System

Abstract

An object of a system according to an embodiment is to efficiently perform matching between an information sender on the Internet and a person image desired by a company.SOLUTION: A system includes a collection part, an analysis part, a patterning part, a matching part, and a sending part. A collection part collects various Web information transmission contents of an information transmitter on the Internet. The analysis unit analyzes human characteristics, possessed skills, and business aptitude based on the information collected by the collection unit. The patterning unit analyzes and patterns a portrait requested by a company. The matching unit lists the information obtained by the analysis unit and the patterning unit and performs matching. The sending unit sends the offer letter to the information sender and the company matched by the matching unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Conventional technology has had the problem of making it difficult to efficiently match information providers on the Internet with the profile of the person a company is looking for.

[0005] The system according to the embodiment aims to efficiently match information providers on the Internet with the type of person that a company is looking for. [Means for solving the problem]

[0006] The system according to the embodiment comprises a collection unit, an analysis unit, a patterning unit, a matching unit, and a sending unit. The collection unit collects various web information posts from information providers on the Internet. The analysis unit analyzes personal characteristics, skills, and business aptitude based on the information collected by the collection unit. The patterning unit analyzes and patterns the type of person a company is looking for. The matching unit lists the information obtained by the analysis unit and the patterning unit and performs matching. The sending unit sends offer letters to information providers and companies matched by the matching unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently match information providers on the Internet with the type of person a company is looking for. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9]1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

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

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

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

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0027] Note that a device other than the data processing device 12 may 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 a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) A service platform according to an embodiment of the present invention is a system that uses a generation AI to match online information providers worldwide with potential employees for a company. The service platform collects various web content posted by online information providers, and the generation AI analyzes their personal characteristics, skills, and business aptitude. The generation AI then analyzes and patterns the profile of the person the company is seeking. This information is then compiled into a list, and the generation AI performs matching. For suitable candidates, the generation AI automatically sends offer letters to the hiring company and the candidate based on the information collected. For example, the service platform collects information from social media, blogs, portfolio sites, etc., including social media posts, blog articles, and portfolio site artwork. Next, the generation AI collects information from job postings published by companies, official company websites, industry reports, and other sources. For example, the service platform collects information about the company's desired location, age group, job type, and required skills. This allows the company to create a pattern of the desired profile. The generation AI then compares the characteristics of the information provider with the profile of the person the company is seeking to optimally match them. For example, a information provider with specific skills is matched with a company seeking the same skills. Next, the generation AI collects the contact information of the information sender and sends an offer letter along with the company's job information. For example, the generation AI collects the contact information of the information sender and sends an offer letter along with the company's job information. This enables smooth communication between the information sender and the company. As a result, the service platform turns information senders from all over the world into potential employees for companies, achieving an optimal match with the profile of the person the company is looking for. This allows the service platform to help companies efficiently secure talent and enable information senders to find jobs that utilize their skills and characteristics.

[0029] A service platform according to an embodiment includes a collection unit, an analysis unit, a patterning unit, a matching unit, and a sending unit. The collection unit collects various web information posts from information providers on the Internet. Examples of the various web information posts include, but are not limited to, blog posts, social media posts, and portfolios. The collection unit collects information from, for example, social media sites, blogs, and portfolio sites. For example, the collection unit can collect information from social media sites such as Twitter (registered trademark), Facebook (registered trademark), and Instagram (registered trademark). The collection unit can also collect information from blogs such as personal blogs, corporate blogs, and technical blogs. The collection unit can also collect information from portfolio sites such as Behance (registered trademark), Dribbble, and GitHub (registered trademark). The analysis unit analyzes personality traits, possessed skills, and business aptitude based on the information collected by the collection unit. Examples of personality traits include, but are not limited to, personality traits, behavioral patterns, and values. Examples of possessed skills include, but are not limited to, technical skills, soft skills, and specialized knowledge. Examples of business aptitude include, but are not limited to, leadership, problem-solving ability, and communication ability. For example, the analysis unit analyzes personality traits from the collected information. The analysis unit can also analyze technical skills from the collected information. The analysis unit can also analyze leadership from the collected information. The patterning unit analyzes and patterns the profile of the person desired by the company. The profile of the person desired by the company includes, but is not limited to, the desired skill set, experience, and personality traits. The patterning unit collects information from, for example, job postings published by the company, official websites, and industry reports, and patterns the profile of the person desired by the company. For example, the patterning unit can collect information from online job sites and official company websites. The patterning unit can also collect information from market research reports and industry analysis reports. The matching unit lists the information obtained by the analysis unit and the patterning unit and performs matching.Matching may include, but is not limited to, methods such as a scoring system or similarity calculation. For example, the matching unit compares the characteristics of the information sender with the profile of the person desired by the company to perform optimal matching. The sending unit sends an offer letter to the information sender and company matched by the matching unit. The offer letter may be sent via, but is not limited to, methods such as email, mail, or a messaging app. For example, the sending unit collects the contact information of the information sender and sends an offer letter along with the company's job information. This allows the service platform according to the embodiment to efficiently match information senders on the Internet with the profile of the person desired by the company and send an offer letter.

[0030] The collection unit can collect information from social media platforms, blogs, and portfolio sites. The collection unit collects information from, for example, social media platforms, blogs, and portfolio sites. Social media platforms include, but are not limited to, Twitter, Facebook, and Instagram. Blogs include, but are not limited to, personal blogs, corporate blogs, and technical blogs. Portfolio sites include, but are not limited to, Behance, Dribbble, and GitHub. For example, the collection unit collects information from Twitter. The collection unit can also collect information from personal blogs. The collection unit can also collect information from Behance. By collecting information from various platforms, the characteristics of the information sender can be more accurately understood. Some or all of the above-described processing by the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data collected from social media platforms into a generation AI, which then analyzes the data.

[0031] The analysis unit can analyze personality traits, possessed skills, and business aptitude from the collected information. For example, the analysis unit can analyze personality traits from the collected information. Examples of personality traits include, but are not limited to, personality traits, behavioral patterns, and values. The analysis unit can also analyze possessed skills from the collected information. Examples of possessed skills include, but are not limited to, technical skills, soft skills, and specialized knowledge. The analysis unit can also analyze business aptitude from the collected information. Examples of business aptitude include, but are not limited to, leadership, problem-solving ability, and communication ability. For example, the analysis unit can analyze personality traits from the collected information. The analysis unit can also analyze technical skills from the collected information. The analysis unit can also analyze leadership from the collected information. This enables more appropriate matching by analyzing the characteristics of the information sender in detail. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the collected data into a generation AI, which then analyzes the data.

[0032] The patterning unit can collect information from job postings, official websites, and industry reports published by companies and create patterns of the profile of the person the company is looking for. For example, the patterning unit collects information from job postings, official websites, and industry reports published by companies and creates patterns of the profile of the person the company is looking for. Job postings published by companies include, but are not limited to, online job posting sites and official company websites. Official websites include, but are not limited to, company homepages and recruitment pages. Industry reports include, but are not limited to, market research reports and industry analysis reports. For example, the patterning unit collects information from online job posting sites. The patterning unit can also collect information from official company websites. The patterning unit can also collect information from market research reports. This allows the profile of the person the company is looking for to be accurately patterned, thereby improving matching accuracy. Some or all of the above-described processing in the patterning unit may be performed using, or without, AI. For example, the patterning unit can input collected data into a generation AI, which then analyzes the data.

[0033] The matching unit can compare the characteristics of the information sender with the profile of the person the company is looking for to perform optimal matching. For example, the matching unit can compare the characteristics of the information sender with the profile of the person the company is looking for to perform optimal matching. Optimal matching can include, but is not limited to, methods such as a scoring system or similarity calculation. For example, the matching unit can compare the characteristics of the information sender with the profile of the person the company is looking for using a scoring system. The matching unit can also compare the characteristics of the information sender with the profile of the person the company is looking for using a similarity calculation. The matching unit can also compare the characteristics of the information sender with the profile of the person the company is looking for using a clustering method. This allows for efficient matching between the information sender and the profile of the person the company is looking for. Some or all of the above-described processing in the matching unit can be performed using, for example, AI, or can be performed without using AI. For example, the matching unit can input collected data into a generation AI, which can then analyze the data.

[0034] The sending unit can collect contact information from the information sender and send an offer letter along with the company's job information. For example, the sending unit collects contact information from the information sender and sends the offer letter along with the company's job information. Contact information includes, but is not limited to, email addresses, telephone numbers, and social media accounts. The offer letter can be sent via, but is not limited to, email, mail, messaging apps, and other methods. For example, the sending unit collects email addresses from the information sender and sends the offer letter along with the company's job information. The sending unit can also collect telephone numbers from the information sender and send the offer letter along with the company's job information. The sending unit can also collect social media accounts from the information sender and send the offer letter along with the company's job information. This enables smooth communication between the information sender and the company. Some or all of the above-described processing by the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the collected contact data into a generation AI, which then creates and sends an offer letter.

