system

Abstract

The system according to this embodiment aims to automatically determine the reliability of job postings and provide an environment in which users can use the service with peace of mind. [Solution] The system according to the embodiment comprises an extraction unit, a verification unit, an analysis unit, a scoring unit, and a withdrawal unit. The extraction unit extracts job description, salary, and company information from job advertisements. The verification unit verifies the company's registration information based on the information extracted by the extraction unit. The analysis unit analyzes the balance between job description and salary based on the information verified by the verification unit. The scoring unit scores the reliability of the job information based on the information analyzed by the analysis unit. The withdrawal unit withdraws job information that has a low score from the scoring unit.

Description

Technical Field

[0004] ,

[0006] , , , , , ,

[0005] , , , , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot 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 as a 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] [[ID=3�]] In the conventional technology, the reliability of job information has not been sufficiently automatically determined, and there is room for improvement.

[0005] The system according to the embodiment aims to automatically determine the reliability of job information and provide an environment that can be used with confidence.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an extraction unit, a verification unit, an analysis unit, a scoring unit, and a withdrawal unit. The extraction unit extracts job description, salary, and company information from job advertisements. The verification unit verifies the company's registration information based on the information extracted by the extraction unit. The analysis unit analyzes the balance between job description and salary based on the information verified by the verification unit. The scoring unit scores the reliability of the job information based on the information analyzed by the analysis unit. The withdrawal unit withdraws job information that has a low score from the scoring unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically determine the reliability of job postings and provide an environment that can be used with peace of mind. [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 numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards 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 AI ​​agent for detecting illegal part-time jobs according to an embodiment of the present invention is a cutting-edge AI solution that scrutinizes job postings on part-time job services and determines the potential risks of illegal part-time jobs. The AI ​​agent for detecting illegal part-time jobs automatically extracts job descriptions, salaries, and company information from job advertisements, verifies company registration information, and analyzes the balance between job descriptions and salaries. This enhances the reliability of job postings and provides a safe environment for users. For example, the AI ​​agent for detecting illegal part-time jobs automatically extracts job descriptions, salaries, and company information from job advertisements. Next, it verifies company registration information based on the extracted information. Furthermore, it analyzes the balance between job descriptions and salaries and scores the reliability of the job postings. Job postings with low scores are judged to have a high risk of being illegal part-time jobs and are removed before being posted on part-time job services. This enhances the reliability of job postings and provides an environment where users can use job postings with peace of mind. In addition, the AI ​​agent can be deployed as an API to each company's job site, contributing to the improvement of the reliability of the entire job market. Thus, the AI ​​agent for detecting illegal part-time jobs can enhance the reliability of job postings and provide a safe environment for users.

[0029] The AI ​​agent for determining whether a job posting is illegal according to this embodiment comprises an extraction unit, a verification unit, an analysis unit, a scoring unit, and a withdrawal unit. The extraction unit extracts job description, salary, and company information from the job advertisement. The extraction unit, for example, analyzes the text data of the job advertisement to identify job description, salary, and company information. The extraction unit can, for example, use natural language processing technology to analyze the text data of the job advertisement and extract job description, salary, and company information. The extraction unit can also use machine learning algorithms to identify job description, salary, and company information from the text data of the job advertisement. For example, the extraction unit can use an AI model that takes the text data of the job advertisement as input and outputs job description, salary, and company information to extract the information. The verification unit verifies the company's registration information based on the information extracted by the extraction unit. The verification unit, for example, checks against a company registration information database to verify the reliability of the company. The verification unit can, for example, access a company registration information database to verify the company's basic information. The verification unit can also check against a company registration information database to verify the reliability of the company. For example, the verification unit can verify the reliability of a company using an AI model that takes a company registration information database as input and outputs the reliability of the company. The analysis unit analyzes the balance between job content and salary based on the information verified by the verification unit. The analysis unit determines, for example, the balance between job content and salary. The analysis unit can analyze the balance between job content and salary using, for example, criteria for evaluating the balance between job content and salary. The analysis unit can also analyze the balance between job content and salary using an algorithm for evaluating the balance between job content and salary. For example, the analysis unit can analyze the balance between job content and salary using an AI model that takes the balance between job content and salary as input and outputs the evaluation result of the balance. The scoring unit scores the reliability of the job posting based on the information analyzed by the analysis unit. The scoring unit scores the reliability of the job posting, for example. The scoring unit can score the reliability of the job posting using, for example, criteria for evaluating the reliability of the job posting.Furthermore, the scoring unit can also score the reliability of job postings using an algorithm for evaluating the reliability of job postings. For example, the scoring unit can score the reliability of job postings using an AI model that takes the reliability of job postings as input and outputs a reliability score. The withdrawal unit withdraws job postings that have low scores determined by the scoring unit. The withdrawal unit withdraws job postings, for example, that have low scores. The withdrawal unit can withdraw job postings using, for example, criteria for automatically withdrawing job postings with low scores. The withdrawal unit can also withdraw job postings using an algorithm for automatically withdrawing job postings with low scores. For example, the withdrawal unit can withdraw job postings using an AI model that takes job postings with low scores as input and outputs a withdrawal instruction. As a result, the AI ​​agent for determining whether a job is illegal according to the embodiment can enhance the reliability of job postings and provide an environment in which users can feel secure.

[0030] The extraction unit extracts job descriptions, salaries, and company information from job advertisements. Specifically, the extraction unit uses natural language processing (NLP) techniques to analyze the text data of job advertisements and identify job descriptions, salaries, and company information. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis, and by combining these, it is possible to accurately extract the necessary information from the text data of job advertisements. For example, morphological analysis is used to divide the text data into words, grammatical analysis is used to analyze the structure of sentences, and semantic analysis is used to understand the meaning of sentences. This allows the extraction unit to accurately extract job descriptions, salaries, and company information from the text data of job advertisements. The extraction unit can also use machine learning algorithms to identify job descriptions, salaries, and company information from the text data of job advertisements. Machine learning algorithms include supervised learning, unsupervised learning, and reinforcement learning, and by combining these, it is possible to extract the necessary information from the text data of job advertisements with high accuracy. For example, supervised learning is used to learn from past job advertisement data and identify job descriptions, salaries, and company information from new job advertisement data. Furthermore, unsupervised learning is used to cluster job advertisement data, identifying job descriptions, salaries, and company information from similar job advertisements. Reinforcement learning can also be used to improve the accuracy of the job advertisement data analysis. As a result, the extraction unit can extract job descriptions, salaries, and company information from the text data of job advertisements with high accuracy.

[0031] The verification unit verifies the company's registration information based on the information extracted by the extraction unit. Specifically, the verification unit compares the information with the company's registration information database to verify the company's reliability. The company's registration information database includes basic company information, officer information, and financial information, and by comparing this information, the company's reliability can be verified. For example, basic company information such as company name, address, date of establishment, and capital can be verified, and officer information such as representative name, officer names, and officer histories can be verified. Financial information such as sales, profits, and liabilities can also be verified. This allows the verification unit to comprehensively evaluate the company's reliability. Furthermore, the verification unit can access the company's registration information database and verify the company's basic information. Basic company information includes company name, address, date of establishment, and capital, and by verifying this information, the company's reliability can be evaluated. In addition, the verification unit can verify the company's reliability by comparing it with the company's registration information database. For example, the reliability of a company can be verified using an AI model that takes the company's registration information database as input and outputs the reliability of the company. The AI ​​model incorporates machine learning algorithms and can accurately assess a company's reliability by learning from past data. This allows the verification unit to quickly and accurately verify the company's reliability.

[0032] The Analysis Department analyzes the balance between job content and salary based on information verified by the Verification Department. Specifically, the Analysis Department analyzes the balance between job content and salary using criteria for determining this balance. These criteria include the difficulty of the work, the volume of work, the risks of the work, and the level of specialization required for the work. Using these criteria, the Analysis Department can comprehensively evaluate the balance between job content and salary. For example, if the work is difficult or the volume of work is high, it is desirable for the salary to be set high. Similarly, if the work is high-risk or highly specialized, it is desirable for the salary to be set high. This allows the Analysis Department to comprehensively evaluate the balance between job content and salary. The Analysis Department can also analyze the balance between job content and salary using algorithms. These algorithms incorporate machine learning algorithms, and by learning from past data, they can evaluate the balance between job content and salary with high accuracy. For example, the Analysis Department can analyze the balance between job content and salary using an AI model that takes the balance between job content and salary as input and outputs the evaluation result. This allows the Analysis Department to analyze the balance between job content and salary quickly and accurately.

[0033] The scoring unit scores the reliability of job postings based on the information analyzed by the analysis unit. Specifically, the scoring unit scores the reliability of job postings using criteria for evaluating their reliability. These criteria include the reliability of the company, the balance between job duties and salary, the accuracy of the job advertisement content, and the history of past job advertisements. Using these criteria, the reliability of job postings can be comprehensively evaluated. For example, if the company has high reliability or the balance between job duties and salary is good, the job posting will be evaluated as highly reliable. Similarly, if the content of the job advertisement is accurate or the history of past job advertisements is good, the job posting will also be evaluated as highly reliable. This allows the scoring unit to comprehensively evaluate the reliability of job postings. The scoring unit can also score the reliability of job postings using an algorithm for evaluating their reliability. The algorithm incorporates a machine learning algorithm, which can evaluate the reliability of job postings with high accuracy by learning from past data. For example, the reliability of job postings can be scored using an AI model that takes the reliability of job postings as input and outputs a reliability score. This allows the scoring unit to score the reliability of job postings quickly and accurately.

