be performed using generative AI, or they may not. For example, the follow-up unit can input data on job seekers' access status into a generating AI, which can then generate the most appropriate follow-up message.

[0037] The information extraction unit can analyze the recruiter's past response history and select the most appropriate questions. For example, the extraction unit may revisit questions that the recruiter has answered in detail in the past. For instance, it might ask the recruiter, "Could you tell me more about the project you discussed in our last interview?" The extraction unit can also avoid questions that the recruiter has avoided in the past. For example, it avoids questions that the recruiter did not want to answer in the past. The extraction unit can also ask questions related to topics that the recruiter has shown interest in in the past. For example, it asks questions related to topics that the recruiter has shown interest in in the past. By analyzing the recruiter's past response history, the extraction unit can select the most appropriate questions and effectively extract information. Some or all of the above processing in the information extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the extraction unit can input the recruiter's past response data into a generative AI, which can then generate the most appropriate questions.

[0038] The information extraction unit can generate specialized questions based on the recruiter's industry knowledge and experience. For example, if the recruiter has experience in the IT industry, the extraction unit can ask questions about the latest technology trends. For instance, it might ask the recruiter, "What technology trends are you currently paying attention to?" Similarly, if the recruiter has experience in manufacturing, the extraction unit can ask questions about production efficiency. For example, it might ask the recruiter, "What are you doing to improve production efficiency?" Furthermore, if the recruiter has experience in marketing, the extraction unit can ask questions about effective promotional strategies. For example, it might ask the recruiter, "What is a recent promotional strategy that has been successful?" This allows for effective information extraction by generating specialized questions based on the recruiter's industry knowledge and experience. Some or all of the above processing in the information extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can input the recruiter's industry knowledge and experience data into a generation AI, which can then generate specialized questions.

[0039] The information extraction unit can take into account the geographical location of the recruiter and ask questions that highlight the unique appeal of the region. For example, if the recruiter is in a rural area, the information extraction unit can ask questions about the local specialties and tourist attractions. For instance, it might ask the recruiter, "Please tell me about the local specialties and tourist attractions in this region." If the recruiter is in an urban area, the information extraction unit can also ask questions about the convenience and infrastructure of the city. For example, it might ask the recruiter, "Please tell me about the convenience and infrastructure of this city." Furthermore, if the recruiter is overseas, the information extraction unit can ask questions about the culture and business practices of that country. For example, it might ask the recruiter, "Please tell me about the culture and business practices of this country." By considering the geographical location of the recruiter, the information extraction unit can effectively highlight the unique appeal of the region. Some or all of the above processing in the information extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information extraction unit can input the recruiter's geographical location data into a generative AI, which can then generate questions that highlight the unique appeal of the region.

[0040] The information extraction unit can analyze the social media activity of recruiters and generate relevant questions. For example, the extraction unit might ask a recruiter, "What are your thoughts on the article you recently shared?" The extraction unit can also ask questions based on what recruiters have said on social media. For example, it might ask a recruiter, "Tell me more about your recent tweets." The extraction unit can also ask questions based on the groups recruiters participate in on social media. For example, it might ask a recruiter, "Tell me about your activities in the groups you participate in." By analyzing the recruiter's social media activity, it is possible to generate relevant questions and effectively extract information. Some or all of the above processing in the information extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can input the recruiter's social media activity data into a generation AI, which can then generate relevant questions.

[0041] The job posting generation unit can adjust the level of detail based on the company's key characteristics when generating job postings. For example, the job posting generation unit can add detailed descriptions to emphasize a company's strengths. For instance, it might list "high technical capabilities" as a company strength and add a detailed explanation. Conversely, it can also keep descriptions concise to downplay a company's weaknesses. For example, it might list "limited experience in launching new businesses" as a weakness and keep the explanation brief. The job posting generation unit can also add specific examples to emphasize a company's growth opportunities. For example, it might list "entering new markets" as a growth opportunity and add specific examples. By adjusting the level of detail based on a company's key characteristics, it becomes possible to generate effective job postings. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the job posting generation unit can input company characteristic data into a generation AI, which can then generate job postings with adjusted levels of detail.

[0042] The job posting generation unit can apply different generation algorithms depending on the industry and size of the company when generating job postings. For example, in the case of large companies, the job posting generation unit can add information about detailed organizational structure and employee benefits. For instance, the job posting generation unit might include "detailed organizational structure" and "generous employee benefits" in the job postings of large companies. The job posting generation unit can also emphasize information about flexible working arrangements and growth opportunities in the case of small and medium-sized enterprises (SMEs). For example, the job posting generation unit might include "flexible working arrangements" and "growth opportunities" in the job postings of SMEs. Furthermore, the job posting generation unit can also emphasize information about innovation and a challenging spirit in the case of startups. For example, the job posting generation unit might include "innovation" and "challenging spirit" in the job postings of startups. By applying different generation algorithms depending on the industry and size of the company, it becomes possible to generate effective job postings. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the job posting generation unit can input data on a company's industry and size into a generation AI, which then applies an appropriate generation algorithm to generate job postings.

[0043] The job posting generation unit can prioritize information based on the company's founding date when generating job postings. For example, in the case of a startup, the job posting generation unit can emphasize growth opportunities and innovation. For instance, it might include "growth opportunities" and "innovation" in the job postings for a startup. Similarly, in the case of an established company, the job posting generation unit can emphasize stability and reliability. For example, it might include "stability" and "reliability" in the job postings for an established company. Furthermore, in the case of a mid-sized company, the job posting generation unit can provide balanced information. For example, it might include "balanced job responsibilities" and "growth opportunities" in the job postings for a mid-sized company. This allows for the generation of effective job postings by prioritizing information based on the company's founding date. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the job posting generation unit can input company founding date data into a generation AI, which can then prioritize information and generate job postings.

[0044] The job posting generation unit can adjust the order of information based on the relevance of companies when generating job postings. For example, the job posting generation unit may list the company's main business activities first. For example, it may list "main business activities" at the beginning of the job posting. The job posting generation unit may also list the company's employee benefits and work environment in the middle. For example, it may list "employee benefits" and "work environment" in the middle of the job posting. The job posting generation unit may also list the company's growth opportunities and career paths at the end. For example, it may list "growth opportunities" and "career paths" at the end of the job posting. By adjusting the order of information based on the relevance of companies, it becomes possible to generate effective job postings. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the job posting generation unit can input company relevance data into a generation AI, and the generation AI can adjust the order of information to generate job postings.