[0035] The sending unit can promote smooth communication between the information sender and the company when sending an offer letter. The sending unit can promote smooth communication between the information sender and the company when sending an offer letter, for example. Smooth communication includes, but is not limited to, methods such as real-time chat and periodic follow-up. For example, the sending unit can provide real-time chat after sending the offer letter. The sending unit can also perform periodic follow-up. The sending unit can also promote smooth communication using a messaging app. This allows smooth communication between the information sender and the company. Some or all of the above-described processing in the sending unit can be performed using, for example, AI, or can be performed without using AI. For example, the sending unit can generate content for the real-time chat using a generation AI to promote communication between the information sender and the company.

[0036] The matching unit can learn from past matching results and improve the algorithm to improve matching accuracy. For example, the matching unit can learn from past matching results and improve the algorithm to improve matching accuracy. Past matching results include, but are not limited to, success cases, failure cases, feedback, etc. Improvements to the algorithm can include, but are not limited to, parameter adjustment, model retraining, etc. For example, the matching unit can learn from past success cases and improve the algorithm. The matching unit can also learn from past failure cases and improve the algorithm. The matching unit can also improve the algorithm based on feedback. This improves matching accuracy and enables more appropriate matching. Some or all of the above-described processing in the matching unit can be performed using, for example, AI, or can be performed without using AI. For example, the matching unit can learn from past matching results using a generation AI and improve the algorithm.

[0037] The collection unit can anonymize the collected information to protect the privacy of the information sender. For example, the collection unit anonymizes the collected information to protect the privacy of the information sender. Privacy protection includes, but is not limited to, methods such as data anonymization, encryption, and access control. Anonymization includes, but is not limited to, methods such as deleting personally identifiable information and masking data. For example, the collection unit deletes personally identifiable information from the collected data. The collection unit can also mask the data. The collection unit can also encrypt the data. This protects the privacy of the information sender. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can anonymize the collected data using generation AI.

[0038] The sending unit can track interactions between the information sender and the company after sending the offer letter and collect feedback. For example, the sending unit can track interactions between the information sender and the company after sending the offer letter and collect feedback. Examples of tracking interactions include, but are not limited to, email tracking and saving chat logs. Examples of collecting feedback include, but are not limited to, surveys, interviews, and reviews. For example, the sending unit tracks emails. The sending unit can also save chat logs. The sending unit can also conduct surveys. In this way, interactions between the information sender and the company are tracked and feedback is collected. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can track interactions and collect feedback using generation AI.

[0039] The patterning unit may periodically update the profile of the person desired by the company and perform patterning based on the latest job information. For example, the patterning unit may periodically update the profile of the person desired by the company and perform patterning based on the latest job information. Periodic updates include, but are not limited to, monthly updates, quarterly updates, and automatic updates. Methods for obtaining the latest job information include, but are not limited to, RSS feeds and API integration. For example, the patterning unit may perform monthly updates. The patterning unit may also perform quarterly updates. The patterning unit may also perform automatic updates. This allows the profile of the person desired by the company to be patterned based on the latest information. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may collect the latest job information using a generation AI and perform patterning.

[0040] The collection unit can analyze the information sender's past posting history and select the optimal collection method when collecting information. For example, the collection unit can analyze the information sender's past posting history and select the optimal collection method when collecting information. Methods for analyzing the past posting history include, but are not limited to, methods such as analyzing the content of posts and the frequency of posts. The optimal collection method can include, but is not limited to, methods such as API collection, scraping, and manual collection. For example, the collection unit can prioritize collecting information from platforms on which the information sender has frequently posted in the past. The collection unit can also analyze trends in the content of posts by the information sender and prioritize collecting highly relevant information. The collection unit can also adjust the collection timing based on the frequency of posts by the information sender. This allows the optimal collection method to be selected based on the information sender's past posting history. Some or all of the above-described processing in the collection unit can be performed, for example, using AI, or can be performed without AI. For example, the collection unit can analyze the past posting history using a generation AI and select the optimal collection method.

[0041] The collection unit may perform filtering based on the current activity status and areas of interest of the information sender when collecting information. For example, the collection unit may perform filtering based on the current activity status and areas of interest of the information sender when collecting information. Examples of current activity status include, but are not limited to, the latest posts and online status. Examples of areas of interest include, but are not limited to, tag information and following accounts. Examples of filtering include, but are not limited to, keyword filtering and category filtering. For example, the collection unit may preferentially collect information related to topics in which the information sender is currently interested. The collection unit may also analyze the current activity status of the information sender and collect highly relevant information. The collection unit may also narrow the scope of information to be collected based on the areas of interest of the information sender. This filters the information based on the current activity status and areas of interest of the information sender. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit may analyze the current activity status and areas of interest of the information sender using a generation AI and perform filtering.

[0042] The collection unit can select the optimal collection means depending on the input method of the information sender when collecting information. For example, the collection unit selects the optimal collection means depending on the input method (voice, text, image, etc.) of the information sender when collecting information. Input methods include, but are not limited to, voice input, text input, image input, etc. The optimal collection means includes, but are not limited to, voice recognition, OCR, text analysis, etc. For example, if the information sender sends information by voice, the collection unit can collect information using voice recognition technology. Also, if the information sender sends information by text, the collection unit can collect information using text analysis technology. Also, if the information sender sends information by image, the collection unit can collect information using image recognition technology. In this way, the optimal collection means is selected depending on the input method of the information sender. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze the input method of the information sender using generation AI and select the optimal collection means.

[0043] When collecting information, the collection unit can prioritize collecting highly relevant information by taking into account the geographical location information of the information sender. For example, when collecting information, the collection unit prioritizes collecting highly relevant information by taking into account the geographical location information of the information sender. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, location information services, etc. Examples of highly relevant information include, but are not limited to, information about geographically nearby areas and trend information for the same area. For example, when the information sender is in a specific area, the collection unit prioritizes collecting information related to that area. The collection unit can also collect information specific to the area based on the geographical location information of the information sender. Furthermore, when the information sender is moving, the collection unit can also collect highly relevant information based on the current location. In this way, highly relevant information is preferentially collected based on the geographical location information of the information sender. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze the geographical location information of the information sender using a generation AI and preferentially collect highly relevant information.

[0044] The collection unit can analyze the social media activity of the information sender when collecting information and collect related information. For example, the collection unit can analyze the social media activity of the information sender when collecting information and collect related information. Social media activity includes, but is not limited to, analysis of post content and engagement. Related information includes, but is not limited to, information on the same topic and related hashtags. For example, the collection unit can collect related information based on information shared by the information sender on social media. The collection unit can also analyze the social media activity history of the information sender and collect highly relevant information. The collection unit can also refer to the activities of the information sender's friends on social media. In this way, related information is collected based on the social media activity of the information sender. Some or all of the above-described processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection unit can analyze the social media activity of the information sender using generation AI and collect related information.

[0045] The collection unit can customize the collection method by reflecting the information sender's past feedback when collecting information. For example, the collection unit customizes the collection method by reflecting the information sender's past feedback when collecting information. Past feedback includes, but is not limited to, survey results, review comments, etc. Customizing the collection method includes, but is not limited to, parameter adjustment based on feedback, changing the collection means, etc. For example, the collection unit adjusts the collection method based on feedback provided by the information sender in the past. The collection unit can also analyze the information sender's past feedback and select the optimal collection means. The collection unit can also adjust the range of information to be collected by reflecting the information sender's feedback. This customizes the collection method based on the information sender's past feedback. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze past feedback using a generation AI and customize the collection method.

[0046] The analysis unit may adjust the level of detail of the analysis based on the importance of the information sender during the analysis. For example, the analysis unit may adjust the level of detail of the analysis based on the importance of the information sender during the analysis. Examples of the importance of the information sender include, but are not limited to, the number of followers, influence score, and engagement rate. Examples of the level of detail of the analysis include, but are not limited to, detailed data analysis, summary reports, and other methods. For example, the analysis unit may perform a detailed analysis on information senders with high importance. The analysis unit may also perform a simplified analysis on information senders with low importance. The analysis unit may also adjust the priority of the analysis based on the importance of the information sender. This adjusts the level of detail of the analysis based on the importance of the information sender. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may evaluate the importance of the information sender using a generation AI and adjust the level of detail of the analysis.

[0047] The analysis unit can apply different analysis algorithms depending on the category of the information provider during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of the information provider during analysis. Examples of information provider categories include, but are not limited to, industry categories, fields of expertise, and interests. Examples of different analysis algorithms include, but are not limited to, clustering algorithms, regression analysis, and classification algorithms. For example, the analysis unit can apply an analysis algorithm that emphasizes technical skills to technical information providers. Furthermore, the analysis unit can apply an analysis algorithm that emphasizes creativity to creative information providers. Furthermore, the analysis unit can apply an analysis algorithm that emphasizes business aptitude to business information providers. In this way, the optimal analysis algorithm is applied depending on the category of the information provider. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can classify the category of the information provider using a generation AI and apply an appropriate analysis algorithm.