[0034] The withdrawal unit withdraws job postings that have low scores determined by the scoring unit. Specifically, the withdrawal unit withdraws job postings using criteria for automatically withdrawing low-scoring job postings. These criteria include a reliability score threshold, past withdrawal history, and the accuracy of the job advertisement content. Using these criteria, the unit can automatically withdraw low-scoring job postings. For example, if the reliability score is below the threshold, if there is a history of many past withdrawals, or if the job advertisement content is inaccurate, the job posting will be judged as having a low score and will be automatically withdrawn. This allows the withdrawal unit to withdraw low-scoring job postings quickly and accurately. The withdrawal unit can also withdraw job postings using an algorithm for automatically withdrawing low-scoring job postings. The algorithm incorporates a machine learning algorithm, and by learning from past data, it can withdraw low-scoring job postings with high accuracy. For example, a job posting can be withdrawn using an AI model that takes low-scoring job postings as input and outputs a withdrawal instruction. This allows the withdrawal unit to withdraw low-scoring job postings quickly and accurately.

[0035] The API unit can be deployed to each company's job posting website. For example, the API unit can provide the functionality of an AI agent for detecting illegal job postings as an API to each company's job posting website that provides job information. The API unit can, for example, provide an API endpoint for evaluating the reliability of job postings. The API unit can also provide API documentation for evaluating the reliability of job postings. For example, the API unit can provide an API that takes an API endpoint for evaluating the reliability of job postings as input and outputs the reliability evaluation result. This can contribute to improving the reliability of the entire job market. Some or all of the above processing in the API unit may be performed using AI, for example, or without using AI. For example, the API unit can input an API endpoint for evaluating the reliability of job postings into a generating AI and have the generating AI execute the generation of the reliability evaluation result.

[0036] The extraction unit can analyze the text data of job advertisements to identify job duties, salary, and company information. For example, the extraction unit can analyze the text data of job advertisements using natural language processing technology to identify job duties, salary, and company information. The extraction unit can also use machine learning algorithms to identify job duties, salary, and company information from the text data of job advertisements. For example, the extraction unit can use an AI model that takes the text data of job advertisements as input and outputs job duties, salary, and company information to extract the information. This allows for accurate information extraction from the text data of job advertisements. Some or all of the above-described processes in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the text data of job advertisements into a generating AI and have the generating AI perform the identification of job duties, salary, and company information.

[0037] The verification unit can verify the reliability of a company by comparing it with a company registration information database. For example, the verification unit can access a company registration information database and verify the company's basic information. The verification unit can also verify the reliability of a company by comparing it with a company registration information database. For example, the verification unit can verify the reliability of a company using an AI model that takes a company registration information database as input and outputs the reliability of the company. This allows for accurate verification of the reliability of a company. Some or all of the above-described processes in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input a company registration information database into a generating AI and have the generating AI perform the verification of the reliability of the company.

[0038] The analysis unit can determine the balance between job content and salary. The analysis unit can analyze the balance between job content and salary using, for example, criteria for evaluating the balance between job content and salary. The analysis unit can also analyze the balance between job content and salary using, for example, algorithms for evaluating the balance between job content and salary. For example, the analysis unit can analyze the balance between job content and salary using an AI model that takes the balance between job content and salary as input and outputs the balance evaluation result. This allows for an accurate determination of the balance between job content and salary. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the balance between job content and salary into a generating AI and have the generating AI perform the balance evaluation.

[0039] The scoring unit can score the reliability of job postings. The scoring unit scores the reliability of job postings using, for example, criteria for evaluating the reliability of job postings. The scoring unit can also score the reliability of job postings using, for example, an algorithm for evaluating the reliability of job postings. For example, the scoring unit can score the reliability of job postings using an AI model that takes the reliability of job postings as input and outputs a reliability score. By scoring the reliability of job postings, highly reliable job postings can be provided. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or without AI. For example, the scoring unit can input the reliability of job postings into a generating AI and have the generating AI calculate the reliability score.

[0040] The withdrawal unit can withdraw job postings with low scores. The withdrawal unit withdraws job postings using, for example, criteria for automatically withdrawing job postings with low scores. The withdrawal unit can also withdraw job postings using, for example, an algorithm for automatically withdrawing job postings with low scores. For example, the withdrawal unit can withdraw job postings using an AI model that takes job postings with low scores as input and outputs a withdrawal instruction. This eliminates unreliable job postings by withdrawing job postings with low scores. Some or all of the above processing in the withdrawal unit may be performed using, for example, AI, or not using AI. For example, the withdrawal unit can input job postings with low scores into a generating AI and have the generating AI execute a withdrawal instruction.

[0041] The extraction unit can extract job descriptions, salary information, and company information not only from the text data of job advertisements but also from images and videos. For example, the extraction unit can analyze images included in job advertisements to identify company logos and office photos, supplementing company information. For example, the extraction unit can extract descriptions of job duties and workplace atmosphere from videos included in job advertisements. For example, the extraction unit can extract salary and benefits information from infographics included in job advertisements. This allows for obtaining more information by extracting information from images and videos as well. Some or all of the above-described processes in the extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the extraction unit can input image and video data from job advertisements into a generating AI and have the generating AI perform the extraction of job descriptions, salary information, and company information.

[0042] The extraction unit can refer to past data of job advertisements and build a feedback loop to improve extraction accuracy. For example, the extraction unit can improve the extraction accuracy of job descriptions based on past job advertisement data. The extraction unit can also improve the extraction accuracy of salary information based on past job advertisement data. The extraction unit can also improve the extraction accuracy of company information based on past job advertisement data. In this way, extraction accuracy can be improved by referring to past data. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input past job advertisement data into a generation AI and have the generation AI perform the extraction accuracy improvement.

[0043] The extraction unit can analyze a company's social media activities and extract relevant information when analyzing job advertisements. For example, the extraction unit can extract the latest news and event information from a company's official social media accounts. The extraction unit can also extract employee profiles and career path information from a company's social media pages. For example, the extraction unit can extract information about corporate culture and employee benefits from a company's social media pages. This allows more relevant information to be obtained by analyzing a company's social media activities. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the extraction unit can input the company's social media data into a generative AI and have the generative AI perform the extraction of relevant information.

[0044] The extraction unit can extract highly relevant information by considering the geographical location of companies when analyzing job advertisements. For example, the extraction unit can extract nearby transportation and access information based on the company's location. The extraction unit can also extract information on local living expenses and prices based on the company's location. The extraction unit can also extract information on surrounding housing and rental properties based on the company's location. This allows for the provision of more relevant information by considering the company's geographical location. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or without a generating AI. For example, the extraction unit can input the company's geographical location data into a generating AI and have the generating AI perform the extraction of relevant information.

[0045] The verification unit can cross-reference not only the company's registration information database but also a database of the company's past legal troubles and reputation. For example, the verification unit can verify the company's basic information by cross-referencing the company's registration information database. The verification unit can also verify legal risks by cross-referencing the company's past legal troubles database. The verification unit can also verify the company's reliability by cross-referencing the company's reputation database. This allows for a more accurate verification of reliability by cross-referencing the company's past legal troubles and reputation database. Some or all of the above-described processes in the verification unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the verification unit can input the company's legal trouble data into a generating AI and have the generating AI perform the legal risk verification.

[0046] The verification unit can analyze a company's financial situation and reflect this in the reliability assessment when verifying the company's reliability. For example, the verification unit can analyze a company's financial statements to confirm its financial soundness. The verification unit can also analyze a company's profitability to confirm the stability of its management. The verification unit can also analyze a company's debt situation to confirm its financial risks. This allows for a more accurate reliability assessment by analyzing a company's financial situation. Some or all of the above-described processes in the verification unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the verification unit can input a company's financial data into a generating AI and have the generating AI perform an analysis of its financial situation.

[0047] The verification unit can refer to a company's reputation within its industry and comparative data with competitors when verifying a company's reliability. For example, the verification unit can verify a company's reputation within its industry and evaluate its reliability. The verification unit can also refer to comparative data with competitors and evaluate the company's relative reliability. The verification unit can also refer to benchmark data within the industry and evaluate the company's reliability. This allows for a more accurate reliability assessment by referring to a company's reputation within its industry and comparative data with competitors. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input company reputation data into a generative AI and have the generative AI perform the reliability evaluation.

[0048] The verification unit can consider a company's environmental, social, and governance (ESG) score when verifying the company's reliability. For example, the verification unit can check a company's environmental score and evaluate its environmental considerations. For example, the verification unit can also check a company's social score and evaluate its social responsibility. For example, the verification unit can check a company's governance score and evaluate the soundness of its management. This allows for a more comprehensive reliability assessment by considering a company's ESG score. Some or all of the above processing in the verification unit may be performed using, for example, a generating AI, or without a generating AI. For example, the verification unit can input a company's ESG data into a generating AI and have the generating AI perform the ESG score evaluation.

[0049] The analysis department can improve the accuracy of its analysis when analyzing the balance between job content and salary by referring to past similar job posting data. For example, the analysis department can improve the accuracy of its analysis of job content based on past similar job posting data. The analysis department can also improve the accuracy of its analysis of salary based on past similar job posting data. The analysis department can also improve the accuracy of its analysis of the balance between job content and salary based on past similar job posting data. In this way, the analysis department can improve the accuracy of its analysis by referring to past similar job posting data. Some or all of the above processes in the analysis department may be performed using, for example, a generation AI, or not using a generation AI. For example, the analysis department can input past similar job posting data into a generation AI and have the generation AI perform the improvement of analysis accuracy.