[0045] The follow-up unit can analyze a job seeker's past access history to select the most appropriate message during follow-up. For example, the follow-up unit can send relevant messages based on job postings the job seeker has previously viewed. For instance, it might send a message saying, "There are new job postings related to job postings you previously viewed." The follow-up unit can also send follow-up messages based on job postings the job seeker has previously applied for. For example, it might send a message saying, "We'd like to inform you about the progress of the job postings you previously applied for." The follow-up unit can also send messages based on industries the job seeker has previously shown interest in. For example, it might send a message saying, "There are new job postings in industries you've shown interest in." By analyzing the job seeker's past access history, the unit can select the most appropriate message and conduct effective follow-up. Some or all of the above processing in the follow-up unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the follow-up unit can input the job seeker's access history data into a generation AI, which can then generate the most appropriate follow-up message.

[0046] The follow-up unit can send customized messages to job seekers based on their work history and skills during follow-up. For example, the follow-up unit can provide relevant job information based on the job seeker's work history. For instance, it might send a message saying, "We have job openings that match your work history." The follow-up unit can also provide appropriate job information based on the job seeker's skills. For example, it might send a message saying, "We have job openings that match your skills." The follow-up unit can also send messages indicating future growth opportunities based on the job seeker's career path. For example, it might send a message saying, "We have growth opportunities that match your career path." This enables effective follow-up by sending customized messages based on the job seeker's work history and skills. Some or all of the above processing in the follow-up unit may be performed using or without a generating AI. For example, the follow-up unit can input the job seeker's work history and skill data into a generating AI, which can then generate customized follow-up messages.

[0047] The follow-up unit can send the most appropriate message during follow-up, taking into account the job seeker's geographical location. For example, if the job seeker is in a rural area, the follow-up unit can provide job information for that area. For example, the follow-up unit could send the job seeker a message saying, "We have job information that suits your area." The follow-up unit can also provide job information for urban areas if the job seeker is in an urban area. For example, the follow-up unit could send the job seeker a message saying, "We have job information for urban areas." Furthermore, if the job seeker is overseas, the follow-up unit can provide job information for that country. For example, the follow-up unit could send the job seeker a message saying, "We have job information for overseas." By considering the job seeker's geographical location, the system can send the most appropriate message and enable effective follow-up. Some or all of the above processing in the follow-up unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the follow-up unit can input the job seeker's geographical location data into a generation AI, which can then generate the most appropriate follow-up message.

[0048] The follow-up unit can analyze a job seeker's social media activity during follow-up and send relevant messages. For example, the follow-up unit can send a message to a job seeker saying, "We have job postings related to the article you recently shared." The follow-up unit can also send messages based on what the job seeker has said on social media. For example, the follow-up unit can send a message to a job seeker saying, "We have job postings related to your recent tweets." The follow-up unit can also send messages based on the groups the job seeker participates in on social media. For example, the follow-up unit can send a message to a job seeker saying, "We have job postings related to the groups you participate in." By analyzing a job seeker's social media activity, it becomes possible to send relevant messages and conduct effective follow-up. Some or all of the above processing in the follow-up unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the follow-up unit can input the job seeker's social media activity data into a generative AI, which can then generate relevant follow-up messages.

[0049] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0050] The regional job posting generation system can further analyze a user's past application history and customize job postings based on that history. For example, it can prioritize displaying similar job postings based on the job title and industry of jobs previously applied for. It can also analyze a job seeker's skills and experience from their past application history and adjust the content of job postings accordingly. For example, if a job seeker has previously applied for jobs in the IT industry, it can prioritize displaying IT industry job postings and provide job postings that match the job seeker's skills. Furthermore, it can estimate a job seeker's interests and preferences from their past application history and adjust the way job postings are presented accordingly. For example, if a job seeker has previously applied for creative jobs, the job posting can be presented in a creative style. This allows the system to leverage a job seeker's past application history to provide more appropriate job postings.

[0051] The regional job posting generation system can further analyze users' social media activity and customize job postings based on their social media posts and shares. It can also provide job postings that users might be interested in based on their social media activity. For example, if a user has stated on social media that they are interested in data science, the system can prioritize displaying data science-related job postings. Furthermore, it can provide relevant job postings based on the groups a user participates in on social media. For instance, if a user is in a "marketing group," marketing-related job postings can be displayed. This allows the system to leverage users' social media activity to provide more relevant job postings.

[0052] The regional job posting generation system can further consider the user's geographical location to provide region-specific job postings. For example, if a user is in a rural area, it can provide job postings related to local specialties or tourist attractions. For instance, if a user expresses interest in local specialties, the system can display job postings related to those products. Similarly, if a user is in an urban area, the system can provide job postings related to urban convenience and infrastructure. For example, if a user values ​​urban convenience, the system can display job postings that emphasize urban convenience. Furthermore, if a user is overseas, the system can provide job postings related to the culture and business practices of that country. For example, if a user expresses interest in foreign cultures, the system can display job postings related to the culture of that country. In this way, the system can provide region-specific job postings that take the user's geographical location into consideration.

[0053] The regional job posting generation system can further customize job postings based on the user's work history and skills. For example, it can provide relevant job postings based on the user's work history. For instance, if a user feels they have experience in the IT industry, IT-related job postings can be prioritized. It can also provide appropriate job postings based on the user's skills. For example, if a user feels they have data analysis skills, data analysis-related job postings can be displayed. Furthermore, it can provide job postings that highlight future growth opportunities based on the user's career path. For example, if a user feels they are aiming for career advancement, job postings with abundant growth opportunities can be displayed. This allows for the provision of more relevant job postings based on the user's work history and skills.

[0054] The regional job posting generation system can further analyze users' past access history and customize job postings based on that history. For example, it can prioritize displaying similar job postings based on the job titles and industries previously viewed. It can also estimate job seekers' interests and preferences from their past access history and adjust the content of job postings accordingly. For example, if a job seeker frequently viewed IT industry job postings in the past, IT industry job postings can be prioritized. Furthermore, it can analyze job seekers' behavior patterns from their past access history and adjust the timing of job posting display accordingly. For example, if a job seeker often views job postings at night, job postings can be displayed at night. This allows the system to leverage job seekers' past access history to provide more relevant job postings.

[0055] The regional job posting generation system can also send region-specific follow-up messages, taking into account the user's geographical location. For example, if a user is in a rural area, it can send follow-up messages related to local specialties or tourist attractions. For instance, if a user expresses interest in local specialties, it can send follow-up messages related to those products. Similarly, if a user is in an urban area, it can send follow-up messages related to urban convenience and infrastructure. For example, if a user values ​​urban convenience, it can send follow-up messages emphasizing urban convenience. Furthermore, if a user is overseas, it can send follow-up messages related to the culture and business practices of that country. For example, if a user expresses interest in foreign cultures, it can send follow-up messages related to the culture of that country. This allows the system to send region-specific follow-up messages, taking into account the user's geographical location.