[0048] The analysis unit can improve the accuracy of the analysis by referring to the information sender's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the information sender's past analysis results during analysis. Past analysis results include, but are not limited to, past reports, database query results, etc. Analysis accuracy can include, but are not limited to, accuracy evaluation metrics, model retraining, etc. For example, the analysis unit can adjust the current analysis based on the information sender's past analysis results. The analysis unit can also learn from past analysis results and improve the analysis algorithm. The analysis unit can also improve the accuracy of the analysis by referring to the information sender's past analysis results. By referring to past analysis results, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can learn from past analysis results using generative AI to improve the accuracy of the analysis.

[0049] The analysis unit may determine the analysis priority based on the posting time of the information sender during analysis. For example, the analysis unit may determine the analysis priority based on the posting time of the information sender during analysis. The posting time may include, but is not limited to, metadata of the posting date and time, a timestamp, etc. The analysis priority may include, but is not limited to, methods such as urgency assessment and importance scoring. For example, the analysis unit may prioritize analysis of recent posts to provide the latest information. The analysis unit may also supplement the current analysis with reference to past posts. The analysis unit may also adjust the analysis priority based on the posting time. This allows the analysis priority to be determined based on the posting time of the information sender. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may analyze the posting time using a generation AI to determine the analysis priority.

[0050] The analysis unit can adjust the order of analysis based on the relevance of the information senders during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the information senders during analysis. Relevance includes, but is not limited to, methods such as co-occurrence network analysis and similarity calculation. The order of analysis includes, but is not limited to, methods such as priority ordering and category ordering. For example, the analysis unit prioritizes analysis when the relevance of the information senders is high. Furthermore, the analysis unit can postpone analysis when the relevance of the information senders is low. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the information senders. In this way, the order of analysis is adjusted based on the relevance of the information senders. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can evaluate the relevance of the information senders using a generation AI and adjust the order of analysis.

[0051] The analysis unit may adjust the use of technical terms in the analysis according to the expertise level of the information sender during the analysis. For example, the analysis unit may adjust the use of technical terms in the analysis according to the expertise level of the information sender during the analysis. Examples of expertise levels include, but are not limited to, qualifications, past achievements, and the number of followers. The use of technical terms may include, but are not limited to, definitions of technical terms and replacement with general terms. For example, if the expertise level of the information sender is high, the analysis unit may provide an analysis that uses a lot of technical terms. Furthermore, if the expertise level of the information sender is low, the analysis unit may provide an analysis that explains the information in simple terms. Furthermore, the analysis unit may adjust the use of technical terms in the analysis according to the expertise level of the information sender. This allows the use of technical terms that are optimal for the expertise level of the information sender. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may use a generation AI to evaluate the expertise level of the information sender and adjust the use of technical terms.

[0052] The patterning unit can improve the accuracy of the patterning by taking into account the interrelationships of the profile of the person desired by the company during patterning. For example, the patterning unit can improve the accuracy of the patterning by taking into account the interrelationships of the profile of the person desired by the company during patterning. Examples of interrelationships include, but are not limited to, methods such as co-occurrence network analysis and correlation analysis. Examples of the accuracy of the patterning include, but are not limited to, methods such as accuracy evaluation indexes and model retraining. For example, the patterning unit can analyze the interrelationships of the profile of the person desired by the company and improve the accuracy of the patterning. The patterning unit can also adjust the patterning criteria by taking into account the interrelationships of the profile of the person desired by the company. The patterning unit can also improve the accuracy of the patterning based on the interrelationships of the profile of the person desired by the company. In this way, the accuracy of the patterning is improved by taking into account the interrelationships of the profile of the person desired by the company. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit can analyze the interrelationships of the profile of the person desired by the company using generation AI to improve the accuracy of the patterning.

[0053] The patterning unit may perform patterning while taking into account the attribute information of the companies. For example, the patterning unit may perform patterning while taking into account the attribute information of the companies. The attribute information may include, but is not limited to, for example, the size, industry, and location of the companies. For example, the patterning may include, but is not limited to, clustering techniques and pattern recognition algorithms. For example, the patterning unit may adjust the patterning criteria according to the industry and size of the companies. The patterning unit may also improve the accuracy of the patterning based on the attribute information of the companies. The patterning unit may also adjust the patterning criteria while taking into account the attribute information of the companies. This allows patterning based on the attribute information of the companies. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may analyze the attribute information of the companies using a generation AI and perform patterning.

[0054] The patterning unit can weight the patterns based on the frequency of job postings by companies during patterning. For example, the patterning unit weights the patterns based on the frequency of job postings by companies during patterning. Job posting frequency includes, but is not limited to, for example, the number of job postings and the period of time for job postings. Weighting methods include, but are not limited to, weighting based on frequency and importance. For example, the patterning unit strengthens the weighting when the frequency of job postings by companies is high. Furthermore, the patterning unit can weaken the weighting when the frequency of job postings by companies is low. Furthermore, the patterning unit can adjust the weighting of the patterns based on the frequency of job postings by companies. In this way, the weighting of the patterns is performed based on the frequency of job postings by companies. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit can analyze the frequency of job postings by companies using a generation AI and weight the patterns.

[0055] The patterning unit may perform patterning by taking into account the geographical distribution of companies. For example, the patterning unit may perform patterning by taking into account the geographical distribution of companies. Examples of geographical distribution include, but are not limited to, company locations and job information by region. Examples of patterning include, but are not limited to, clustering techniques and pattern recognition algorithms. For example, the patterning unit may adjust the patterning criteria based on company locations. The patterning unit may also improve the accuracy of the patterning by taking into account the geographical distribution of companies. The patterning unit may also adjust the patterning criteria based on the geographical distribution of companies. This allows patterning based on the geographical distribution of companies. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may analyze the geographical distribution of companies using a generation AI and perform patterning.

[0056] The patterning unit can improve the accuracy of the patterning by referring to the company's related literature during patterning. For example, the patterning unit can improve the accuracy of the patterning by referring to the company's related literature during patterning. Examples of related literature include, but are not limited to, industry reports, academic papers, and patent documents. Methods for improving the accuracy of the patterning include, but are not limited to, accuracy evaluation indices and model retraining. For example, the patterning unit can adjust the patterning criteria based on the company's related literature. The patterning unit can also improve the accuracy of the patterning by referring to the company's related literature. The patterning unit can also adjust the patterning criteria taking the company's related literature into consideration. By referring to the company's related literature, the accuracy of the patterning is improved. Some or all of the above-described processing in the patterning unit can be performed using, for example, AI, or without AI. For example, the patterning unit can analyze the company's related literature using a generation AI to improve the accuracy of the patterning.

[0057] The patterning unit may perform patterning by taking into account the market value of the company. For example, the patterning unit may perform patterning by taking into account the market value of the company. Market value may include, but is not limited to, a company's sales, stock price, and industry position. Patterning may include, but is not limited to, clustering techniques, pattern recognition algorithms, and other methods. For example, the patterning unit may increase weighting when the company's market value is high. Furthermore, the patterning unit may decrease weighting when the company's market value is low. Furthermore, the patterning unit may adjust the weighting of the patterning based on the company's market value. This allows patterning based on the company's market value. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without AI. For example, the patterning unit may analyze a company's market value using a generation AI and perform patterning.

[0058] The matching unit may improve the accuracy of matching by taking into account the relationship between the information sender and the company during matching. For example, the matching unit may improve the accuracy of matching by taking into account the relationship between the information sender and the company during matching. Examples of the relationship include, but are not limited to, co-occurrence network analysis and correlation analysis. Examples of the accuracy of matching include, but are not limited to, accuracy evaluation indexes and model retraining. For example, the matching unit may analyze past interactions between the information sender and the company to improve the accuracy of matching. The matching unit may also adjust matching criteria by taking into account the relationship between the information sender and the company. The matching unit may also improve the accuracy of matching based on the relationship between the information sender and the company. By taking into account the relationship between the information sender and the company, the accuracy of matching is improved. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may analyze the relationship between the information sender and the company using a generation AI to improve the accuracy of matching.

[0059] The matching unit may perform matching by taking into account attribute information of the information sender and the company. For example, the matching unit may perform matching by taking into account attribute information of the information sender and the company. Attribute information may include, for example, but is not limited to, the company's size, industry, and location. Matching may include, for example, but is not limited to, a scoring system, similarity calculation, or other methods. For example, the matching unit may perform matching by comparing the skill set of the information sender with the skill set desired by the company. The matching unit may also perform matching by taking into account the information sender's industry experience and the company's industry. The matching unit may also perform matching by taking into account the information sender's desired work location and the company's location. This allows optimal matching to be performed based on the attribute information of the information sender and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may analyze the attribute information of the information sender and the company using a generation AI to perform matching.