[0050] The analysis department can evaluate the balance between job content and salary by considering the risks and workload of the work. For example, the analysis department can evaluate the risks of the work and analyze the balance with salary. The analysis department can also evaluate the workload and analyze the balance with salary. The analysis department can also comprehensively evaluate the risks and workload of the work and analyze the balance with salary. This allows for a more accurate balance evaluation by considering the risks and workload of the work. Some or all of the above processes in the analysis department may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis department can input job risk data into a generative AI and have the generative AI perform a risk evaluation.

[0051] The analysis department can refer to industry-wide salary levels and trend data when analyzing the balance between job content and salary. For example, the analysis department can refer to industry-wide salary levels and analyze the balance between job content and salary. The analysis department can also refer to industry trend data and analyze the balance between job content and salary. The analysis department can also refer to industry benchmark data and analyze the balance between job content and salary. This allows for a more accurate balance analysis by referring to industry-wide salary levels and trend data. Some or all of the above processing in the analysis department may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis department can input industry salary data into a generative AI and have the generative AI perform a salary level evaluation.

[0052] The analysis department can consider regional living costs and price indices when analyzing the balance between job content and salary. For example, the analysis department can analyze the balance between job content and salary by considering regional living costs. The analysis department can also analyze the balance between job content and salary by considering regional price indices. The analysis department can also analyze the balance between job content and salary by comprehensively considering regional living costs and price indices. This allows for a more accurate balance analysis by considering regional living costs and price indices. Some or all of the above processing in the analysis department may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis department can input regional living cost data into a generating AI and have the generating AI perform the balance analysis.

[0053] The scoring unit can optimize the scoring algorithm by referring to past score data when calculating the reliability score. For example, the scoring unit can improve the accuracy of calculating the reliability score based on past score data. The scoring unit can also optimize the scoring algorithm based on past score data. For example, the scoring unit can adjust the scoring criteria based on past score data. This allows the scoring algorithm to be optimized by referring to past score data. Some or all of the above processes in the scoring unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the scoring unit can input past score data into a generative AI and have the generative AI perform the optimization of the scoring algorithm.

[0054] The scoring unit can include the level of detail and transparency of job advertisements as evaluation criteria when calculating the reliability score. For example, the scoring unit can evaluate the level of detail of job advertisements and reflect it in the reliability score. The scoring unit can also evaluate the transparency of job advertisements and reflect it in the reliability score. For example, the scoring unit can comprehensively evaluate the level of detail and transparency of job advertisements and reflect it in the reliability score. This allows for a more accurate reliability assessment by including the level of detail and transparency of job advertisements as evaluation criteria. Some or all of the above processing in the scoring unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the scoring unit can input detailed data of job advertisements into a generating AI and have the generating AI calculate the reliability score.

[0055] The scoring unit can refer to a company's reputation within its industry and comparative data with competitors when calculating the reliability score. For example, the scoring unit can refer to a company's reputation within its industry and reflect it in the reliability score. The scoring unit can also refer to comparative data with competitors and evaluate the company's relative reliability. The scoring unit can also refer to benchmark data within the industry and reflect it in the reliability score. This allows for a more accurate reliability assessment by referring to a company's reputation within its industry and comparative data with competitors. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input company reputation data into a generative AI and have the generative AI calculate the reliability score.

[0056] The scoring unit can consider a company's environmental, social, and governance (ESG) score when calculating the reliability score. For example, the scoring unit can refer to a company's environmental score and reflect it in the reliability score. The scoring unit can also refer to a company's social score and reflect it in the reliability score. The scoring unit can also refer to a company's governance score and reflect it in the reliability score. This allows for a more comprehensive reliability assessment by considering a company's ESG score. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input a company's ESG data into a generative AI and have the generative AI calculate the reliability score.

[0057] The withdrawal unit can optimize the withdrawal algorithm by referring to past withdrawal history when a withdrawal occurs. For example, the withdrawal unit optimizes the withdrawal algorithm based on past withdrawal history. The withdrawal unit can also adjust the withdrawal criteria based on past withdrawal history. The withdrawal unit can also improve the accuracy of withdrawals based on past withdrawal history. This allows the withdrawal algorithm to be optimized by referring to past withdrawal history. Some or all of the above processing in the withdrawal unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the withdrawal unit can input past withdrawal history data into a generative AI and have the generative AI perform the optimization of the withdrawal algorithm.

[0058] The withdrawal unit can customize the method of notifying users of a job posting when it is withdrawn, according to the content of the job posting. For example, the withdrawal unit can customize the content of the withdrawal notification according to the content of the job posting. The withdrawal unit can also customize the timing of the withdrawal notification according to the content of the job posting. The withdrawal unit can also customize the method of notification (email, SMS, etc.) according to the content of the job posting. By customizing the notification method according to the content of the job posting, more appropriate notifications can be made. Some or all of the above processing in the withdrawal unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the withdrawal unit can input the content data of the job posting into a generating AI and have the generating AI perform the customization of the notification method.

[0059] The withdrawal unit can refer to the company's past reliability score and reputation data when a withdrawal is made. For example, the withdrawal unit can refer to the company's past reliability score and reflect it in the withdrawal decision. The withdrawal unit can also refer to the company's reputation data and reflect it in the withdrawal decision. For example, the withdrawal unit can comprehensively refer to the company's past reliability score and reputation data and reflect it in the withdrawal decision. This allows for a more accurate withdrawal decision by referring to the company's past reliability score and reputation data. Some or all of the above processing in the withdrawal unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the withdrawal unit can input the company's reliability score data into a generating AI and have the generating AI execute the withdrawal decision.

[0060] The API unit can provide customized APIs tailored to the characteristics of each company's job site when providing APIs. For example, the API unit can provide customized API endpoints tailored to the characteristics of each company's job site. The API unit can also provide customized API response formats tailored to the characteristics of each company's job site. The API unit can also provide customized API authentication methods tailored to the characteristics of each company's job site. This allows for the provision of more appropriate information by providing APIs tailored to the characteristics of each company's job site. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input job site characteristic data into a generative AI and have the generative AI perform the provision of a customized API.

[0061] The API unit can optimize the API delivery method by referring to past API usage history when providing an API. For example, the API unit can optimize the API endpoint based on past API usage history. The API unit can also optimize the API response format based on past API usage history. The API unit can also optimize the API authentication method based on past API usage history. In this way, the delivery method can be optimized by referring to past API usage history. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input past API usage history data into a generative AI and have the generative AI perform the optimization of the delivery method.

[0062] The API unit can provide customized APIs tailored to the characteristics of each company's job site when providing APIs. For example, the API unit can provide customized API endpoints tailored to the characteristics of each company's job site. The API unit can also provide customized API response formats tailored to the characteristics of each company's job site. The API unit can also provide customized API authentication methods tailored to the characteristics of each company's job site. This allows for the provision of more appropriate information by providing APIs tailored to the characteristics of each company's job site. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input job site characteristic data into a generative AI and have the generative AI perform the provision of a customized API.

[0063] The API unit can optimize the API delivery method by referring to past API usage history when providing an API. For example, the API unit can optimize the API endpoint based on past API usage history. The API unit can also optimize the API response format based on past API usage history. The API unit can also optimize the API authentication method based on past API usage history. In this way, the delivery method can be optimized by referring to past API usage history. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input past API usage history data into a generative AI and have the generative AI perform the optimization of the delivery method.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] The extraction unit can extract job descriptions, salary information, and company information not only from text data but also from audio data of job advertisements. For example, it can analyze audio messages included in job advertisements to supplement information such as company descriptions and details of job duties. It can also integrate the information extracted from audio data with text data to provide more accurate information. Furthermore, speech recognition technology and natural language processing technology can be used to analyze the audio data. This allows for a more multifaceted understanding of the job advertisement content by extracting information from audio data as well.

[0066] The verification unit can analyze a company's supply chain information and reflect it in the reliability assessment when verifying a company's reliability. For example, it can verify the reliability of a company's major trading partners and suppliers and reflect this in the company's reliability assessment. It can also evaluate the transparency and sustainability of the entire supply chain and reflect this in the company's reliability score. Furthermore, supply chain management systems and databases can be used for analyzing supply chain information. This allows for a more comprehensive reliability assessment by considering a company's supply chain information.

[0067] The analysis department can evaluate the balance between job content and salary by considering the skill and qualification requirements for the job. For example, it can assess the level of skills and qualifications required for the job and analyze whether the salary is commensurate with them. It can also refer to the market value of skills and qualifications and evaluate the balance with salary. Furthermore, it can utilize databases and algorithms to evaluate the skill and qualification requirements. This allows for a more accurate balance evaluation by considering the skill and qualification requirements for the job.

[0068] The scoring unit can include a company's customer satisfaction data as an evaluation criterion when calculating the reliability score. For example, it can refer to the results of a company's customer satisfaction survey and reflect them in the reliability score. It can also analyze customer feedback and reviews and reflect them in the company's reliability evaluation. Furthermore, customer relationship management systems and databases can be used to analyze customer satisfaction data. By including a company's customer satisfaction data as an evaluation criterion, a more accurate reliability evaluation can be achieved.