[0056] The following briefly describes the processing flow for example form 1.

[0057] Step 1: The extraction department extracts the company's appeal. Specifically, it converses with the company's recruiters and uses generated AI to extract specific information about the company's strengths, work environment, and growth opportunities. For example, it asks questions such as, "What are the company's strengths?" or "Do you provide an environment where employees can work comfortably?" Step 2: The job posting generation unit generates job postings based on the information extracted by the extraction unit. Using the generation AI, it generates job postings that specifically describe the company's appeal and adds detailed explanations as needed. Step 3: The follow-up unit delivers follow-up messages based on the job information generated by the job information generation unit. Using generation AI, it links user IDs with job search conditions, determines each user's access status, and delivers follow-up messages at the appropriate time. For example, if a job seeker shows interest in a particular job posting, it sends additional information related to that job posting or a reminder to apply.

[0058] (Example of form 2) The regional job posting generation system according to an embodiment of the present invention is a system that solves the problem of labor shortages in rural areas by generating regional job postings at low cost using a generation AI and providing appropriate follow-up to job seekers. The regional job posting generation system uses the generation AI to converse with company recruiters and articulate the company's appeal. In this process, the generation AI conducts interviews with recruiters and extracts the company's appeal that even the recruiters themselves may not be aware of. This makes it possible to generate attractive job postings with virtually no costs for interviews or writing. For example, job postings are generated that specifically describe the company's strengths, ease of work, and growth opportunities. Next, a follow-up generation AI operates on a messaging app. By building the service on a messaging app, user IDs and users' job-seeking conditions are linked. The generation AI determines the access status of each user and delivers follow-up messages at the appropriate time. This eliminates the need for knowledge or experience for service operators and minimizes operational costs. For example, if a job seeker shows interest in a particular job posting, the generation AI sends additional information related to that job posting and application reminders. Furthermore, this system can be deployed to many regions. Many regions and municipalities are facing the challenge of industrial decline due to labor shortages, making the need for such a system extremely high. Because it is low-cost and requires no special skills to operate, it can be easily adopted by local businesses and municipalities. Furthermore, as it is an intermediary rather than a recruitment service, the licensing hurdles are low. This system allows job site operators to create attractive job postings at low cost, and makes it easier for companies to acquire talented personnel. Job seekers can more easily find jobs that suit them, and municipalities can increase the number of migrants. For example, a local small or medium-sized enterprise could use AI to create job postings and follow up with job seekers via a messaging app, thereby securing talented personnel and revitalizing local industries. Thus, a regional job posting generation system utilizing AI is expected to solve the labor shortage problem in rural areas and contribute to regional revitalization.

[0059] The regional job information generation system according to this embodiment comprises a data extraction unit, a job information generation unit, and a follow-up unit. The data extraction unit extracts the appeal of companies. For example, the data extraction unit engages in conversation with company recruiters to extract the appeal of companies. Using a generation AI, the data extraction unit can conduct interviews with company recruiters to extract specific information about the company's strengths, ease of work, and growth opportunities. For example, the data extraction unit can ask company recruiters, "What are your company's strengths?" to extract the company's appeal. The data extraction unit can also extract appeals that company recruiters are unaware of. For example, the data extraction unit can ask company recruiters, "Do you provide an environment where employees can work comfortably?" to extract the company's appeal. The job information generation unit generates job information based on the information extracted by the data extraction unit. The job information generation unit uses a generation AI to generate job information that specifically describes the appeal of companies. For example, the job information generation unit generates job information that specifically describes the company's strengths, ease of work, and growth opportunities. The job information generation unit can also use a generation AI to adjust the way the job information is presented. For example, the job posting generation unit adds detailed descriptions to emphasize the company's appeal. The follow-up unit delivers follow-up messages based on the job postings generated by the job posting generation unit. The follow-up unit uses generation AI to link user IDs with job search conditions, determines each user's access status, and delivers follow-up messages at the appropriate time. For example, if a job seeker shows interest in a particular job posting, the follow-up unit sends additional information related to that job posting and application reminders. Furthermore, the follow-up unit does not require any knowledge or experience from the service operator, minimizing operational costs. For example, the follow-up unit uses generation AI to analyze the job seeker's access status in real time and deliver follow-up messages at the appropriate time. As a result, the regional job posting generation system according to this embodiment can create and deliver job postings effectively and at low cost by highlighting the company's appeal, generating job postings, and delivering follow-up messages.

[0060] The extraction unit extracts the company's appeal. Specifically, the extraction unit engages in direct conversations with company recruiters to gather information on the company's strengths, work environment, and growth opportunities. Generative AI plays a crucial role in this process. Generative AI asks recruiters specific questions using pre-set prompts. For example, it extracts the company's appeal through questions such as, "What are your company's strengths?" or "Do you provide a comfortable working environment for employees?" The generative AI can analyze the recruiter's answers in real time and automatically generate further in-depth questions. This makes it possible to extract appeals and strengths that recruiters may not have been aware of. Furthermore, the extraction unit analyzes the company's past job postings and employee feedback to evaluate the company's appeal from multiple perspectives. For example, it can gain a concrete understanding of the company's work environment and growth opportunities based on employee satisfaction surveys and turnover rate data. As a result, the extraction unit can comprehensively extract the company's appeal and collect high-quality data to provide to the job posting generation unit.

[0061] The job posting generation unit generates job postings based on the information extracted by the data extraction unit. By using generation AI, it can automatically create job postings that specifically describe the attractiveness of a company. For example, it can generate attractive job postings for job seekers by describing in detail the company's strengths, work environment, and growth opportunities. The generation AI can use natural language processing technology to adjust the expression to emphasize the company's attractiveness. For example, it can add specific examples and data to highlight the company's strengths. The generation AI can also automatically generate catchy phrases and headlines to attract the attention of job seekers. Furthermore, the job posting generation unit can output the generated job postings in multiple formats. For example, it can generate job postings compatible with various media, such as HTML format for websites and PDF format for printing. As a result, the job posting generation unit can provide job postings that maximize the attractiveness of companies and effectively appeal to job seekers.