[0060] The matching unit may weight the matching based on the activity frequency of the information sender and the company during matching. For example, the matching unit may weight the matching based on the activity frequency of the information sender and the company during matching. Activity frequency includes, but is not limited to, posting frequency and update frequency. Weighting methods include, but are not limited to, frequency-based weighting and importance-based weighting. For example, the matching unit may increase the weighting if the activity frequency of the information sender is high. Furthermore, the matching unit may decrease the weighting if the activity frequency of the information sender is low. Furthermore, the matching unit may adjust the matching weighting based on the activity frequency of the information sender and the company. This allows the matching weighting to be based on the activity frequency of the information sender and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without AI. For example, the matching unit may use a generation AI to analyze the activity frequency of the information sender and the company and weight the matching.

[0061] The matching unit may perform matching by taking into account the geographical distribution of information senders and companies. For example, the matching unit may perform matching by taking into account the geographical distribution of information senders and companies. Examples of geographical distribution include, but are not limited to, company locations and job information by region. Examples of matching include, but are not limited to, scoring systems and similarity calculations. For example, the matching unit may perform matching by taking into account the residence of the information sender and the location of the company. The matching unit may also perform matching by taking into account the information sender's desired work location and the location of the company. The matching unit may also improve the accuracy of matching based on the geographical distribution of information senders and companies. This allows optimal matching to be performed based on the geographical distribution of information senders and companies. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may use a generation AI to analyze the geographical distribution of information senders and companies and perform matching.

[0062] The matching unit may improve the accuracy of matching by referring to related literature between the information provider and the company during matching. For example, the matching unit may improve the accuracy of matching by referring to related literature between the information provider and the company during matching. Examples of related literature include, but are not limited to, industry reports, academic papers, and patent documents. Methods for improving the accuracy of matching include, but are not limited to, accuracy evaluation indices and model retraining. For example, the matching unit may perform matching by referring to the information provider's past performance and papers. The matching unit may also improve the accuracy of matching based on related literature between the company. The matching unit may also adjust the matching criteria by taking into account related literature between the information provider and the company. By doing so, the accuracy of matching is improved by referring to related literature between the information provider and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without AI. For example, the matching unit may use a generation AI to analyze related literature between the information provider and the company to improve the accuracy of matching.

[0063] The matching unit may perform matching by taking into account the market value of the information sender and the company. For example, the matching unit may perform matching by taking into account the market value of the information sender and the company. Market value may include, but is not limited to, a company's sales, stock price, and industry position. Matching may include, but is not limited to, a scoring system, similarity calculation, or other methods. For example, the matching unit may increase weighting if the market value of the information sender is high. Furthermore, the matching unit may decrease weighting if the market value of the information sender is low. Furthermore, the matching unit may adjust the matching weighting based on the market value of the information sender and the company. This allows optimal matching to be performed based on the market value of the information sender and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without AI. For example, the matching unit may analyze the market value of the information sender and the company using a generation AI and perform matching.

[0064] The sending unit can select the optimal sending method by referring to the information sender's past communication history when sending the offer letter. For example, the sending unit can select the optimal sending method by referring to the information sender's past communication history when sending the offer letter. Examples of past communication history include, but are not limited to, email tracking and chat log storage. Examples of optimal sending methods include, but are not limited to, email, mail, and messaging apps. For example, the sending unit selects the optimal sending method based on a sending method previously preferred by the information sender. The sending unit can also analyze the information sender's past communication history and select the optimal sending method. The sending unit can also adjust the sending method by referring to the information sender's past feedback. In this way, the optimal sending method is selected based on the information sender's past communication history. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the information sender's past communication history using a generation AI and select the optimal sending method.

[0065] The sending unit can customize the content of the offer letter based on the current activity status of the information sender when sending the offer letter. For example, the sending unit customizes the content of the offer letter based on the current activity status of the information sender when sending the offer letter. Examples of the current activity status include, but are not limited to, the latest posts and online status. Examples of customizing the content of the offer letter include, but are not limited to, creating an individual message and adjusting a template. For example, the sending unit sends an offer letter including content related to a topic that the information sender is currently interested in. The sending unit can also analyze the current activity status of the information sender and send an offer letter including highly relevant content. The sending unit can also customize the content of the offer letter based on the information sender's areas of interest. As a result, the content of the offer letter is customized based on the current activity status of the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the current activity status of the information sender using a generation AI and customize the content of the offer letter.

[0066] The sending unit can improve the sending method by reflecting feedback from the information sender when sending an offer letter. For example, the sending unit improves the sending method by reflecting feedback from the information sender when sending an offer letter. Examples of feedback include, but are not limited to, questionnaires, interviews, and reviews. Examples of improving the sending method include, but are not limited to, parameter adjustments and changes to the sending means based on the feedback. For example, the sending unit adjusts the sending method based on feedback previously provided by the information sender. The sending unit can also analyze past feedback from the information sender and select an optimal sending method. The sending unit can also adjust the sending content by reflecting feedback from the information sender. This improves the sending method based on feedback from the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze feedback from the information sender using a generation AI and improve the sending method.

[0067] The sending unit can select the optimal sending method by taking into consideration the geographical location information of the information sender when sending the offer letter. For example, the sending unit selects the optimal sending method by taking into consideration the geographical location information of the information sender when sending the offer letter. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, location information services, etc. Examples of optimal sending methods include, but are not limited to, email, mail, messaging apps, etc. For example, the sending unit selects the optimal sending method based on the location of the information sender. The sending unit can also adjust the sending method by taking into consideration the geographical location information of the information sender. The sending unit can also select the optimal sending method based on the geographical location information of the information sender. In this way, the optimal sending method is selected based on the geographical location information of the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the geographical location information of the information sender using a generation AI and select the optimal sending method.

[0068] The sending unit can customize the content of the offer letter by analyzing the social media activity of the information sender when sending the offer letter. For example, the sending unit analyzes the social media activity of the information sender when sending the offer letter to customize the content of the offer letter. Examples of social media activity include, but are not limited to, analyzing posted content and engagement analysis. Examples of customizing the content of the offer letter include, but are not limited to, creating individual messages and adjusting templates. For example, the sending unit customizes the content of the offer letter based on information shared by the information sender on social media. The sending unit can also analyze the social media activity history of the information sender and send an offer letter containing highly relevant content. The sending unit can also refer to the activity of the information sender's friends on social media to send an offer letter containing relevant content. In this way, the content of the offer letter is customized based on the social media activity of the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the social media activity of the information sender using a generation AI to customize the content of the offer letter.

[0069] The sending unit can customize the sending method by reflecting the information sender's past feedback when sending an offer letter. For example, the sending unit customizes the sending method by reflecting the information sender's past feedback when sending an offer letter. Past feedback includes, but is not limited to, survey results, review comments, etc. Customizing the sending method includes, but is not limited to, parameter adjustment based on feedback, changing the sending means, etc. For example, the sending unit adjusts the sending method based on feedback previously provided by the information sender. The sending unit can also analyze the information sender's past feedback and select the optimal sending method. The sending unit can also adjust the sending content by reflecting the information sender's feedback. In this way, the sending method is customized based on the information sender's past feedback. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the information sender's past feedback using a generation AI and customize the sending method.

[0070] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0071] The collection unit can also analyze the content of past posts by the information provider and adjust the method of collecting information based on the tone and style of the posts. For example, if the information provider has posted in a positive tone in the past, the collection unit can prioritize collecting information with a similar tone. Also, if the information provider has posted a lot of technical content, the collection unit can prioritize collecting technical information. Furthermore, if the information provider uses a lot of visual content, the collection unit can prioritize collecting information including images and videos. This makes it possible to collect more relevant information based on the content of past posts by the information provider.

[0072] The pattern creation department can also take into account a company's culture and values ​​when creating patterns for the type of person a company is looking for. For example, the pattern creation department analyzes the values ​​that a company values ​​(e.g., innovation, teamwork, customer orientation, etc.) and creates patterns for the type of person they are looking for based on these. It can also create patterns for appropriate types of people by taking into account the company's culture (e.g., flat organizational structure, encouragement of remote work, etc.). Furthermore, it can analyze a company's past hiring data and adjust the criteria for pattern creation based on successful hiring cases. This makes it possible to create patterns for people who match the company's culture and values.

[0073] After sending the offer letter, the sending department can track the exchange between the information sender and the company and collect feedback. For example, the sending department can track emails to check whether the offer letter has been opened. The sending department can also save chat logs and analyze the content of the exchanges. Furthermore, the sending department can conduct surveys and collect feedback from both the information sender and the company. This makes it possible to track the exchange between the information sender and the company and improve services based on the feedback.