[0069] The withdrawal function allows for customization of the withdrawal notification method according to the content of the job advertisement. For example, the content of the withdrawal notification can be customized according to the content of the job advertisement. The timing of the withdrawal notification can also be customized according to the content of the job advertisement. Furthermore, the method of withdrawal notification (email, SMS, etc.) can be customized according to the content of the job advertisement. This allows for more appropriate notifications by customizing the notification method according to the content of the job advertisement.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The extraction unit extracts job description, salary, and company information from the job advertisement. For example, it analyzes the text data of the job advertisement and uses natural language processing technology and machine learning algorithms to identify job description, salary, and company information. The extraction unit uses an AI model that takes the text data of the job advertisement as input and outputs job description, salary, and company information. Step 2: The verification unit verifies the company's registration information based on the information extracted by the extraction unit. For example, it checks against a company registration information database to verify the company's reliability. The verification unit accesses the company registration information database and uses an AI model to verify the company's basic information. Step 3: The analysis unit analyzes the balance between job duties and salary based on the information verified by the verification unit. For example, it analyzes the balance between job duties and salary using criteria and algorithms for evaluating the balance between job duties and salary. The analysis unit uses an AI model that takes the balance between job duties and salary as input and outputs the evaluation results of the balance. Step 4: The scoring unit scores the reliability of the job postings based on the information analyzed by the analysis unit. For example, it scores the reliability of job postings using criteria and algorithms for evaluating the reliability of job postings. The scoring unit uses an AI model that takes the reliability of job postings as input and outputs a reliability score. Step 5: The withdrawal unit withdraws job postings with low scores determined by the scoring unit. For example, it uses criteria and algorithms to automatically withdraw job postings with low scores. The withdrawal unit uses an AI model that takes job postings with low scores as input and outputs instructions to withdraw them.

[0072] (Example of form 2) The AI ​​agent for detecting illegal part-time jobs according to an embodiment of the present invention is a cutting-edge AI solution that scrutinizes job postings on part-time job services and determines the potential risks of illegal part-time jobs. The AI ​​agent for detecting illegal part-time jobs automatically extracts job descriptions, salaries, and company information from job advertisements, verifies company registration information, and analyzes the balance between job descriptions and salaries. This enhances the reliability of job postings and provides a safe environment for users. For example, the AI ​​agent for detecting illegal part-time jobs automatically extracts job descriptions, salaries, and company information from job advertisements. Next, it verifies company registration information based on the extracted information. Furthermore, it analyzes the balance between job descriptions and salaries and scores the reliability of the job postings. Job postings with low scores are judged to have a high risk of being illegal part-time jobs and are removed before being posted on part-time job services. This enhances the reliability of job postings and provides an environment where users can use job postings with peace of mind. In addition, the AI ​​agent can be deployed as an API to each company's job site, contributing to the improvement of the reliability of the entire job market. Thus, the AI ​​agent for detecting illegal part-time jobs can enhance the reliability of job postings and provide a safe environment for users.

[0073] The AI ​​agent for determining whether a job posting is illegal according to this embodiment comprises an extraction unit, a verification unit, an analysis unit, a scoring unit, and a withdrawal unit. The extraction unit extracts job description, salary, and company information from the job advertisement. The extraction unit, for example, analyzes the text data of the job advertisement to identify job description, salary, and company information. The extraction unit can, for example, use natural language processing technology to analyze the text data of the job advertisement and extract job description, salary, and company information. The extraction unit can also use machine learning algorithms to identify job description, salary, and company information from the text data of the job advertisement. For example, the extraction unit can use an AI model that takes the text data of the job advertisement as input and outputs job description, salary, and company information to extract the information. The verification unit verifies the company's registration information based on the information extracted by the extraction unit. The verification unit, for example, checks against a company registration information database to verify the reliability of the company. The verification unit can, for example, access a company registration information database to verify the company's basic information. The verification unit can also check against a company registration information database to verify the reliability of the company. For example, the verification unit can verify the reliability of a company using an AI model that takes a company registration information database as input and outputs the reliability of the company. The analysis unit analyzes the balance between job content and salary based on the information verified by the verification unit. The analysis unit determines, for example, the balance between job content and salary. The analysis unit can analyze the balance between job content and salary using, for example, criteria for evaluating the balance between job content and salary. The analysis unit can also analyze the balance between job content and salary using an algorithm for evaluating the balance between job content and salary. For example, the analysis unit can analyze the balance between job content and salary using an AI model that takes the balance between job content and salary as input and outputs the evaluation result of the balance. The scoring unit scores the reliability of the job posting based on the information analyzed by the analysis unit. The scoring unit scores the reliability of the job posting, for example. The scoring unit can score the reliability of the job posting using, for example, criteria for evaluating the reliability of the job posting.Furthermore, the scoring unit can also score the reliability of job postings using an algorithm for evaluating the reliability of job postings. For example, the scoring unit can score the reliability of job postings using an AI model that takes the reliability of job postings as input and outputs a reliability score. The withdrawal unit withdraws job postings that have low scores determined by the scoring unit. The withdrawal unit withdraws job postings, for example, that have low scores. The withdrawal unit can withdraw job postings using, for example, criteria for automatically withdrawing job postings with low scores. The withdrawal unit can also withdraw job postings using an algorithm for automatically withdrawing job postings with low scores. For example, the withdrawal unit can withdraw job postings using an AI model that takes job postings with low scores as input and outputs a withdrawal instruction. As a result, the AI ​​agent for determining whether a job is illegal according to the embodiment can enhance the reliability of job postings and provide an environment in which users can feel secure.

[0074] The extraction unit extracts job descriptions, salaries, and company information from job advertisements. Specifically, the extraction unit uses natural language processing (NLP) techniques to analyze the text data of job advertisements and identify job descriptions, salaries, and company information. Natural language processing techniques include morphological analysis, grammatical analysis, and semantic analysis, and by combining these, it is possible to accurately extract the necessary information from the text data of job advertisements. For example, morphological analysis is used to divide the text data into words, grammatical analysis is used to analyze the structure of sentences, and semantic analysis is used to understand the meaning of sentences. This allows the extraction unit to accurately extract job descriptions, salaries, and company information from the text data of job advertisements. The extraction unit can also use machine learning algorithms to identify job descriptions, salaries, and company information from the text data of job advertisements. Machine learning algorithms include supervised learning, unsupervised learning, and reinforcement learning, and by combining these, it is possible to extract the necessary information from the text data of job advertisements with high accuracy. For example, supervised learning is used to learn from past job advertisement data and identify job descriptions, salaries, and company information from new job advertisement data. Furthermore, unsupervised learning is used to cluster job advertisement data, identifying job descriptions, salaries, and company information from similar job advertisements. Reinforcement learning can also be used to improve the accuracy of the job advertisement data analysis. As a result, the extraction unit can extract job descriptions, salaries, and company information from the text data of job advertisements with high accuracy.

[0075] The verification unit verifies the company's registration information based on the information extracted by the extraction unit. Specifically, the verification unit compares the information with the company's registration information database to verify the company's reliability. The company's registration information database includes basic company information, officer information, and financial information, and by comparing this information, the company's reliability can be verified. For example, basic company information such as company name, address, date of establishment, and capital can be verified, and officer information such as representative name, officer names, and officer histories can be verified. Financial information such as sales, profits, and liabilities can also be verified. This allows the verification unit to comprehensively evaluate the company's reliability. Furthermore, the verification unit can access the company's registration information database and verify the company's basic information. Basic company information includes company name, address, date of establishment, and capital, and by verifying this information, the company's reliability can be evaluated. In addition, the verification unit can verify the company's reliability by comparing it with the company's registration information database. For example, the reliability of a company can be verified using an AI model that takes the company's registration information database as input and outputs the reliability of the company. The AI ​​model incorporates machine learning algorithms and can accurately assess a company's reliability by learning from past data. This allows the verification unit to quickly and accurately verify the company's reliability.

[0076] The Analysis Department analyzes the balance between job content and salary based on information verified by the Verification Department. Specifically, the Analysis Department analyzes the balance between job content and salary using criteria for determining this balance. These criteria include the difficulty of the work, the volume of work, the risks of the work, and the level of specialization required for the work. Using these criteria, the Analysis Department can comprehensively evaluate the balance between job content and salary. For example, if the work is difficult or the volume of work is high, it is desirable for the salary to be set high. Similarly, if the work is high-risk or highly specialized, it is desirable for the salary to be set high. This allows the Analysis Department to comprehensively evaluate the balance between job content and salary. The Analysis Department can also analyze the balance between job content and salary using algorithms. These algorithms incorporate machine learning algorithms, and by learning from past data, they can evaluate the balance between job content and salary with high accuracy. For example, the Analysis Department can analyze the balance between job content and salary using an AI model that takes the balance between job content and salary as input and outputs the evaluation result. This allows the Analysis Department to analyze the balance between job content and salary quickly and accurately.

[0077] The scoring unit scores the reliability of job postings based on the information analyzed by the analysis unit. Specifically, the scoring unit scores the reliability of job postings using criteria for evaluating their reliability. These criteria include the reliability of the company, the balance between job duties and salary, the accuracy of the job advertisement content, and the history of past job advertisements. Using these criteria, the reliability of job postings can be comprehensively evaluated. For example, if the company has high reliability or the balance between job duties and salary is good, the job posting will be evaluated as highly reliable. Similarly, if the content of the job advertisement is accurate or the history of past job advertisements is good, the job posting will also be evaluated as highly reliable. This allows the scoring unit to comprehensively evaluate the reliability of job postings. The scoring unit can also score the reliability of job postings using an algorithm for evaluating their reliability. The algorithm incorporates a machine learning algorithm, which can evaluate the reliability of job postings with high accuracy by learning from past data. For example, the reliability of job postings can be scored using an AI model that takes the reliability of job postings as input and outputs a reliability score. This allows the scoring unit to score the reliability of job postings quickly and accurately.