[0062] The Follow-Up Department delivers follow-up messages based on job postings generated by the Job Posting Generation Department. Using generation AI, it can link user IDs with job search criteria and analyze user access in real time. For example, if a job seeker shows interest in a particular job posting, it automatically sends additional information related to that posting and application reminders. The generation AI analyzes the job seeker's behavior history and access patterns to deliver follow-up messages at the optimal time. For example, if a job seeker views a job posting but does not apply after a certain period, it sends a reminder message. Furthermore, the Follow-Up Department can collect feedback from job seekers and continuously improve the content of job postings and the effectiveness of follow-up messages. For example, it can review the wording of job postings and the content of follow-up messages based on feedback from job seekers. In addition, the Follow-Up Department can reliably transmit information using multiple communication methods. For example, it can reliably deliver important information using not only smartphone notifications but also voice calls, SMS, and email. This allows the Follow-Up Department to provide job seekers with quick and reliable follow-up messages, improving the application rate.

[0063] The information extraction unit can converse with company recruiters and extract information about the company's appeal. For example, the information extraction unit can converse with company recruiters face-to-face to extract information about the company. Alternatively, the information extraction unit can converse with company recruiters via telephone or chatbot to extract information about the company's appeal. For example, the information extraction unit can ask a company recruiter by phone, "What are your company's strengths?" to extract information about the company. Alternatively, the information extraction unit can use a chatbot to ask a company recruiter, "Do you provide a comfortable working environment for employees?" to extract information about the company's appeal. In this way, the information extraction unit can effectively extract information about the company's appeal through conversations with company recruiters. Some or all of the above processing in the information extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information extraction unit can input the content of the conversation with a company recruiter into a generative AI, which can then generate questions to extract information about the company's appeal.

[0064] The follow-up unit can link user IDs and job search criteria on the messaging app, determine each user's access status, and deliver follow-up messages at the appropriate time. For example, the follow-up unit can link user IDs and job search criteria on the messaging app. For example, when a user logs into the messaging app, the follow-up unit can automatically link user IDs and job search criteria. The follow-up unit can also determine each user's access status and deliver follow-up messages at the appropriate time. For example, when a user accesses a specific job posting, the follow-up unit will deliver a follow-up message related to that job posting. The follow-up unit can also deliver a reminder message if a user has not accessed the app for a certain period of time. This allows for the effective provision of job information by determining each user's access status and delivering follow-up messages at the appropriate time. Some or all of the above processing in the follow-up unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the follow-up unit can input user access status data into a generation AI, which can then generate follow-up messages at the appropriate time.

[0065] The follow-up unit can send additional information and application reminders related to a job posting when a job seeker shows interest in that posting. For example, when a job seeker accesses a specific job posting, the follow-up unit can send additional information related to that posting. For example, when a job seeker accesses a specific job posting, the follow-up unit can send detailed information about the company related to that posting. The follow-up unit can also send application reminders when a job seeker shows interest in a specific job posting. For example, when a job seeker shows interest in a specific job posting, the follow-up unit can send a message reminding them of the application deadline. The follow-up unit can also send interview tips related to a specific job posting when a job seeker shows interest in that posting. This helps maintain the job seeker's interest and encourages applications by sending them additional relevant information and application reminders when they show interest in a specific job posting. Some or all of the above processing in the follow-up unit may be performed using generative AI or not. For example, the follow-up unit can input job seeker access data into a generating AI, which can then generate relevant additional information and application reminders.

[0066] The follow-up department requires no knowledge or experience from service operators, minimizing operational costs. For example, the follow-up department uses generative AI to analyze job seekers' access patterns in real time and deliver follow-up messages at the appropriate time. This allows service operators to perform effective follow-up without special knowledge or experience. For instance, the follow-up department's generative AI automatically analyzes job seekers' access patterns and generates follow-up messages at the optimal time. Furthermore, the follow-up department can use generative AI to generate customized messages based on job seekers' interests. This allows service operators to perform effective follow-up with job seekers without significant effort. Additionally, the follow-up department can use generative AI to collect job seeker feedback and use it to improve the service. For example, the follow-up department's generative AI analyzes job seeker feedback and suggests areas for service improvement. This eliminates the need for knowledge or experience from service operators and minimizes operational costs. Some or all of the above-described processes in the follow-up department may be performed using generative AI, or they may not. For example, the follow-up unit can input data on job seekers' access status into a generating AI, which can then generate the most appropriate follow-up message.

[0067] The information extraction function can estimate the recruiter's emotions and adjust the content and order of questions based on the estimated emotions. For example, if the recruiter is nervous, the extractor can start with simple questions to help them relax. For instance, it might ask the recruiter, "Tell me about your recent projects," to help them relax. If the recruiter is excited, the extractor can also prioritize questions about specific achievements and success stories. For example, it might ask the recruiter, "Tell me about your recent success stories," to maintain their excitement. Furthermore, if the recruiter is tired, the extractor can ask short, to-the-point questions. For example, it might ask the recruiter, "Tell me about the progress of your current projects," taking fatigue into consideration. This allows for effective information extraction by adjusting the content and order of questions based on the recruiter's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processing in the extraction unit may be performed using a generating AI, or it may be performed without a generating AI. For example, the extraction unit can input the facial expression data of the recruiter into a generating AI, which can then estimate the emotions and adjust the content and order of the questions.

[0068] The information extraction unit can analyze the recruiter's past response history and select the most appropriate questions. For example, the extraction unit may revisit questions that the recruiter has answered in detail in the past. For instance, it might ask the recruiter, "Could you tell me more about the project you discussed in our last interview?" The extraction unit can also avoid questions that the recruiter has avoided in the past. For example, it avoids questions that the recruiter did not want to answer in the past. The extraction unit can also ask questions related to topics that the recruiter has shown interest in in the past. For example, it asks questions related to topics that the recruiter has shown interest in in the past. By analyzing the recruiter's past response history, the extraction unit can select the most appropriate questions and effectively extract information. Some or all of the above processing in the information extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the extraction unit can input the recruiter's past response data into a generative AI, which can then generate the most appropriate questions.

[0069] The information extraction unit can generate specialized questions based on the recruiter's industry knowledge and experience. For example, if the recruiter has experience in the IT industry, the extraction unit can ask questions about the latest technology trends. For instance, it might ask the recruiter, "What technology trends are you currently paying attention to?" Similarly, if the recruiter has experience in manufacturing, the extraction unit can ask questions about production efficiency. For example, it might ask the recruiter, "What are you doing to improve production efficiency?" Furthermore, if the recruiter has experience in marketing, the extraction unit can ask questions about effective promotional strategies. For example, it might ask the recruiter, "What is a recent promotional strategy that has been successful?" This allows for effective information extraction by generating specialized questions based on the recruiter's industry knowledge and experience. Some or all of the above processing in the information extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can input the recruiter's industry knowledge and experience data into a generation AI, which can then generate specialized questions.