[0074] The analysis unit can also adjust the use of technical terms in the analysis depending on the information sender's level of expertise. For example, if the information sender's level of expertise is high, the analysis unit can provide an analysis that uses a lot of technical terms. If the information sender's level of expertise is low, the analysis unit can provide an analysis that explains things in simple terms. Furthermore, the analysis unit can adjust the level of detail in the analysis depending on the information sender's level of expertise. This makes it possible to provide an optimal analysis depending on the information sender's level of expertise.

[0075] The pattern generation unit can also take into account the market value of a company when generating patterns for the type of person a company is looking for. For example, the pattern generation unit can analyze a company's sales, stock price, and position within the industry, and generate patterns for the type of person it is looking for based on this. In addition, if the company's market value is high, the pattern generation unit can increase the weighting, and if it is low, the pattern generation unit can decrease the weighting. Furthermore, the pattern generation criteria can be adjusted based on the company's market value. This makes it possible to generate patterns for the optimal type of person based on the company's market value.

[0076] When sending the offer letter, the sending unit may select the optimal sending method taking into consideration the geographical location information of the information sender. For example, the sending unit may select the optimal sending method based on the location of the information sender. The sending unit may also adjust the sending method taking into consideration the geographical location information of the information sender. Furthermore, the sending unit may select the optimal sending method based on the geographical location information of the information sender. In this way, the optimal sending method is selected based on the geographical location information of the information sender.

[0077] The processing flow of the first embodiment will be briefly explained below.

[0078] Step 1: The collection unit collects various web information posts from online information providers. These web information posts include blog articles, social media posts, and portfolios. The collection unit collects information from social media, blogs, and portfolio sites. For example, information is collected from social media sites such as Twitter, Facebook, and Instagram, personal blogs, corporate blogs, technical blogs, and portfolio sites such as Behance, Dribbble, and GitHub. Step 2: The analysis department analyzes the personality traits, skills, and business aptitude based on the information collected by the collection department. Personality traits include personality traits, behavioral patterns, and values, while skills include technical skills, soft skills, and specialized knowledge. Business aptitude includes leadership, problem-solving skills, and communication skills. For example, the analysis department analyzes personality traits, technical skills, and leadership from the collected information. Step 3: The pattern generation department analyzes the profile of the person a company is looking for and creates a pattern. The profile of the person a company is looking for includes the desired skill set, experience, personality traits, etc. The pattern generation department collects information from job postings published by companies, official websites, and industry reports, and creates a pattern of the profile of the person a company is looking for. For example, information is collected from online job sites, official company websites, market research reports, and industry analysis reports. Step 4: The matching section lists the information obtained by the analysis section and patterning section and performs matching. Matching involves methods such as scoring systems and similarity calculations. For example, the matching section compares the characteristics of the information provider with the profile of the person the company is looking for to find the optimal match. Step 5: The sending department sends offer letters to the information senders and companies matched by the matching department. Offer letters can be sent via email, mail, messaging apps, etc. For example, the sending department collects the contact information of the information senders and sends the offer letters along with the company's job information.

[0079] (Example 2) A service platform according to an embodiment of the present invention is a system that uses a generation AI to match online information providers worldwide with potential employees for a company. The service platform collects various web content posted by online information providers, and the generation AI analyzes their personal characteristics, skills, and business aptitude. The generation AI then analyzes and patterns the profile of the person the company is seeking. This information is then compiled into a list, and the generation AI performs matching. For suitable candidates, the generation AI automatically sends offer letters to the hiring company and the candidate based on the information collected. For example, the service platform collects information from social media, blogs, portfolio sites, etc., including social media posts, blog articles, and portfolio site artwork. Next, the generation AI collects information from job postings published by companies, official company websites, industry reports, and other sources. For example, the service platform collects information about the company's desired location, age group, job type, and required skills. This allows the company to create a pattern of the desired profile. The generation AI then compares the characteristics of the information provider with the profile of the person the company is seeking to optimally match them. For example, a information provider with specific skills is matched with a company seeking the same skills. Next, the generation AI collects the contact information of the information sender and sends an offer letter along with the company's job information. For example, the generation AI collects the contact information of the information sender and sends an offer letter along with the company's job information. This enables smooth communication between the information sender and the company. As a result, the service platform turns information senders from all over the world into potential employees for companies, achieving an optimal match with the profile of the person the company is looking for. This allows the service platform to help companies efficiently secure talent and enable information senders to find jobs that utilize their skills and characteristics.

[0080] A service platform according to an embodiment includes a collection unit, an analysis unit, a patterning unit, a matching unit, and a sending unit. The collection unit collects various web information posts from information providers on the Internet. Examples of various web information posts include, but are not limited to, blog posts, social media posts, and portfolios. The collection unit collects information from, for example, social media sites, blogs, and portfolio sites. For example, the collection unit can collect information from social media sites such as Twitter, Facebook, and Instagram. The collection unit can also collect information from blogs such as personal blogs, corporate blogs, and technical blogs. The collection unit can also collect information from portfolio sites such as Behance, Dribbble, and GitHub. The analysis unit analyzes personality traits, possessed skills, and business aptitude based on the information collected by the collection unit. Examples of personality traits include, but are not limited to, personality traits, behavioral patterns, and values. Examples of possessed skills include, but are not limited to, technical skills, soft skills, and specialized knowledge. Examples of business aptitude include, but are not limited to, leadership, problem-solving skills, and communication skills. For example, the analysis unit analyzes personality traits from the collected information. The analysis unit can also analyze technical skills from the collected information. The analysis unit can also analyze leadership from the collected information. The patterning unit analyzes and patterns the profile of the person the company is looking for. The profile of the person the company is looking for includes, for example, a desired skill set, experience, personality traits, etc., but is not limited to these examples. The patterning unit collects information from, for example, job postings published by the company, official websites, and industry reports, and patterns the profile of the person the company is looking for. For example, the patterning unit can collect information from online job sites and official company websites. The patterning unit can also collect information from market research reports and industry analysis reports. The matching unit lists the information obtained by the analysis unit and the patterning unit and performs matching. Matching can include, for example, methods such as a scoring system and similarity calculation, but is not limited to these examples.For example, the matching unit compares the characteristics of the information sender with the profile of the person the company is looking for, and performs optimal matching. The sending unit sends an offer letter to the information sender and the company matched by the matching unit. The offer letter may be sent by, for example, email, mail, messaging app, or other methods, but is not limited to these examples. For example, the sending unit collects the contact information of the information sender and sends an offer letter along with the company's job information. In this way, the service platform according to the embodiment can efficiently match information senders on the Internet with the profile of the person the company is looking for, and send an offer letter.

[0081] The collection unit can collect information from social media platforms, blogs, and portfolio sites. The collection unit collects information from, for example, social media platforms, blogs, and portfolio sites. Social media platforms include, but are not limited to, Twitter, Facebook, and Instagram. Blogs include, but are not limited to, personal blogs, corporate blogs, and technical blogs. Portfolio sites include, but are not limited to, Behance, Dribbble, and GitHub. For example, the collection unit collects information from Twitter. The collection unit can also collect information from personal blogs. The collection unit can also collect information from Behance. By collecting information from various platforms, the characteristics of the information sender can be more accurately understood. Some or all of the above-described processing by the collection unit may be performed, for example, using AI, or may be performed without using AI. For example, the collection unit can input data collected from social media platforms into a generation AI, which then analyzes the data.

[0082] The analysis unit can analyze personality traits, possessed skills, and business aptitude from the collected information. For example, the analysis unit can analyze personality traits from the collected information. Examples of personality traits include, but are not limited to, personality traits, behavioral patterns, and values. The analysis unit can also analyze possessed skills from the collected information. Examples of possessed skills include, but are not limited to, technical skills, soft skills, and specialized knowledge. The analysis unit can also analyze business aptitude from the collected information. Examples of business aptitude include, but are not limited to, leadership, problem-solving ability, and communication ability. For example, the analysis unit can analyze personality traits from the collected information. The analysis unit can also analyze technical skills from the collected information. The analysis unit can also analyze leadership from the collected information. This enables more appropriate matching by analyzing the characteristics of the information sender in detail. Some or all of the above-described processing by the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can input the collected data into a generation AI, which then analyzes the data.

[0083] The patterning unit can collect information from job postings, official websites, and industry reports published by companies and create patterns of the profile of the person the company is looking for. For example, the patterning unit collects information from job postings, official websites, and industry reports published by companies and creates patterns of the profile of the person the company is looking for. Job postings published by companies include, but are not limited to, online job posting sites and official company websites. Official websites include, but are not limited to, company homepages and recruitment pages. Industry reports include, but are not limited to, market research reports and industry analysis reports. For example, the patterning unit collects information from online job posting sites. The patterning unit can also collect information from official company websites. The patterning unit can also collect information from market research reports. This allows the profile of the person the company is looking for to be accurately patterned, thereby improving matching accuracy. Some or all of the above-described processing in the patterning unit may be performed using, or without, AI. For example, the patterning unit can input collected data into a generation AI, which then analyzes the data.