[0078] The withdrawal unit withdraws job postings that have low scores determined by the scoring unit. Specifically, the withdrawal unit withdraws job postings using criteria for automatically withdrawing low-scoring job postings. These criteria include a reliability score threshold, past withdrawal history, and the accuracy of the job advertisement content. Using these criteria, the unit can automatically withdraw low-scoring job postings. For example, if the reliability score is below the threshold, if there is a history of many past withdrawals, or if the job advertisement content is inaccurate, the job posting will be judged as having a low score and will be automatically withdrawn. This allows the withdrawal unit to withdraw low-scoring job postings quickly and accurately. The withdrawal unit can also withdraw job postings using an algorithm for automatically withdrawing low-scoring job postings. The algorithm incorporates a machine learning algorithm, and by learning from past data, it can withdraw low-scoring job postings with high accuracy. For example, a job posting can be withdrawn using an AI model that takes low-scoring job postings as input and outputs a withdrawal instruction. This allows the withdrawal unit to withdraw low-scoring job postings quickly and accurately.

[0079] The API unit can be deployed to each company's job posting website. For example, the API unit can provide the functionality of an AI agent for detecting illegal job postings as an API to each company's job posting website that provides job information. The API unit can, for example, provide an API endpoint for evaluating the reliability of job postings. The API unit can also provide API documentation for evaluating the reliability of job postings. For example, the API unit can provide an API that takes an API endpoint for evaluating the reliability of job postings as input and outputs the reliability evaluation result. This can contribute to improving the reliability of the entire job market. Some or all of the above processing in the API unit may be performed using AI, for example, or without using AI. For example, the API unit can input an API endpoint for evaluating the reliability of job postings into a generating AI and have the generating AI execute the generation of the reliability evaluation result.

[0080] The extraction unit can analyze the text data of job advertisements to identify job duties, salary, and company information. For example, the extraction unit can analyze the text data of job advertisements using natural language processing technology to identify job duties, salary, and company information. The extraction unit can also use machine learning algorithms to identify job duties, salary, and company information from the text data of job advertisements. For example, the extraction unit can use an AI model that takes the text data of job advertisements as input and outputs job duties, salary, and company information to extract the information. This allows for accurate information extraction from the text data of job advertisements. Some or all of the above-described processes in the extraction unit may be performed using AI, for example, or without AI. For example, the extraction unit can input the text data of job advertisements into a generating AI and have the generating AI perform the identification of job duties, salary, and company information.

[0081] The verification unit can verify the reliability of a company by comparing it with a company registration information database. For example, the verification unit can access a company registration information database and verify the company's basic information. The verification unit can also verify the reliability of a company by comparing it with a company registration information database. For example, the verification unit can verify the reliability of a company using an AI model that takes a company registration information database as input and outputs the reliability of the company. This allows for accurate verification of the reliability of a company. Some or all of the above-described processes in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input a company registration information database into a generating AI and have the generating AI perform the verification of the reliability of the company.

[0082] The analysis unit can determine the balance between job content and salary. The analysis unit can analyze the balance between job content and salary using, for example, criteria for evaluating the balance between job content and salary. The analysis unit can also analyze the balance between job content and salary using, for example, algorithms for evaluating the balance between job content and salary. For example, the analysis unit can analyze the balance between job content and salary using an AI model that takes the balance between job content and salary as input and outputs the balance evaluation result. This allows for an accurate determination of the balance between job content and salary. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input the balance between job content and salary into a generating AI and have the generating AI perform the balance evaluation.

[0083] The scoring unit can score the reliability of job postings. The scoring unit scores the reliability of job postings using, for example, criteria for evaluating the reliability of job postings. The scoring unit can also score the reliability of job postings using, for example, an algorithm for evaluating the reliability of job postings. For example, the scoring unit can score the reliability of job postings using an AI model that takes the reliability of job postings as input and outputs a reliability score. By scoring the reliability of job postings, highly reliable job postings can be provided. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or without AI. For example, the scoring unit can input the reliability of job postings into a generating AI and have the generating AI calculate the reliability score.

[0084] The withdrawal unit can withdraw job postings with low scores. The withdrawal unit withdraws job postings using, for example, criteria for automatically withdrawing job postings with low scores. The withdrawal unit can also withdraw job postings using, for example, an algorithm for automatically withdrawing job postings with low scores. For example, the withdrawal unit can withdraw job postings using an AI model that takes job postings with low scores as input and outputs a withdrawal instruction. This eliminates unreliable job postings by withdrawing job postings with low scores. Some or all of the above processing in the withdrawal unit may be performed using, for example, AI, or not using AI. For example, the withdrawal unit can input job postings with low scores into a generating AI and have the generating AI execute a withdrawal instruction.

[0085] The extraction unit can estimate the user's emotions and adjust the job advertisement analysis method based on the estimated user emotions. For example, if the user is feeling anxious, the extraction unit can provide detailed analysis results to reassure them. For example, if the user is in a hurry, the extraction unit can provide concise analysis results to allow them to quickly obtain information. For example, if the user is interested, the extraction unit can provide relevant additional information to deepen their interest. This allows for more appropriate analysis results to be provided by adjusting the analysis method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the extraction unit may be performed using AI, for example, or not using AI. For example, the extraction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0086] The extraction unit can extract job descriptions, salary information, and company information not only from the text data of job advertisements but also from images and videos. For example, the extraction unit can analyze images included in job advertisements to identify company logos and office photos, supplementing company information. For example, the extraction unit can extract descriptions of job duties and workplace atmosphere from videos included in job advertisements. For example, the extraction unit can extract salary and benefits information from infographics included in job advertisements. This allows for obtaining more information by extracting information from images and videos as well. Some or all of the above-described processes in the extraction unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the extraction unit can input image and video data from job advertisements into a generating AI and have the generating AI perform the extraction of job descriptions, salary information, and company information.

[0087] The extraction unit can refer to past data of job advertisements and build a feedback loop to improve extraction accuracy. For example, the extraction unit can improve the extraction accuracy of job descriptions based on past job advertisement data. The extraction unit can also improve the extraction accuracy of salary information based on past job advertisement data. The extraction unit can also improve the extraction accuracy of company information based on past job advertisement data. In this way, extraction accuracy can be improved by referring to past data. Some or all of the above processing in the extraction unit may be performed using, for example, a generation AI, or without a generation AI. For example, the extraction unit can input past job advertisement data into a generation AI and have the generation AI perform the extraction accuracy improvement.

[0088] The extraction unit can estimate the user's emotions and determine the priority of information to extract based on the estimated emotions. For example, if the user is feeling anxious, the extraction unit may prioritize extracting company information and verify its reliability. If the user is in a hurry, the extraction unit may prioritize extracting salary information to enable quick decision-making. If the user is interested, the extraction unit may prioritize extracting job-related information to deepen their interest. This allows for the provision of more appropriate information by prioritizing information according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, 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 extraction unit may be performed using AI or not. For example, the extraction unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0089] The extraction unit can analyze a company's social media activities and extract relevant information when analyzing job advertisements. For example, the extraction unit can extract the latest news and event information from a company's official social media accounts. The extraction unit can also extract employee profiles and career path information from a company's social media pages. For example, the extraction unit can extract information about corporate culture and employee benefits from a company's social media pages. This allows more relevant information to be obtained by analyzing a company's social media activities. Some or all of the above processing in the extraction unit may be performed using, for example, a generative AI, or without a generative AI. For example, the extraction unit can input the company's social media data into a generative AI and have the generative AI perform the extraction of relevant information.

[0090] The extraction unit can extract highly relevant information by considering the geographical location of companies when analyzing job advertisements. For example, the extraction unit can extract nearby transportation and access information based on the company's location. The extraction unit can also extract information on local living expenses and prices based on the company's location. The extraction unit can also extract information on surrounding housing and rental properties based on the company's location. This allows for the provision of more relevant information by considering the company's geographical location. Some or all of the above processing in the extraction unit may be performed using, for example, a generating AI, or without a generating AI. For example, the extraction unit can input the company's geographical location data into a generating AI and have the generating AI perform the extraction of relevant information.

[0091] The verification unit can estimate the user's emotions and adjust the criteria for verifying the company's trustworthiness based on the estimated user emotions. For example, if the user is feeling anxious, the verification unit will verify the company's trustworthiness using strict criteria. For example, if the user is in a hurry, the verification unit can also use simplified criteria to quickly verify trustworthiness. For example, if the user is interested, the verification unit can also verify the company's trustworthiness using detailed criteria. This allows for more appropriate trustworthiness verification by adjusting the trustworthiness verification criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0092] The verification unit can cross-reference not only the company's registration information database but also a database of the company's past legal troubles and reputation. For example, the verification unit can verify the company's basic information by cross-referencing the company's registration information database. The verification unit can also verify legal risks by cross-referencing the company's past legal troubles database. The verification unit can also verify the company's reliability by cross-referencing the company's reputation database. This allows for a more accurate verification of reliability by cross-referencing the company's past legal troubles and reputation database. Some or all of the above-described processes in the verification unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the verification unit can input the company's legal trouble data into a generating AI and have the generating AI perform the legal risk verification.

[0093] The verification unit can analyze a company's financial situation and reflect this in the reliability assessment when verifying the company's reliability. For example, the verification unit can analyze a company's financial statements to confirm its financial soundness. The verification unit can also analyze a company's profitability to confirm the stability of its management. The verification unit can also analyze a company's debt situation to confirm its financial risks. This allows for a more accurate reliability assessment by analyzing a company's financial situation. Some or all of the above-described processes in the verification unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the verification unit can input a company's financial data into a generating AI and have the generating AI perform an analysis of its financial situation.