[0070] The information extraction unit can estimate the recruiter's emotions and adjust the difficulty of questions based on the estimated emotions. For example, if the recruiter is relaxed, the extraction unit will ask difficult questions. For example, it might ask the recruiter, "What was the most difficult challenge in your most recent project?" Conversely, if the recruiter is nervous, the extraction unit can start with easy questions. For example, it might ask the recruiter, "Please tell me about your current position." Furthermore, if the recruiter is tired, the extraction unit can ask short and easy questions. For example, it might ask the recruiter, "Please tell me about the progress of your most recent project." By adjusting the difficulty of questions based on the recruiter's emotions, effective information extraction becomes possible. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the information extraction unit may be performed using generative AI or not. For example, the drawer unit can input the facial expression data of the recruiter into a generating AI, which can estimate emotions and adjust the difficulty level of the questions.

[0071] The information extraction unit can take into account the geographical location of the recruiter and ask questions that highlight the unique appeal of the region. For example, if the recruiter is in a rural area, the information extraction unit can ask questions about the local specialties and tourist attractions. For instance, it might ask the recruiter, "Please tell me about the local specialties and tourist attractions in this region." If the recruiter is in an urban area, the information extraction unit can also ask questions about the convenience and infrastructure of the city. For example, it might ask the recruiter, "Please tell me about the convenience and infrastructure of this city." Furthermore, if the recruiter is overseas, the information extraction unit can ask questions about the culture and business practices of that country. For example, it might ask the recruiter, "Please tell me about the culture and business practices of this country." By considering the geographical location of the recruiter, the information extraction unit can effectively highlight the unique appeal of the region. Some or all of the above processing in the information extraction unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the information extraction unit can input the recruiter's geographical location data into a generative AI, which can then generate questions that highlight the unique appeal of the region.

[0072] The information extraction unit can analyze the social media activity of recruiters and generate relevant questions. For example, the extraction unit might ask a recruiter, "What are your thoughts on the article you recently shared?" The extraction unit can also ask questions based on what recruiters have said on social media. For example, it might ask a recruiter, "Tell me more about your recent tweets." The extraction unit can also ask questions based on the groups recruiters participate in on social media. For example, it might ask a recruiter, "Tell me about your activities in the groups you participate in." By analyzing the recruiter's social media activity, it is possible to generate relevant questions and effectively extract information. Some or all of the above processing in the information extraction unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the extraction unit can input the recruiter's social media activity data into a generation AI, which can then generate relevant questions.

[0073] The job posting generation unit can estimate the emotions of recruiters and adjust the way job postings are expressed based on those estimated emotions. For example, if a recruiter is relaxed, the job posting generation unit will use detailed and friendly language. For instance, it might write "Friendly work environment" in the job posting. If a recruiter is nervous, the job posting generation unit can also use concise and to-the-point language. For example, it might write "Efficient work processes" in the job posting. If a recruiter is excited, the job posting generation unit can also use emphasized language. For example, it might write "Rapidly growing company" in the job posting. By adjusting the way job postings are expressed based on the emotions of recruiters, it becomes possible to generate effective job postings. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the job posting generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the job posting generation unit can input facial expression data of recruiters into a generation AI, which can then estimate emotions and adjust the way the job postings are presented.

[0074] The job posting generation unit can adjust the level of detail based on the company's key characteristics when generating job postings. For example, the job posting generation unit can add detailed descriptions to emphasize a company's strengths. For instance, it might list "high technical capabilities" as a company strength and add a detailed explanation. Conversely, it can also keep descriptions concise to downplay a company's weaknesses. For example, it might list "limited experience in launching new businesses" as a weakness and keep the explanation brief. The job posting generation unit can also add specific examples to emphasize a company's growth opportunities. For example, it might list "entering new markets" as a growth opportunity and add specific examples. By adjusting the level of detail based on a company's key characteristics, it becomes possible to generate effective job postings. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the job posting generation unit can input company characteristic data into a generation AI, which can then generate job postings with adjusted levels of detail.

[0075] The job posting generation unit can apply different generation algorithms depending on the industry and size of the company when generating job postings. For example, in the case of large companies, the job posting generation unit can add information about detailed organizational structure and employee benefits. For instance, the job posting generation unit might include "detailed organizational structure" and "generous employee benefits" in the job postings of large companies. The job posting generation unit can also emphasize information about flexible working arrangements and growth opportunities in the case of small and medium-sized enterprises (SMEs). For example, the job posting generation unit might include "flexible working arrangements" and "growth opportunities" in the job postings of SMEs. Furthermore, the job posting generation unit can also emphasize information about innovation and a challenging spirit in the case of startups. For example, the job posting generation unit might include "innovation" and "challenging spirit" in the job postings of startups. By applying different generation algorithms depending on the industry and size of the company, it becomes possible to generate effective job postings. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without using a generation AI. For example, the job posting generation unit can input data on a company's industry and size into a generation AI, which then applies an appropriate generation algorithm to generate job postings.

[0076] The job posting generation unit can estimate the emotions of recruiters and adjust the length of the job posting based on the estimated emotions. For example, if the recruiter is relaxed, the job posting generation unit will generate a detailed job posting. For instance, it might include "detailed job description" and "specific growth opportunities" in the job posting. Conversely, if the recruiter is nervous, the job posting generation unit can generate a concise job posting. For example, it might include "concise job description" and "key growth opportunities" in the job posting. Furthermore, if the recruiter is excited, the job posting generation unit can generate a job posting that includes emphasized points. For example, it might include "emphasized job description" and "prominent growth opportunities" in the job posting. This allows for the generation of effective job postings by adjusting the length of the job posting based on the recruiter's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is not limited to, but could be a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processes in the job posting generation unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the job posting generation unit can input facial expression data of recruiters into a generation AI, which can then estimate emotions and adjust the length of the job posting.

[0077] The job posting generation unit can prioritize information based on the company's founding date when generating job postings. For example, in the case of a startup, the job posting generation unit can emphasize growth opportunities and innovation. For instance, it might include "growth opportunities" and "innovation" in the job postings for a startup. Similarly, in the case of an established company, the job posting generation unit can emphasize stability and reliability. For example, it might include "stability" and "reliability" in the job postings for an established company. Furthermore, in the case of a mid-sized company, the job posting generation unit can provide balanced information. For example, it might include "balanced job responsibilities" and "growth opportunities" in the job postings for a mid-sized company. This allows for the generation of effective job postings by prioritizing information based on the company's founding date. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the job posting generation unit can input company founding date data into a generation AI, which can then prioritize information and generate job postings.