[0084] The matching unit can compare the characteristics of the information sender with the profile of the person the company is looking for to perform optimal matching. For example, the matching unit can compare the characteristics of the information sender with the profile of the person the company is looking for to perform optimal matching. Optimal matching can include, but is not limited to, methods such as a scoring system or similarity calculation. For example, the matching unit can compare the characteristics of the information sender with the profile of the person the company is looking for using a scoring system. The matching unit can also compare the characteristics of the information sender with the profile of the person the company is looking for using a similarity calculation. The matching unit can also compare the characteristics of the information sender with the profile of the person the company is looking for using a clustering method. This allows for efficient matching between the information sender and the profile of the person the company is looking for. Some or all of the above-described processing in the matching unit can be performed using, for example, AI, or can be performed without using AI. For example, the matching unit can input collected data into a generation AI, which can then analyze the data.

[0085] The sending unit can collect contact information from the information sender and send an offer letter along with the company's job information. For example, the sending unit collects contact information from the information sender and sends the offer letter along with the company's job information. Contact information includes, but is not limited to, email addresses, telephone numbers, and social media accounts. The offer letter can be sent via, but is not limited to, email, mail, messaging apps, and other methods. For example, the sending unit collects email addresses from the information sender and sends the offer letter along with the company's job information. The sending unit can also collect telephone numbers from the information sender and send the offer letter along with the company's job information. The sending unit can also collect social media accounts from the information sender and send the offer letter along with the company's job information. This enables smooth communication between the information sender and the company. Some or all of the above-described processing by the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can input the collected contact data into a generation AI, which then creates and sends an offer letter.

[0086] The sending unit can promote smooth communication between the information sender and the company when sending an offer letter. The sending unit can promote smooth communication between the information sender and the company when sending an offer letter, for example. Smooth communication includes, but is not limited to, methods such as real-time chat and periodic follow-up. For example, the sending unit can provide real-time chat after sending the offer letter. The sending unit can also perform periodic follow-up. The sending unit can also promote smooth communication using a messaging app. This allows smooth communication between the information sender and the company. Some or all of the above-described processing in the sending unit can be performed using, for example, AI, or can be performed without using AI. For example, the sending unit can generate content for the real-time chat using a generation AI to promote communication between the information sender and the company.

[0087] The matching unit can learn from past matching results and improve the algorithm to improve matching accuracy. For example, the matching unit can learn from past matching results and improve the algorithm to improve matching accuracy. Past matching results include, but are not limited to, success cases, failure cases, feedback, etc. Improvements to the algorithm can include, but are not limited to, parameter adjustment, model retraining, etc. For example, the matching unit can learn from past success cases and improve the algorithm. The matching unit can also learn from past failure cases and improve the algorithm. The matching unit can also improve the algorithm based on feedback. This improves matching accuracy and enables more appropriate matching. Some or all of the above-described processing in the matching unit can be performed using, for example, AI, or can be performed without using AI. For example, the matching unit can learn from past matching results using a generation AI and improve the algorithm.

[0088] The collection unit can anonymize the collected information to protect the privacy of the information sender. For example, the collection unit anonymizes the collected information to protect the privacy of the information sender. Privacy protection includes, but is not limited to, methods such as data anonymization, encryption, and access control. Anonymization includes, but is not limited to, methods such as deleting personally identifiable information and masking data. For example, the collection unit deletes personally identifiable information from the collected data. The collection unit can also mask the data. The collection unit can also encrypt the data. This protects the privacy of the information sender. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can anonymize the collected data using generation AI.

[0089] The sending unit can track interactions between the information sender and the company after sending the offer letter and collect feedback. For example, the sending unit can track interactions between the information sender and the company after sending the offer letter and collect feedback. Examples of tracking interactions include, but are not limited to, email tracking and saving chat logs. Examples of collecting feedback include, but are not limited to, surveys, interviews, and reviews. For example, the sending unit tracks emails. The sending unit can also save chat logs. The sending unit can also conduct surveys. In this way, interactions between the information sender and the company are tracked and feedback is collected. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can track interactions and collect feedback using generation AI.

[0090] The patterning unit may periodically update the profile of the person desired by the company and perform patterning based on the latest job information. For example, the patterning unit may periodically update the profile of the person desired by the company and perform patterning based on the latest job information. Periodic updates include, but are not limited to, monthly updates, quarterly updates, and automatic updates. Methods for obtaining the latest job information include, but are not limited to, RSS feeds and API integration. For example, the patterning unit may perform monthly updates. The patterning unit may also perform quarterly updates. The patterning unit may also perform automatic updates. This allows the profile of the person desired by the company to be patterned based on the latest information. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may collect the latest job information using a generation AI and perform patterning.

[0091] The collection unit can estimate the user's emotions and adjust the timing of information collection based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and adjusts the timing of information collection based on the estimated user emotions. Emotion estimation includes, but is not limited to, methods such as facial expression recognition, text analysis, and voice analysis. The timing of information collection includes, but is not limited to, methods such as real-time collection, periodic collection, and event-driven collection. For example, if the user is feeling stressed, the collection unit reduces the frequency of information collection to reduce the burden. Also, if the user is relaxed, the collection unit can increase the frequency of information collection to collect more information. Also, if the user is excited, the collection unit can collect information in real time and immediately reflect the information. This adjusts the timing of information collection according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit may use a generation AI to estimate the user's emotions and adjust the timing of information collection.

[0092] The collection unit can analyze the information sender's past posting history and select the optimal collection method when collecting information. For example, the collection unit can analyze the information sender's past posting history and select the optimal collection method when collecting information. Methods for analyzing the past posting history include, but are not limited to, methods such as analyzing the content of posts and the frequency of posts. The optimal collection method can include, but is not limited to, methods such as API collection, scraping, and manual collection. For example, the collection unit can prioritize collecting information from platforms on which the information sender has frequently posted in the past. The collection unit can also analyze trends in the content of posts by the information sender and prioritize collecting highly relevant information. The collection unit can also adjust the collection timing based on the frequency of posts by the information sender. This allows the optimal collection method to be selected based on the information sender's past posting history. Some or all of the above-described processing in the collection unit can be performed, for example, using AI, or can be performed without AI. For example, the collection unit can analyze the past posting history using a generation AI and select the optimal collection method.

[0093] The collection unit may perform filtering based on the current activity status and areas of interest of the information sender when collecting information. For example, the collection unit may perform filtering based on the current activity status and areas of interest of the information sender when collecting information. Examples of current activity status include, but are not limited to, the latest posts and online status. Examples of areas of interest include, but are not limited to, tag information and following accounts. Examples of filtering include, but are not limited to, keyword filtering and category filtering. For example, the collection unit may preferentially collect information related to topics in which the information sender is currently interested. The collection unit may also analyze the current activity status of the information sender and collect highly relevant information. The collection unit may also narrow the scope of information to be collected based on the areas of interest of the information sender. This filters the information based on the current activity status and areas of interest of the information sender. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without AI. For example, the collection unit may analyze the current activity status and areas of interest of the information sender using a generation AI and perform filtering.

[0094] The collection unit can select the optimal collection means depending on the input method of the information sender when collecting information. For example, the collection unit selects the optimal collection means depending on the input method (voice, text, image, etc.) of the information sender when collecting information. Input methods include, but are not limited to, voice input, text input, image input, etc. The optimal collection means includes, but are not limited to, voice recognition, OCR, text analysis, etc. For example, if the information sender sends information by voice, the collection unit can collect information using voice recognition technology. Also, if the information sender sends information by text, the collection unit can collect information using text analysis technology. Also, if the information sender sends information by image, the collection unit can collect information using image recognition technology. In this way, the optimal collection means is selected depending on the input method of the information sender. Some or all of the above-mentioned processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze the input method of the information sender using generation AI and select the optimal collection means.

[0095] The collection unit can estimate the user's emotions and determine the priority of information to be collected based on the estimated user emotions. The collection unit, for example, estimates the user's emotions and determines the priority of information to be collected based on the estimated user emotions. Emotion estimation includes, but is not limited to, methods such as facial expression recognition, text analysis, and voice analysis. Information prioritization includes, but is not limited to, methods such as importance scoring and urgency assessment. For example, when the user is stressed, the collection unit postpones information of low importance. Furthermore, when the user is relaxed, the collection unit can prioritize collecting detailed information. Furthermore, when the user is excited, the collection unit can prioritize collecting important information in real time. In this way, the priority of information to be collected is determined according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the collection unit may be performed using, for example, an AI, or without using an AI. For example, the collection unit can use the generation AI to estimate the user's emotions and determine the priority of the information to be collected.