[0094] The verification unit can estimate the user's emotions and adjust how the verification results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the verification unit can display detailed verification results to provide reassurance. For example, if the user is in a hurry, the verification unit can display concise verification results to allow them to quickly obtain information. For example, if the user is interested, the verification unit can display relevant additional information to deepen their interest. This allows for more appropriate information to be provided by adjusting how the verification results are displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, 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 verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0095] The verification unit can refer to a company's reputation within its industry and comparative data with competitors when verifying a company's reliability. For example, the verification unit can verify a company's reputation within its industry and evaluate its reliability. The verification unit can also refer to comparative data with competitors and evaluate the company's relative reliability. The verification unit can also refer to benchmark data within the industry and evaluate the company's reliability. This allows for a more accurate reliability assessment by referring to a company's reputation within its industry and comparative data with competitors. Some or all of the above processing in the verification unit may be performed using, for example, a generative AI, or without a generative AI. For example, the verification unit can input company reputation data into a generative AI and have the generative AI perform the reliability evaluation.

[0096] The verification unit can consider a company's environmental, social, and governance (ESG) score when verifying the company's reliability. For example, the verification unit can check a company's environmental score and evaluate its environmental considerations. For example, the verification unit can also check a company's social score and evaluate its social responsibility. For example, the verification unit can check a company's governance score and evaluate the soundness of its management. This allows for a more comprehensive reliability assessment by considering a company's ESG score. Some or all of the above processing in the verification unit may be performed using, for example, a generating AI, or without a generating AI. For example, the verification unit can input a company's ESG data into a generating AI and have the generating AI perform the ESG score evaluation.

[0097] The analysis unit can estimate the user's emotions and adjust the criteria for analyzing the balance between work content and salary based on the estimated user emotions. For example, if the user is feeling anxious, the analysis unit will analyze the balance between work content and salary using strict criteria. For example, if the user is in a hurry, the analysis unit can also use simplified criteria to quickly analyze the balance. For example, if the user is interested, the analysis unit can also analyze the balance between work content and salary using detailed criteria. This allows for a more appropriate balance analysis by adjusting the analysis criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0098] The analysis department can improve the accuracy of its analysis when analyzing the balance between job content and salary by referring to past similar job posting data. For example, the analysis department can improve the accuracy of its analysis of job content based on past similar job posting data. The analysis department can also improve the accuracy of its analysis of salary based on past similar job posting data. The analysis department can also improve the accuracy of its analysis of the balance between job content and salary based on past similar job posting data. In this way, the analysis department can improve the accuracy of its analysis by referring to past similar job posting data. Some or all of the above processes in the analysis department may be performed using, for example, a generation AI, or not using a generation AI. For example, the analysis department can input past similar job posting data into a generation AI and have the generation AI perform the improvement of analysis accuracy.

[0099] The analysis department can evaluate the balance between job content and salary by considering the risks and workload of the work. For example, the analysis department can evaluate the risks of the work and analyze the balance with salary. The analysis department can also evaluate the workload and analyze the balance with salary. The analysis department can also comprehensively evaluate the risks and workload of the work and analyze the balance with salary. This allows for a more accurate balance evaluation by considering the risks and workload of the work. Some or all of the above processes in the analysis department may be performed using, for example, a generative AI, or without using a generative AI. For example, the analysis department can input job risk data into a generative AI and have the generative AI perform a risk evaluation.

[0100] The analysis unit can estimate the user's emotions and adjust how the analysis results are displayed based on the estimated emotions. For example, if the user is feeling anxious, the analysis unit can display detailed analysis results to provide reassurance. For example, if the user is in a hurry, the analysis unit can display concise analysis results to allow them to quickly obtain information. For example, if the user is interested, the analysis unit can display relevant additional information to deepen their interest. This allows for more appropriate information to be provided by adjusting the display method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or not using AI. For example, the analysis unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0101] The analysis department can refer to industry-wide salary levels and trend data when analyzing the balance between job content and salary. For example, the analysis department can refer to industry-wide salary levels and analyze the balance between job content and salary. The analysis department can also refer to industry trend data and analyze the balance between job content and salary. The analysis department can also refer to industry benchmark data and analyze the balance between job content and salary. This allows for a more accurate balance analysis by referring to industry-wide salary levels and trend data. Some or all of the above processing in the analysis department may be performed using, for example, a generative AI, or not using a generative AI. For example, the analysis department can input industry salary data into a generative AI and have the generative AI perform a salary level evaluation.

[0102] The analysis department can consider regional living costs and price indices when analyzing the balance between job content and salary. For example, the analysis department can analyze the balance between job content and salary by considering regional living costs. The analysis department can also analyze the balance between job content and salary by considering regional price indices. The analysis department can also analyze the balance between job content and salary by comprehensively considering regional living costs and price indices. This allows for a more accurate balance analysis by considering regional living costs and price indices. Some or all of the above processing in the analysis department may be performed using, for example, a generating AI, or without using a generating AI. For example, the analysis department can input regional living cost data into a generating AI and have the generating AI perform the balance analysis.

[0103] The scoring unit can estimate the user's emotions and adjust the method for calculating the reliability score based on the estimated user emotions. For example, if the user is feeling anxious, the scoring unit can calculate a reliability score using strict criteria. For example, if the user is in a hurry, the scoring unit can also use simplified criteria to quickly calculate a reliability score. For example, if the user is interested, the scoring unit can also calculate a reliability score using detailed criteria. This allows for a more appropriate reliability assessment by adjusting the scoring method according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scoring unit may be performed using AI or not using AI. For example, the scoring unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0104] The scoring unit can optimize the scoring algorithm by referring to past score data when calculating the reliability score. For example, the scoring unit can improve the accuracy of calculating the reliability score based on past score data. The scoring unit can also optimize the scoring algorithm based on past score data. For example, the scoring unit can adjust the scoring criteria based on past score data. This allows the scoring algorithm to be optimized by referring to past score data. Some or all of the above processes in the scoring unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the scoring unit can input past score data into a generative AI and have the generative AI perform the optimization of the scoring algorithm.

[0105] The scoring unit can include the level of detail and transparency of job advertisements as evaluation criteria when calculating the reliability score. For example, the scoring unit can evaluate the level of detail of job advertisements and reflect it in the reliability score. The scoring unit can also evaluate the transparency of job advertisements and reflect it in the reliability score. For example, the scoring unit can comprehensively evaluate the level of detail and transparency of job advertisements and reflect it in the reliability score. This allows for a more accurate reliability assessment by including the level of detail and transparency of job advertisements as evaluation criteria. Some or all of the above processing in the scoring unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the scoring unit can input detailed data of job advertisements into a generating AI and have the generating AI calculate the reliability score.

[0106] The scoring unit can estimate the user's emotions and adjust how the score is displayed based on the estimated emotions. For example, if the user is feeling anxious, the scoring unit can display a detailed breakdown of the score to provide reassurance. For example, if the user is in a hurry, the scoring unit can display a concise score to allow them to quickly obtain information. For example, if the user is interested, the scoring unit can display additional relevant information to deepen their interest. This allows for more appropriate information to be provided by adjusting how the score is displayed according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the scoring unit may be performed using AI or not using AI. For example, the scoring unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0107] The scoring unit can refer to a company's reputation within its industry and comparative data with competitors when calculating the reliability score. For example, the scoring unit can refer to a company's reputation within its industry and reflect it in the reliability score. The scoring unit can also refer to comparative data with competitors and evaluate the company's relative reliability. The scoring unit can also refer to benchmark data within the industry and reflect it in the reliability score. This allows for a more accurate reliability assessment by referring to a company's reputation within its industry and comparative data with competitors. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input company reputation data into a generative AI and have the generative AI calculate the reliability score.

[0108] The scoring unit can consider a company's environmental, social, and governance (ESG) score when calculating the reliability score. For example, the scoring unit can refer to a company's environmental score and reflect it in the reliability score. The scoring unit can also refer to a company's social score and reflect it in the reliability score. The scoring unit can also refer to a company's governance score and reflect it in the reliability score. This allows for a more comprehensive reliability assessment by considering a company's ESG score. Some or all of the above processing in the scoring unit may be performed using, for example, a generative AI, or without a generative AI. For example, the scoring unit can input a company's ESG data into a generative AI and have the generative AI calculate the reliability score.

[0109] The withdrawal unit can estimate the user's emotions and adjust the withdrawal criteria based on the estimated emotions. For example, if the user is feeling anxious, the withdrawal unit may use strict criteria for withdrawal. For example, if the user is in a hurry, the withdrawal unit may use simplified criteria for quick withdrawal. For example, if the user is interested, the withdrawal unit may use detailed criteria for withdrawal. This allows for more appropriate withdrawals by adjusting the withdrawal criteria according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the withdrawal unit may be performed using AI or not using AI. For example, the withdrawal unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0110] The withdrawal unit can optimize the withdrawal algorithm by referring to past withdrawal history when a withdrawal occurs. For example, the withdrawal unit optimizes the withdrawal algorithm based on past withdrawal history. The withdrawal unit can also adjust the withdrawal criteria based on past withdrawal history. The withdrawal unit can also improve the accuracy of withdrawals based on past withdrawal history. This allows the withdrawal algorithm to be optimized by referring to past withdrawal history. Some or all of the above processing in the withdrawal unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the withdrawal unit can input past withdrawal history data into a generative AI and have the generative AI perform the optimization of the withdrawal algorithm.

[0111] The withdrawal unit can customize the method of notifying users of a job posting when it is withdrawn, according to the content of the job posting. For example, the withdrawal unit can customize the content of the withdrawal notification according to the content of the job posting. The withdrawal unit can also customize the timing of the withdrawal notification according to the content of the job posting. The withdrawal unit can also customize the method of notification (email, SMS, etc.) according to the content of the job posting. By customizing the notification method according to the content of the job posting, more appropriate notifications can be made. Some or all of the above processing in the withdrawal unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the withdrawal unit can input the content data of the job posting into a generating AI and have the generating AI perform the customization of the notification method.