[0078] The job posting generation unit can adjust the order of information based on the relevance of companies when generating job postings. For example, the job posting generation unit may list the company's main business activities first. For example, it may list "main business activities" at the beginning of the job posting. The job posting generation unit may also list the company's employee benefits and work environment in the middle. For example, it may list "employee benefits" and "work environment" in the middle of the job posting. The job posting generation unit may also list the company's growth opportunities and career paths at the end. For example, it may list "growth opportunities" and "career paths" at the end of the job posting. By adjusting the order of information based on the relevance of companies, it becomes possible to generate effective job postings. Some or all of the above processing in the job posting generation unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the job posting generation unit can input company relevance data into a generation AI, and the generation AI can adjust the order of information to generate job postings.

[0079] The follow-up unit can estimate the job seeker's emotions and adjust the content of follow-up messages based on those emotions. For example, if the job seeker is excited, the follow-up unit can provide detailed information. For instance, it might send the job seeker a message saying, "Here are the detailed job description for this position." The follow-up unit can also send reassuring messages if the job seeker is feeling anxious. For example, it might send the job seeker a message saying, "This position is perfect for you." Furthermore, if the job seeker is relaxed, the follow-up unit can send friendly messages. For example, it might send the job seeker a message saying, "Would you like to know more about this position?" This allows for effective follow-up by adjusting the content of follow-up messages based on the job seeker's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the follow-up unit may be performed using a generative AI, or they may not be performed using a generative AI. For example, the follow-up unit can input the applicant's facial expression data into a generative AI, which can then estimate the emotions and adjust the content of the follow-up message.

[0080] The follow-up unit can analyze a job seeker's past access history to select the most appropriate message during follow-up. For example, the follow-up unit can send relevant messages based on job postings the job seeker has previously viewed. For instance, it might send a message saying, "There are new job postings related to job postings you previously viewed." The follow-up unit can also send follow-up messages based on job postings the job seeker has previously applied for. For example, it might send a message saying, "We'd like to inform you about the progress of the job postings you previously applied for." The follow-up unit can also send messages based on industries the job seeker has previously shown interest in. For example, it might send a message saying, "There are new job postings in industries you've shown interest in." By analyzing the job seeker's past access history, the unit can select the most appropriate message and conduct effective follow-up. Some or all of the above processing in the follow-up unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the follow-up unit can input the job seeker's access history data into a generation AI, which can then generate the most appropriate follow-up message.

[0081] The follow-up unit can send customized messages to job seekers based on their work history and skills during follow-up. For example, the follow-up unit can provide relevant job information based on the job seeker's work history. For instance, it might send a message saying, "We have job openings that match your work history." The follow-up unit can also provide appropriate job information based on the job seeker's skills. For example, it might send a message saying, "We have job openings that match your skills." The follow-up unit can also send messages indicating future growth opportunities based on the job seeker's career path. For example, it might send a message saying, "We have growth opportunities that match your career path." This enables effective follow-up by sending customized messages based on the job seeker's work history and skills. Some or all of the above processing in the follow-up unit may be performed using or without a generating AI. For example, the follow-up unit can input the job seeker's work history and skill data into a generating AI, which can then generate customized follow-up messages.

[0082] The follow-up unit can estimate the job seeker's emotions and adjust the timing of follow-up messages based on the estimated emotions. For example, if the job seeker is excited, the follow-up unit can send a follow-up message immediately. For example, the follow-up unit might send a message saying, "Apply for this job immediately." The follow-up unit can also send a follow-up message at an appropriate time if the job seeker is relaxed. For example, the follow-up unit might send a message saying, "Please think about this job a little more." Furthermore, if the job seeker is feeling anxious, the follow-up unit can send a follow-up message at a time that provides reassurance. For example, the follow-up unit might send a message saying, "This job is perfect for you." This allows for effective follow-up by adjusting the timing of follow-up messages based on the job seeker's emotions. Emotion estimation is achieved using emotion estimation functions, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the follow-up unit may be performed using a generative AI, or they may not be performed using a generative AI. For example, the follow-up unit can input the applicant's facial expression data into a generative AI, which can then estimate their emotions and adjust the timing of sending follow-up messages.

[0083] The follow-up unit can send the most appropriate message during follow-up, taking into account the job seeker's geographical location. For example, if the job seeker is in a rural area, the follow-up unit can provide job information for that area. For example, the follow-up unit could send the job seeker a message saying, "We have job information that suits your area." The follow-up unit can also provide job information for urban areas if the job seeker is in an urban area. For example, the follow-up unit could send the job seeker a message saying, "We have job information for urban areas." Furthermore, if the job seeker is overseas, the follow-up unit can provide job information for that country. For example, the follow-up unit could send the job seeker a message saying, "We have job information for overseas." By considering the job seeker's geographical location, the system can send the most appropriate message and enable effective follow-up. Some or all of the above processing in the follow-up unit may be performed using a generation AI, or it may be performed without a generation AI. For example, the follow-up unit can input the job seeker's geographical location data into a generation AI, which can then generate the most appropriate follow-up message.

[0084] The follow-up unit can analyze a job seeker's social media activity during follow-up and send relevant messages. For example, the follow-up unit can send a message to a job seeker saying, "We have job postings related to the article you recently shared." The follow-up unit can also send messages based on what the job seeker has said on social media. For example, the follow-up unit can send a message to a job seeker saying, "We have job postings related to your recent tweets." The follow-up unit can also send messages based on the groups the job seeker participates in on social media. For example, the follow-up unit can send a message to a job seeker saying, "We have job postings related to the groups you participate in." By analyzing a job seeker's social media activity, it becomes possible to send relevant messages and conduct effective follow-up. Some or all of the above processing in the follow-up unit may be performed using a generative AI, or it may be performed without a generative AI. For example, the follow-up unit can input the job seeker's social media activity data into a generative AI, which can then generate relevant follow-up messages.

[0085] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0086] The regional job posting generation system can further analyze a user's past application history and customize job postings based on that history. For example, it can prioritize displaying similar job postings based on the job title and industry of jobs previously applied for. It can also analyze a job seeker's skills and experience from their past application history and adjust the content of job postings accordingly. For example, if a job seeker has previously applied for jobs in the IT industry, it can prioritize displaying IT industry job postings and provide job postings that match the job seeker's skills. Furthermore, it can estimate a job seeker's interests and preferences from their past application history and adjust the way job postings are presented accordingly. For example, if a job seeker has previously applied for creative jobs, the job posting can be presented in a creative style. This allows the system to leverage a job seeker's past application history to provide more appropriate job postings.