[0096] When collecting information, the collection unit can prioritize collecting highly relevant information by taking into account the geographical location information of the information sender. For example, when collecting information, the collection unit prioritizes collecting highly relevant information by taking into account the geographical location information of the information sender. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, location information services, etc. Examples of highly relevant information include, but are not limited to, information about geographically nearby areas and trend information for the same area. For example, when the information sender is in a specific area, the collection unit prioritizes collecting information related to that area. The collection unit can also collect information specific to the area based on the geographical location information of the information sender. Furthermore, when the information sender is moving, the collection unit can also collect highly relevant information based on the current location. In this way, highly relevant information is preferentially collected based on the geographical location information of the information sender. Some or all of the above-described processing by the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze the geographical location information of the information sender using a generation AI and preferentially collect highly relevant information.

[0097] The collection unit can analyze the social media activity of the information sender when collecting information and collect related information. For example, the collection unit can analyze the social media activity of the information sender when collecting information and collect related information. Social media activity includes, but is not limited to, analysis of post content and engagement. Related information includes, but is not limited to, information on the same topic and related hashtags. For example, the collection unit can collect related information based on information shared by the information sender on social media. The collection unit can also analyze the social media activity history of the information sender and collect highly relevant information. The collection unit can also refer to the activities of the information sender's friends on social media. In this way, related information is collected based on the social media activity of the information sender. Some or all of the above-described processing in the collection unit can be performed, for example, using AI or without AI. For example, the collection unit can analyze the social media activity of the information sender using generation AI and collect related information.

[0098] The collection unit can customize the collection method by reflecting the information sender's past feedback when collecting information. For example, the collection unit customizes the collection method by reflecting the information sender's past feedback when collecting information. Past feedback includes, but is not limited to, survey results, review comments, etc. Customizing the collection method includes, but is not limited to, parameter adjustment based on feedback, changing the collection means, etc. For example, the collection unit adjusts the collection method based on feedback provided by the information sender in the past. The collection unit can also analyze the information sender's past feedback and select the optimal collection means. The collection unit can also adjust the range of information to be collected by reflecting the information sender's feedback. This customizes the collection method based on the information sender's past feedback. Some or all of the above-described processing in the collection unit may be performed using, for example, AI, or may be performed without using AI. For example, the collection unit can analyze past feedback using a generation AI and customize the collection method.

[0099] The analysis unit can estimate the user's emotion and adjust the presentation method of the analysis based on the estimated user's emotion. The analysis unit, for example, estimates the user's emotion and adjusts the presentation method of the analysis based on the estimated user's emotion. Emotion estimation includes, but is not limited to, facial expression recognition, text analysis, and voice analysis. Analysis presentation methods include, but are not limited to, graph display, text report, and infographic. For example, if the user is nervous, the analysis unit provides a simple, highly visible presentation method. If the user is relaxed, the analysis unit can provide a presentation method that includes detailed information. If the user is in a hurry, the analysis unit can provide a presentation method that focuses on the main points. This adjusts the presentation method of the analysis according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can use generative AI to infer a user's emotions and adjust how the analysis is presented.

[0100] The analysis unit may adjust the level of detail of the analysis based on the importance of the information sender during the analysis. For example, the analysis unit may adjust the level of detail of the analysis based on the importance of the information sender during the analysis. Examples of the importance of the information sender include, but are not limited to, the number of followers, influence score, and engagement rate. Examples of the level of detail of the analysis include, but are not limited to, detailed data analysis, summary reports, and other methods. For example, the analysis unit may perform a detailed analysis on information senders with high importance. The analysis unit may also perform a simplified analysis on information senders with low importance. The analysis unit may also adjust the priority of the analysis based on the importance of the information sender. This adjusts the level of detail of the analysis based on the importance of the information sender. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit may evaluate the importance of the information sender using a generation AI and adjust the level of detail of the analysis.

[0101] The analysis unit can apply different analysis algorithms depending on the category of the information provider during analysis. For example, the analysis unit applies different analysis algorithms depending on the category of the information provider during analysis. Examples of information provider categories include, but are not limited to, industry categories, fields of expertise, and interests. Examples of different analysis algorithms include, but are not limited to, clustering algorithms, regression analysis, and classification algorithms. For example, the analysis unit can apply an analysis algorithm that emphasizes technical skills to technical information providers. Furthermore, the analysis unit can apply an analysis algorithm that emphasizes creativity to creative information providers. Furthermore, the analysis unit can apply an analysis algorithm that emphasizes business aptitude to business information providers. In this way, the optimal analysis algorithm is applied depending on the category of the information provider. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without using AI. For example, the analysis unit can classify the category of the information provider using a generation AI and apply an appropriate analysis algorithm.

[0102] The analysis unit can improve the accuracy of the analysis by referring to the information sender's past analysis results during analysis. For example, the analysis unit can improve the accuracy of the analysis by referring to the information sender's past analysis results during analysis. Past analysis results include, but are not limited to, past reports, database query results, etc. Analysis accuracy can include, but are not limited to, accuracy evaluation metrics, model retraining, etc. For example, the analysis unit can adjust the current analysis based on the information sender's past analysis results. The analysis unit can also learn from past analysis results and improve the analysis algorithm. The analysis unit can also improve the accuracy of the analysis by referring to the information sender's past analysis results. By referring to past analysis results, the accuracy of the analysis can be improved. Some or all of the above-described processing in the analysis unit can be performed, for example, using AI or without AI. For example, the analysis unit can learn from past analysis results using generative AI to improve the accuracy of the analysis.

[0103] The analysis unit can estimate the user's emotion and adjust the length of the analysis based on the estimated user emotion. The analysis unit, for example, estimates the user's emotion and adjusts the length of the analysis based on the estimated user emotion. Emotion estimation can be performed using, for example, facial expression recognition, text analysis, and voice analysis, but is not limited to these examples. The length of the analysis can be performed using, for example, a detailed report, a summary report, and other methods, but is not limited to these examples. For example, the analysis unit can provide a short, concise analysis if the user is in a hurry. The analysis unit can also provide a longer analysis with detailed explanations if the user is relaxed. The analysis unit can also provide an analysis with visually stimulating effects if the user is excited. In this way, the length of the analysis can be adjusted according to the user's emotion. Emotion estimation can be achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the analysis unit can be performed using, for example, AI, or without AI. For example, the analysis unit can use generative AI to estimate the user's emotions and adjust the length of the analysis.

[0104] The analysis unit may determine the analysis priority based on the posting time of the information sender during analysis. For example, the analysis unit may determine the analysis priority based on the posting time of the information sender during analysis. The posting time may include, but is not limited to, metadata of the posting date and time, a timestamp, etc. The analysis priority may include, but is not limited to, methods such as urgency assessment and importance scoring. For example, the analysis unit may prioritize analysis of recent posts to provide the latest information. The analysis unit may also supplement the current analysis with reference to past posts. The analysis unit may also adjust the analysis priority based on the posting time. This allows the analysis priority to be determined based on the posting time of the information sender. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may analyze the posting time using a generation AI to determine the analysis priority.

[0105] The analysis unit can adjust the order of analysis based on the relevance of the information senders during analysis. The analysis unit, for example, adjusts the order of analysis based on the relevance of the information senders during analysis. Relevance includes, but is not limited to, methods such as co-occurrence network analysis and similarity calculation. The order of analysis includes, but is not limited to, methods such as priority ordering and category ordering. For example, the analysis unit prioritizes analysis when the relevance of the information senders is high. Furthermore, the analysis unit can postpone analysis when the relevance of the information senders is low. Furthermore, the analysis unit can adjust the order of analysis based on the relevance of the information senders. In this way, the order of analysis is adjusted based on the relevance of the information senders. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit can evaluate the relevance of the information senders using a generation AI and adjust the order of analysis.

[0106] The analysis unit may adjust the use of technical terms in the analysis according to the expertise level of the information sender during the analysis. For example, the analysis unit may adjust the use of technical terms in the analysis according to the expertise level of the information sender during the analysis. Examples of expertise levels include, but are not limited to, qualifications, past achievements, and the number of followers. The use of technical terms may include, but are not limited to, definitions of technical terms and replacement with general terms. For example, if the expertise level of the information sender is high, the analysis unit may provide an analysis that uses a lot of technical terms. Furthermore, if the expertise level of the information sender is low, the analysis unit may provide an analysis that explains the information in simple terms. Furthermore, the analysis unit may adjust the use of technical terms in the analysis according to the expertise level of the information sender. This allows the use of technical terms that are optimal for the expertise level of the information sender. Some or all of the above-described processing in the analysis unit may be performed using, for example, AI, or may be performed without AI. For example, the analysis unit may use a generation AI to evaluate the expertise level of the information sender and adjust the use of technical terms.