[0112] The withdrawal unit can estimate the user's emotions and determine the priority of withdrawals based on the estimated emotions. For example, if the user is feeling anxious, the withdrawal unit will prioritize withdrawals. For example, if the user is in a hurry, the withdrawal unit can also perform withdrawals quickly. For example, if the user is interested, the withdrawal unit can perform withdrawals based on detailed criteria. This allows for more appropriate withdrawals by determining the priority of withdrawals according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the withdrawal unit may be performed using AI or not using AI. For example, the withdrawal unit can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0113] The withdrawal unit can refer to the company's past reliability score and reputation data when a withdrawal is made. For example, the withdrawal unit can refer to the company's past reliability score and reflect it in the withdrawal decision. The withdrawal unit can also refer to the company's reputation data and reflect it in the withdrawal decision. For example, the withdrawal unit can comprehensively refer to the company's past reliability score and reputation data and reflect it in the withdrawal decision. This allows for a more accurate withdrawal decision by referring to the company's past reliability score and reputation data. Some or all of the above processing in the withdrawal unit may be performed using, for example, a generating AI, or without using a generating AI. For example, the withdrawal unit can input the company's reliability score data into a generating AI and have the generating AI execute the withdrawal decision.

[0114] The API section can estimate the user's emotions and adjust how the API is delivered based on the estimated emotions. For example, if the user is feeling anxious, the API section can provide detailed API documentation to reassure them. If the user is in a hurry, the API section can provide concise API documentation to allow them to quickly obtain information. If the user is interested, the API section can provide additional relevant information to deepen their interest. This allows for more appropriate information to be provided by adjusting how the API is delivered according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the API section may be performed using AI or not. For example, the API section can input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0115] The API unit can provide customized APIs tailored to the characteristics of each company's job site when providing APIs. For example, the API unit can provide customized API endpoints tailored to the characteristics of each company's job site. The API unit can also provide customized API response formats tailored to the characteristics of each company's job site. The API unit can also provide customized API authentication methods tailored to the characteristics of each company's job site. This allows for the provision of more appropriate information by providing APIs tailored to the characteristics of each company's job site. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input job site characteristic data into a generative AI and have the generative AI perform the provision of a customized API.

[0116] The API unit can optimize the API delivery method by referring to past API usage history when providing an API. For example, the API unit can optimize the API endpoint based on past API usage history. The API unit can also optimize the API response format based on past API usage history. The API unit can also optimize the API authentication method based on past API usage history. In this way, the delivery method can be optimized by referring to past API usage history. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input past API usage history data into a generative AI and have the generative AI perform the optimization of the delivery method.

[0117] The API unit can estimate the user's emotions and adjust the frequency of API usage based on the estimated emotions. For example, if the user is feeling anxious, the API unit may use the API frequently to provide detailed information. For example, if the user is in a hurry, the API unit may adjust the frequency of API usage to provide information quickly. For example, if the user is interested, the API unit may adjust the frequency of API usage to provide additional relevant information. This allows for more appropriate information to be provided by adjusting the frequency of API usage according to the user's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the API unit may be performed using AI or not using AI. For example, the API unit may input user emotion data into a generative AI and have the generative AI perform emotion estimation.

[0118] The API unit can provide customized APIs tailored to the characteristics of each company's job site when providing APIs. For example, the API unit can provide customized API endpoints tailored to the characteristics of each company's job site. The API unit can also provide customized API response formats tailored to the characteristics of each company's job site. The API unit can also provide customized API authentication methods tailored to the characteristics of each company's job site. This allows for the provision of more appropriate information by providing APIs tailored to the characteristics of each company's job site. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input job site characteristic data into a generative AI and have the generative AI perform the provision of a customized API.

[0119] The API unit can optimize the API delivery method by referring to past API usage history when providing an API. For example, the API unit can optimize the API endpoint based on past API usage history. The API unit can also optimize the API response format based on past API usage history. The API unit can also optimize the API authentication method based on past API usage history. In this way, the delivery method can be optimized by referring to past API usage history. Some or all of the above processing in the API unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the API unit can input past API usage history data into a generative AI and have the generative AI perform the optimization of the delivery method.

[0120] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0121] The extraction unit can extract job descriptions, salary information, and company information not only from text data but also from audio data of job advertisements. For example, it can analyze audio messages included in job advertisements to supplement information such as company descriptions and details of job duties. It can also integrate the information extracted from audio data with text data to provide more accurate information. Furthermore, speech recognition technology and natural language processing technology can be used to analyze the audio data. This allows for a more multifaceted understanding of the job advertisement content by extracting information from audio data as well.

[0122] The verification unit can analyze a company's supply chain information and reflect it in the reliability assessment when verifying a company's reliability. For example, it can verify the reliability of a company's major trading partners and suppliers and reflect this in the company's reliability assessment. It can also evaluate the transparency and sustainability of the entire supply chain and reflect this in the company's reliability score. Furthermore, supply chain management systems and databases can be used for analyzing supply chain information. This allows for a more comprehensive reliability assessment by considering a company's supply chain information.

[0123] The analysis department can evaluate the balance between job content and salary by considering the skill and qualification requirements for the job. For example, it can assess the level of skills and qualifications required for the job and analyze whether the salary is commensurate with them. It can also refer to the market value of skills and qualifications and evaluate the balance with salary. Furthermore, it can utilize databases and algorithms to evaluate the skill and qualification requirements. This allows for a more accurate balance evaluation by considering the skill and qualification requirements for the job.

[0124] The scoring unit can include a company's customer satisfaction data as an evaluation criterion when calculating the reliability score. For example, it can refer to the results of a company's customer satisfaction survey and reflect them in the reliability score. It can also analyze customer feedback and reviews and reflect them in the company's reliability evaluation. Furthermore, customer relationship management systems and databases can be used to analyze customer satisfaction data. By including a company's customer satisfaction data as an evaluation criterion, a more accurate reliability evaluation can be achieved.

[0125] The withdrawal function allows for customization of the withdrawal notification method according to the content of the job advertisement. For example, the content of the withdrawal notification can be customized according to the content of the job advertisement. The timing of the withdrawal notification can also be customized according to the content of the job advertisement. Furthermore, the method of withdrawal notification (email, SMS, etc.) can be customized according to the content of the job advertisement. This allows for more appropriate notifications by customizing the notification method according to the content of the job advertisement.

[0126] The extraction unit can estimate the user's emotions and adjust the job advertisement analysis method based on the estimated user emotions. For example, if the user is feeling anxious, it can provide detailed analysis results to reassure them. If the user is in a hurry, it can provide concise analysis results to allow them to quickly obtain information. Furthermore, if the user is interested, it can provide relevant additional information to deepen their interest. In this way, by adjusting the analysis method according to the user's emotions, more appropriate analysis results can be provided.

[0127] The verification unit can estimate the user's emotions and adjust the criteria for verifying the company's trustworthiness based on those estimated emotions. For example, if the user is feeling anxious, the company's trustworthiness can be verified using strict criteria. If the user is in a hurry, simplified criteria can be used to quickly verify trustworthiness. Furthermore, if the user is interested, the company's trustworthiness can be verified using detailed criteria. This allows for more appropriate trustworthiness verification by adjusting the criteria according to the user's emotions.

[0128] The analytics department can estimate user emotions and adjust the criteria for analyzing the balance between job content and salary based on those estimated emotions. For example, if a user is feeling anxious, the analysis can be performed using strict criteria. If a user is in a hurry, simplified criteria can be used for a quick balance analysis. Furthermore, if a user is interested, the analysis can be performed using detailed criteria. This allows for a more appropriate balance analysis by adjusting the analysis criteria according to the user's emotions.

[0129] The scoring unit can estimate the user's emotions and adjust the reliability score calculation method based on those emotions. For example, if the user is feeling anxious, a strict reliability score can be calculated. If the user is in a hurry, a simplified standard can be used to quickly calculate the reliability score. Furthermore, if the user is interested, a detailed standard can be used to calculate the reliability score. This allows for a more appropriate reliability assessment by adjusting the scoring method according to the user's emotions.

[0130] The withdrawal function can estimate the user's emotions and adjust the withdrawal criteria based on those emotions. For example, if the user is feeling anxious, a stricter withdrawal criterion can be used. If the user is in a hurry, a simplified criterion can be used for a quick withdrawal. Furthermore, if the user is interested, a more detailed criterion can be used for withdrawal. This allows for more appropriate withdrawals by adjusting the withdrawal criteria according to the user's emotions.

[0131] The following briefly describes the processing flow for example form 2.