[0087] The regional job posting generation system can further analyze users' social media activity and customize job postings based on their social media posts and shares. It can also provide job postings that users might be interested in based on their social media activity. For example, if a user has stated on social media that they are interested in data science, the system can prioritize displaying data science-related job postings. Furthermore, it can provide relevant job postings based on the groups a user participates in on social media. For instance, if a user is in a "marketing group," marketing-related job postings can be displayed. This allows the system to leverage users' social media activity to provide more relevant job postings.

[0088] The regional job posting generation system can further estimate the user's emotions and adjust the display order of job postings based on those emotions. For example, if a user is excited, the most attractive job postings can be displayed first. For example, if a user feels they are "looking for a new challenge," job postings with abundant growth opportunities can be displayed first. Also, if a user is feeling anxious, job postings that provide a sense of security can be displayed first. For example, if a user feels they are "looking for a stable job," job postings that emphasize stability can be displayed first. Furthermore, if a user is relaxed, friendly job postings can be displayed first. For example, if a user feels they are "looking for a friendly work environment," job postings that emphasize a friendly work environment can be displayed first. In this way, by adjusting the display order of job postings based on the user's emotions, it becomes possible to provide more effective job information.

[0089] The regional job posting generation system can further consider the user's geographical location to provide region-specific job postings. For example, if a user is in a rural area, it can provide job postings related to local specialties or tourist attractions. For instance, if a user expresses interest in local specialties, the system can display job postings related to those products. Similarly, if a user is in an urban area, the system can provide job postings related to urban convenience and infrastructure. For example, if a user values ​​urban convenience, the system can display job postings that emphasize urban convenience. Furthermore, if a user is overseas, the system can provide job postings related to the culture and business practices of that country. For example, if a user expresses interest in foreign cultures, the system can display job postings related to the culture of that country. In this way, the system can provide region-specific job postings that take the user's geographical location into consideration.

[0090] The regional job posting generation system can further customize job postings based on the user's work history and skills. For example, it can provide relevant job postings based on the user's work history. For instance, if a user feels they have experience in the IT industry, IT-related job postings can be prioritized. It can also provide appropriate job postings based on the user's skills. For example, if a user feels they have data analysis skills, data analysis-related job postings can be displayed. Furthermore, it can provide job postings that highlight future growth opportunities based on the user's career path. For example, if a user feels they are aiming for career advancement, job postings with abundant growth opportunities can be displayed. This allows for the provision of more relevant job postings based on the user's work history and skills.

[0091] The regional job posting generation system can further estimate the user's emotions and adjust the content of follow-up messages based on those emotions. For example, if the user is excited, detailed information can be provided. For instance, if the user feels they are "looking for a new challenge," detailed information about job postings with abundant growth opportunities can be provided. Also, if the user is feeling anxious, reassuring messages can be sent. For example, if the user feels they are "looking for a stable job," detailed information about job postings emphasizing stability can be provided. Furthermore, if the user is relaxed, friendly messages can be sent. For example, if the user feels they are "looking for a friendly work environment," detailed information about job postings emphasizing a friendly work environment can be provided. This allows for more effective follow-up by adjusting the content of follow-up messages based on the user's emotions.

[0092] The regional job posting generation system can further analyze users' past access history and customize job postings based on that history. For example, it can prioritize displaying similar job postings based on the job titles and industries previously viewed. It can also estimate job seekers' interests and preferences from their past access history and adjust the content of job postings accordingly. For example, if a job seeker frequently viewed IT industry job postings in the past, IT industry job postings can be prioritized. Furthermore, it can analyze job seekers' behavior patterns from their past access history and adjust the timing of job posting display accordingly. For example, if a job seeker often views job postings at night, job postings can be displayed at night. This allows the system to leverage job seekers' past access history to provide more relevant job postings.

[0093] The regional job posting generation system can further estimate the user's emotions and adjust the way job postings are presented based on those emotions. For example, if the user is relaxed, detailed and friendly language can be used. For instance, the job posting could state "friendly work environment." If the user is tense, concise and to-the-point language can be used. For example, the job posting could state "efficient work processes." Furthermore, if the user is excited, emphasized language can be used. For example, the job posting could state "rapidly growing company." By adjusting the way job postings are presented based on the user's emotions, it becomes possible to provide more effective job information.

[0094] The regional job posting generation system can also send region-specific follow-up messages, taking into account the user's geographical location. For example, if a user is in a rural area, it can send follow-up messages related to local specialties or tourist attractions. For instance, if a user expresses interest in local specialties, it can send follow-up messages related to those products. Similarly, if a user is in an urban area, it can send follow-up messages related to urban convenience and infrastructure. For example, if a user values ​​urban convenience, it can send follow-up messages emphasizing urban convenience. Furthermore, if a user is overseas, it can send follow-up messages related to the culture and business practices of that country. For example, if a user expresses interest in foreign cultures, it can send follow-up messages related to the culture of that country. This allows the system to send region-specific follow-up messages, taking into account the user's geographical location.

[0095] The regional job posting generation system can further estimate the user's emotions and adjust the timing of follow-up messages based on those emotions. For example, if a user is excited, a follow-up message can be sent immediately. For example, if a user feels they are "looking for a new challenge," a follow-up message highlighting job opportunities with abundant growth potential can be sent immediately. Also, if a user is relaxed, a follow-up message can be sent at an appropriate time. For example, if a user feels they are "looking for a friendly work environment," a follow-up message emphasizing a friendly work environment can be sent at an appropriate time. Furthermore, if a user is feeling anxious, a follow-up message can be sent at a time that provides reassurance. For example, if a user feels they are "looking for a stable job," a follow-up message highlighting stability can be sent at a time that provides reassurance. In this way, by adjusting the timing of follow-up messages based on the user's emotions, more effective follow-up becomes possible.

[0096] The following briefly describes the processing flow for example form 2.

[0097] Step 1: The extraction department extracts the company's appeal. Specifically, it converses with the company's recruiters and uses generated AI to extract specific information about the company's strengths, work environment, and growth opportunities. For example, it asks questions such as, "What are the company's strengths?" or "Do you provide an environment where employees can work comfortably?" Step 2: The job posting generation unit generates job postings based on the information extracted by the extraction unit. Using the generation AI, it generates job postings that specifically describe the company's appeal and adds detailed explanations as needed. Step 3: The follow-up unit delivers follow-up messages based on the job information generated by the job information generation unit. Using generation AI, it links user IDs with job search conditions, determines each user's access status, and delivers follow-up messages at the appropriate time. For example, if a job seeker shows interest in a particular job posting, it sends additional information related to that job posting or a reminder to apply.