[0132] Step 1: The extraction unit extracts job description, salary, and company information from the job advertisement. For example, it analyzes the text data of the job advertisement and uses natural language processing technology and machine learning algorithms to identify job description, salary, and company information. The extraction unit uses an AI model that takes the text data of the job advertisement as input and outputs job description, salary, and company information. Step 2: The verification unit verifies the company's registration information based on the information extracted by the extraction unit. For example, it checks against a company registration information database to verify the company's reliability. The verification unit accesses the company registration information database and uses an AI model to verify the company's basic information. Step 3: The analysis unit analyzes the balance between job duties and salary based on the information verified by the verification unit. For example, it analyzes the balance between job duties and salary using criteria and algorithms for evaluating the balance between job duties and salary. The analysis unit uses an AI model that takes the balance between job duties and salary as input and outputs the evaluation results of the balance. Step 4: The scoring unit scores the reliability of the job postings based on the information analyzed by the analysis unit. For example, it scores the reliability of job postings using criteria and algorithms for evaluating the reliability of job postings. The scoring unit uses an AI model that takes the reliability of job postings as input and outputs a reliability score. Step 5: The withdrawal unit withdraws job postings with low scores determined by the scoring unit. For example, it uses criteria and algorithms to automatically withdraw job postings with low scores. The withdrawal unit uses an AI model that takes job postings with low scores as input and outputs instructions to withdraw them.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] Each of the multiple elements described above, including the extraction unit, verification unit, analysis unit, scoring unit, and withdrawal unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the smart device 14 and analyzes the text data of the job advertisement to extract job description, salary, and company information. The verification unit is implemented by the identification processing unit 290 of the data processing unit 12 and verifies the reliability of the company by comparing it with the company's registration information database. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the balance between job description and salary. The scoring unit is implemented by the identification processing unit 290 of the data processing unit 12 and scores the reliability of the job information. The withdrawal unit is implemented by the control unit 46A of the smart device 14 and automatically withdraws job information with a low score. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0137] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] Each of the multiple elements described above, including the extraction unit, verification unit, analysis unit, scoring unit, and withdrawal unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the extraction unit is implemented by the control unit 46A of the smart glasses 214 and analyzes the text data of the job advertisement to extract job description, salary, and company information. The verification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and verifies the reliability of the company by comparing it with the company's registration information database. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the balance between job description and salary. The scoring unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and scores the reliability of the job information. The withdrawal unit is implemented by, for example, the control unit 46A of the smart glasses 214 and automatically withdraws job information with a low score. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0153] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] Each of the multiple elements described above, including the extraction unit, verification unit, analysis unit, scoring unit, and withdrawal unit, is implemented in 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 analyzes the text data of the job advertisement to extract job description, salary, and company information. The verification unit is implemented by the identification processing unit 290 of the data processing unit 12 and verifies the reliability of the company by comparing it with the company's registration information database. The analysis unit is implemented by the identification processing unit 290 of the data processing unit 12 and analyzes the balance between job description and salary. The scoring unit is implemented by the identification processing unit 290 of the data processing unit 12 and scores the reliability of the job information. The withdrawal unit is implemented by the control unit 46A of the headset terminal 314 and automatically withdraws job information with a low score. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0169] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.).

[0182] 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.

[0183] 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.

[0184] 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.

[0185] Each of the multiple elements described above, including the extraction unit, verification unit, analysis unit, scoring unit, and withdrawal 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 and analyzes the text data of the job advertisement to extract job description, salary, and company information. The verification unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and verifies the reliability of the company by comparing it with the company's registration information database. The analysis unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and analyzes the balance between job description and salary. The scoring unit is implemented by, for example, the identification processing unit 290 of the data processing unit 12 and scores the reliability of the job information. The withdrawal unit is implemented by, for example, the control unit 46A of the robot 414 and automatically withdraws job information with a low score. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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."

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] (Note 1) An extraction unit that extracts job descriptions, salaries, and company information from job advertisements, A verification unit confirms the company's registration information based on the information extracted by the extraction unit, Based on the information confirmed by the aforementioned verification unit, an analysis unit analyzes the balance between job duties and salary, A scoring unit that scores the reliability of job postings based on the information analyzed by the aforementioned analysis unit, The system includes a withdrawal unit that withdraws job postings with low scores determined by the scoring unit. A system characterized by the following features. (Note 2) It includes an API and will be deployed to various companies' job posting websites. The system described in Appendix 1, characterized by the features described herein. (Note 3) The extraction unit is We analyze the text data of job advertisements to identify job duties, salary, and company information. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned verification unit is The reliability of a company is verified by cross-referencing it with the company's registration information database. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit is Determine the balance between job duties and salary. The system described in Appendix 1, characterized by the features described herein. (Note 6) The scoring unit, Score the reliability of job postings. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned withdrawal section is, Remove job postings with low scores. The system described in Appendix 1, characterized by the features described herein. (Note 8) The extraction unit is We estimate user sentiment and adjust the job advertisement analysis method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The extraction unit is In addition to text data from job advertisements, the system extracts job descriptions, salary information, and company details from images and videos. The system described in Appendix 1, characterized by the features described herein. (Note 10) The extraction unit is We will refer to past data from job advertisements and build a feedback loop to improve extraction accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 11) The extraction unit is It estimates the user's emotions and determines the priority of information to extract based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The extraction unit is When analyzing job advertisements, we analyze the company's social media activity and extract relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 13) The extraction unit is When analyzing job advertisements, the geographical location of companies is taken into consideration to extract highly relevant information. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned verification unit is We estimate user sentiment and adjust the criteria for verifying a company's trustworthiness based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned verification unit is In addition to the company registration information database, the database also cross-references the company's past legal troubles and reputation. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned verification unit is When verifying a company's reliability, analyze its financial situation and reflect this in the reliability assessment. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned verification unit is The system estimates the user's emotions and adjusts how the confirmation results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned verification unit is When verifying a company's reliability, we refer to its reputation within the industry and comparative data with competitors. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned verification unit is When verifying a company's reliability, consider its Environmental, Social, and Governance (ESG) score. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit is We estimate user sentiment and adjust the criteria for analyzing the balance between job content and salary based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit is When analyzing the balance between job duties and salary, we improve the accuracy of the analysis by referring to past similar job posting data. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit is When analyzing the balance between job duties and salary, the balance is evaluated by considering the risks and workload of the work. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned analysis unit is It estimates the user's emotions and adjusts how the analysis results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned analysis unit is When analyzing the balance between job responsibilities and salary, refer to industry-wide salary levels and trend data. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned analysis unit is When analyzing the balance between job duties and salary, consider the cost of living and price indices for each region. The system described in Appendix 1, characterized by the features described herein. (Note 26) The scoring unit, We estimate the user's emotions and adjust the method for calculating the reliability score based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The scoring unit, When calculating reliability scores, the scoring algorithm is optimized by referring to past score data. The system described in Appendix 1, characterized by the features described herein. (Note 28) The scoring unit, When calculating the reliability score, the level of detail and transparency of the job advertisement will be included as evaluation criteria. The system described in Appendix 1, characterized by the features described herein. (Note 29) The scoring unit, The system estimates the user's emotions and adjusts how the score is displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The scoring unit, When calculating reliability scores, we refer to data on a company's reputation within its industry and comparisons with competitors. The system described in Appendix 1, characterized by the features described herein. (Note 31) The scoring unit, When calculating the reliability score, we will consider the company's environmental, social, and governance (ESG) score. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned withdrawal section is, We estimate user sentiment and adjust the withdrawal criteria based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned withdrawal section is, When a withdrawal is made, the withdrawal algorithm is optimized by referring to past withdrawal history. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned withdrawal section is, When a job posting is withdrawn, the method of notifying the withdrawal will be customized according to the content of the job advertisement. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned withdrawal section is, The system estimates the user's emotions and determines the priority of withdrawals based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned withdrawal section is, When withdrawing a claim, the company's past reliability scores and reputation data are referenced. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned API section is We estimate the user's emotions and adjust how the API is delivered based on those estimated emotions. The system described in Appendix 2, characterized by the features described herein. (Note 38) The aforementioned API section is When providing the API, we will provide a customized API tailored to the characteristics of each company's job posting site. The system described in Appendix 2, characterized by the features described herein. (Note 39) The aforementioned API section is When providing APIs, we optimize the delivery method by referring to past API usage history. The system described in Appendix 2, characterized by the features described herein. (Note 40) The aforementioned API section is It estimates user sentiment and adjusts API usage frequency based on the estimated user sentiment. The system described in Appendix 2, characterized by the features described herein. (Note 41) The aforementioned API section is When providing the API, we will provide a customized API tailored to the characteristics of each company's job posting site. The system described in Appendix 2, characterized by the features described herein. (Note 42) The aforementioned API section is When providing APIs, we optimize the delivery method by referring to past API usage history. The system described in Appendix 2, characterized by the features described herein. [Explanation of symbols]

[0205] 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. An extraction unit that extracts job descriptions, salaries, and company information from job advertisements, A verification unit confirms the company's registration information based on the information extracted by the extraction unit, Based on the information confirmed by the aforementioned verification unit, an analysis unit analyzes the balance between job duties and salary, A scoring unit that scores the reliability of job postings based on the information analyzed by the aforementioned analysis unit, The system includes a withdrawal unit that withdraws job postings with low scores determined by the scoring unit. A system characterized by the following features.

2. It includes an API and will be deployed to various companies' job posting websites. The system according to feature 1.

3. The extraction unit is We analyze the text data of job advertisements to identify job duties, salary, and company information. The system according to feature 1.

4. The aforementioned verification unit is The reliability of a company is verified by cross-referencing it with the company's registration information database. The system according to feature 1.

5. The aforementioned analysis unit is Determine the balance between job duties and salary. The system according to feature 1.

6. The scoring unit, Score the reliability of job postings. The system according to feature 1.

7. The aforementioned withdrawal section is, Remove job postings with low scores. The system according to feature 1.

8. The extraction unit is We estimate user sentiment and adjust the job advertisement analysis method based on the estimated user sentiment. The system according to feature 1.

9. The extraction unit is In addition to text data from job advertisements, the system extracts job descriptions, salary information, and company details from images and videos. The system according to feature 1.

10. The extraction unit is We will refer to past data from job advertisements and build a feedback loop to improve extraction accuracy. The system according to feature 1.

Images