[0098] 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.

[0099] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0100] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0101] Each of the multiple elements described above, including the extraction unit, job information generation unit, and follow-up unit, is implemented, for example, by at least one of the smart device 14 and the data processing device 12. For example, the extraction unit is implemented by the control unit 46A of the smart device 14, and engages in conversation with the company's recruiter to highlight the company's appeal. The job information generation unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and generates job information based on the extracted information. The follow-up unit is implemented, for example, by the control unit 46A of the smart device 14, and links the user ID with the job application conditions and delivers follow-up messages at the appropriate time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0102] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0103] 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.

[0104] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0105] 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.

[0106] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0107] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0108] 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.

[0109] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0110] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0111] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0112] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0113] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0114] 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.

[0115] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0116] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0117] Each of the multiple elements described above, including the extraction unit, job information generation unit, and follow-up unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing device 12. For example, the extraction unit is implemented by the control unit 46A of the smart glasses 214, and engages in conversation with the company's recruiter to highlight the company's appeal. The job information generation unit is implemented, for example, by the identification processing unit 290 of the data processing device 12, and generates job information based on the extracted information. The follow-up unit is implemented, for example, by the control unit 46A of the smart glasses 214, and links the user ID with the job application conditions and delivers follow-up messages at the appropriate time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0118] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0119] 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.

[0120] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0121] 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.

[0122] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0123] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0124] 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.

[0125] 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.

[0126] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0127] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0128] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0129] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0130] 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.

[0131] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0132] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0133] Each of the multiple elements described above, including the extraction unit, job information generation unit, and follow-up unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the headset terminal 314, and engages in conversation with the company's recruiter to highlight the company's appeal. The job information generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and generates job information based on the extracted information. The follow-up unit is implemented by, for example, the control unit 46A of the headset terminal 314, and links the user ID with the job application conditions and delivers follow-up messages at the appropriate time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0134] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0135] 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.

[0136] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0137] 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.

[0138] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0139] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0140] 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.

[0141] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0142] 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.

[0143] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0144] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0145] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0146] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0147] 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.

[0148] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0149] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0150] Each of the multiple elements described above, including the extraction unit, job information generation unit, and follow-up unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the robot 414, which converses with the company's recruiter and highlights the company's attractiveness. The job information generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, which generates job information based on the extracted information. The follow-up unit is implemented by, for example, the control unit 46A of the robot 414, which links the user ID with the job application conditions and delivers follow-up messages at the appropriate time. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0151] 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.

[0152] Figure 9 shows the 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.

[0153] 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.

[0154] 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.

[0155] 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, and motorcycles, 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 based, for example, 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.

[0156] 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."

[0157] 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.

[0158] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0167] 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 other things 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.

[0168] 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.

[0169] (Note 1) The department that brings out the company's appeal, A job information generation unit generates job information based on the information extracted by the extraction unit, The system includes a follow-up unit that delivers follow-up messages based on the job information generated by the job information generation unit. A system characterized by the following features. (Note 2) The aforementioned drawer section is I engage in conversations with company recruiters to highlight the company's appeal. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned follow-up unit is, The messaging app links user IDs with job search criteria, determines each user's access status, and delivers follow-up messages at the appropriate time. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned follow-up unit is, When a job seeker expresses interest in a particular job posting, we send them additional information related to that posting and reminders to apply. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned follow-up unit is, The service requires no knowledge or experience from the service operator, and operating costs are kept to a minimum. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned drawer section is The system estimates the recruiter's emotions and adjusts the content and order of questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned drawer section is Analyze the recruiter's past response history to select the most suitable questions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned drawer section is Based on the recruiter's industry knowledge and experience, we generate specialized questions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned drawer section is The system estimates the recruiter's emotions and adjusts the difficulty of the questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned drawer section is Considering the geographical location of the hiring manager, ask questions that highlight the unique appeal of the region. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned drawer section is Analyze recruiters' social media activity and generate relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned job information generation unit, We estimate the emotions of recruiters and adjust the way job postings are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned job information generation unit, When generating job postings, adjust the level of detail based on key characteristics of the company. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned job information generation unit, When generating job postings, different generation algorithms are applied depending on the company's industry and size. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned job information generation unit, The system estimates the recruiter's feelings and adjusts the length of the job posting based on those estimated feelings. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned job information generation unit, When generating job postings, the information is prioritized based on the company's founding date. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned job information generation unit, When generating job postings, the order of information is adjusted based on the relevance of the companies. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned follow-up unit is, The system estimates the job seeker's emotions and adjusts the content of follow-up messages based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned follow-up unit is, During follow-up, the system analyzes the job seeker's past access history to select the most appropriate message. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned follow-up unit is, During follow-up, send customized messages based on the job seeker's work history and skills. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned follow-up unit is, The system estimates the job seeker's emotions and adjusts the timing of follow-up messages based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned follow-up unit is, When following up, we send the most appropriate message considering the job seeker's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned follow-up unit is, During follow-up, analyze the job seeker's social media activity and send relevant messages. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0170] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The department that brings out the company's appeal, A job information generation unit generates job information based on the information extracted by the extraction unit, The system includes a follow-up unit that delivers follow-up messages based on the job information generated by the job information generation unit. A system characterized by the following features.

2. The aforementioned drawer section is I engage in conversations with company recruiters to highlight the company's appeal. The system according to feature 1.

3. The aforementioned follow-up unit is, The messaging app links user IDs with job search criteria, determines each user's access status, and delivers follow-up messages at the appropriate time. The system according to feature 1.

4. The aforementioned follow-up unit is, When a job seeker expresses interest in a particular job posting, we send them additional information related to that posting and reminders to apply. The system according to feature 1.

5. The aforementioned follow-up unit is, The service requires no knowledge or experience from the service operator, and operating costs are kept to a minimum. The system according to feature 1.

6. The aforementioned drawer section is The system estimates the recruiter's emotions and adjusts the content and order of questions based on those estimated emotions. The system according to feature 1.

7. The aforementioned drawer section is Analyze the recruiter's past response history to select the most suitable questions. The system according to feature 1.

8. The aforementioned drawer section is Based on the recruiter's industry knowledge and experience, we generate specialized questions. The system according to feature 1.

9. The aforementioned drawer section is The system estimates the recruiter's emotions and adjusts the difficulty of the questions based on those estimated emotions. The system according to feature 1.

10. The aforementioned drawer section is Considering the geographical location of the hiring manager, ask questions that highlight the unique appeal of the region. The system according to feature 1.

Images