[0107] The patterning unit can estimate the user's emotion and adjust the patterning criteria based on the estimated user's emotion. The patterning unit, for example, estimates the user's emotion and adjusts the patterning criteria based on the estimated user's emotion. Emotion estimation includes, but is not limited to, methods such as facial expression recognition, text analysis, and voice analysis. Patterning criteria include, but are not limited to, methods such as clustering techniques and pattern recognition algorithms. For example, the patterning unit performs detailed patterning when the user is relaxed. The patterning unit can also perform simplified patterning when the user is in a hurry. The patterning unit can also perform visually stimulating patterning when the user is excited. In this way, the patterning criteria are adjusted according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may use a generation AI to estimate the user's emotions and adjust the patterning criteria.

[0108] The patterning unit can improve the accuracy of the patterning by taking into account the interrelationships of the profile of the person desired by the company during patterning. For example, the patterning unit can improve the accuracy of the patterning by taking into account the interrelationships of the profile of the person desired by the company during patterning. Examples of interrelationships include, but are not limited to, methods such as co-occurrence network analysis and correlation analysis. Examples of the accuracy of the patterning include, but are not limited to, methods such as accuracy evaluation indexes and model retraining. For example, the patterning unit can analyze the interrelationships of the profile of the person desired by the company and improve the accuracy of the patterning. The patterning unit can also adjust the patterning criteria by taking into account the interrelationships of the profile of the person desired by the company. The patterning unit can also improve the accuracy of the patterning based on the interrelationships of the profile of the person desired by the company. In this way, the accuracy of the patterning is improved by taking into account the interrelationships of the profile of the person desired by the company. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit can analyze the interrelationships of the profile of the person desired by the company using generation AI to improve the accuracy of the patterning.

[0109] The patterning unit may perform patterning while taking into account the attribute information of the companies. For example, the patterning unit may perform patterning while taking into account the attribute information of the companies. The attribute information may include, but is not limited to, for example, the size, industry, and location of the companies. For example, the patterning may include, but is not limited to, clustering techniques and pattern recognition algorithms. For example, the patterning unit may adjust the patterning criteria according to the industry and size of the companies. The patterning unit may also improve the accuracy of the patterning based on the attribute information of the companies. The patterning unit may also adjust the patterning criteria while taking into account the attribute information of the companies. This allows patterning based on the attribute information of the companies. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may analyze the attribute information of the companies using a generation AI and perform patterning.

[0110] The patterning unit can weight the patterns based on the frequency of job postings by companies during patterning. For example, the patterning unit weights the patterns based on the frequency of job postings by companies during patterning. Job posting frequency includes, but is not limited to, for example, the number of job postings and the period of time for job postings. Weighting methods include, but are not limited to, weighting based on frequency and importance. For example, the patterning unit strengthens the weighting when the frequency of job postings by companies is high. Furthermore, the patterning unit can weaken the weighting when the frequency of job postings by companies is low. Furthermore, the patterning unit can adjust the weighting of the patterns based on the frequency of job postings by companies. In this way, the weighting of the patterns is performed based on the frequency of job postings by companies. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit can analyze the frequency of job postings by companies using a generation AI and weight the patterns.

[0111] The patterning unit can estimate the user's emotion and adjust the order in which the patterning results are displayed based on the estimated user's emotion. The patterning unit, for example, estimates the user's emotion and adjusts the order in which the patterning results are displayed based on the estimated user's emotion. Emotion estimation can be performed using, for example, facial expression recognition, text analysis, and voice analysis, but is not limited to these examples. The display order can be performed using, for example, priority-based ordering, category-based ordering, and other methods, but is not limited to these examples. For example, if the user is relaxed, the patterning unit can prioritize displaying detailed patterning results. If the user is in a hurry, the patterning unit can prioritize displaying key point patterning results. If the user is excited, the patterning unit can prioritize displaying visually stimulating patterning results. In this way, the order in which the patterning results are displayed is adjusted according to the user's emotion. Emotion estimation is achieved using, for example, an emotion estimation function using an emotion engine or a generation AI. The generation AI can be, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may use a generation AI to estimate the user's emotions and adjust the order in which the patterning results are displayed.

[0112] The patterning unit may perform patterning by taking into account the geographical distribution of companies. For example, the patterning unit may perform patterning by taking into account the geographical distribution of companies. Examples of geographical distribution include, but are not limited to, company locations and job information by region. Examples of patterning include, but are not limited to, clustering techniques and pattern recognition algorithms. For example, the patterning unit may adjust the patterning criteria based on company locations. The patterning unit may also improve the accuracy of the patterning by taking into account the geographical distribution of companies. The patterning unit may also adjust the patterning criteria based on the geographical distribution of companies. This allows patterning based on the geographical distribution of companies. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without using AI. For example, the patterning unit may analyze the geographical distribution of companies using a generation AI and perform patterning.

[0113] The patterning unit can improve the accuracy of the patterning by referring to the company's related literature during patterning. For example, the patterning unit can improve the accuracy of the patterning by referring to the company's related literature during patterning. Examples of related literature include, but are not limited to, industry reports, academic papers, and patent documents. Methods for improving the accuracy of the patterning include, but are not limited to, accuracy evaluation indices and model retraining. For example, the patterning unit can adjust the patterning criteria based on the company's related literature. The patterning unit can also improve the accuracy of the patterning by referring to the company's related literature. The patterning unit can also adjust the patterning criteria taking the company's related literature into consideration. By referring to the company's related literature, the accuracy of the patterning is improved. Some or all of the above-described processing in the patterning unit can be performed using, for example, AI, or without AI. For example, the patterning unit can analyze the company's related literature using a generation AI to improve the accuracy of the patterning.

[0114] The patterning unit may perform patterning by taking into account the market value of the company. For example, the patterning unit may perform patterning by taking into account the market value of the company. Market value may include, but is not limited to, a company's sales, stock price, and industry position. Patterning may include, but is not limited to, clustering techniques, pattern recognition algorithms, and other methods. For example, the patterning unit may increase weighting when the company's market value is high. Furthermore, the patterning unit may decrease weighting when the company's market value is low. Furthermore, the patterning unit may adjust the weighting of the patterning based on the company's market value. This allows patterning based on the company's market value. Some or all of the above-described processing in the patterning unit may be performed using, for example, AI, or may be performed without AI. For example, the patterning unit may analyze a company's market value using a generation AI and perform patterning.

[0115] The matching unit can estimate the user's emotion and adjust the matching criteria based on the estimated user's emotion. The matching unit, for example, estimates the user's emotion and adjusts the matching criteria based on the estimated user's emotion. Emotion estimation includes, but is not limited to, methods such as facial expression recognition, text analysis, and voice analysis. Matching criteria include, but are not limited to, methods such as scoring systems and similarity calculations. For example, the matching unit applies detailed matching criteria when the user is relaxed. The matching unit can also apply simplified matching criteria when the user is in a hurry. The matching unit can also apply visually stimulating matching criteria when the user is excited. In this way, the matching criteria are adjusted according to the user's emotion. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the matching unit may be performed using, for example, an AI, or without using an AI. For example, the matching unit can use generative AI to estimate the user's emotions and adjust the matching criteria.

[0116] The matching unit may improve the accuracy of matching by taking into account the relationship between the information sender and the company during matching. For example, the matching unit may improve the accuracy of matching by taking into account the relationship between the information sender and the company during matching. Examples of the relationship include, but are not limited to, co-occurrence network analysis and correlation analysis. Examples of the accuracy of matching include, but are not limited to, accuracy evaluation indexes and model retraining. For example, the matching unit may analyze past interactions between the information sender and the company to improve the accuracy of matching. The matching unit may also adjust matching criteria by taking into account the relationship between the information sender and the company. The matching unit may also improve the accuracy of matching based on the relationship between the information sender and the company. By taking into account the relationship between the information sender and the company, the accuracy of matching is improved. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may analyze the relationship between the information sender and the company using a generation AI to improve the accuracy of matching.

[0117] The matching unit may perform matching by taking into account attribute information of the information sender and the company. For example, the matching unit may perform matching by taking into account attribute information of the information sender and the company. Attribute information may include, for example, but is not limited to, the company's size, industry, and location. Matching may include, for example, but is not limited to, a scoring system, similarity calculation, or other methods. For example, the matching unit may perform matching by comparing the skill set of the information sender with the skill set desired by the company. The matching unit may also perform matching by taking into account the information sender's industry experience and the company's industry. The matching unit may also perform matching by taking into account the information sender's desired work location and the company's location. This allows optimal matching to be performed based on the attribute information of the information sender and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may analyze the attribute information of the information sender and the company using a generation AI to perform matching.

[0118] The matching unit may weight the matching based on the activity frequency of the information sender and the company during matching. For example, the matching unit may weight the matching based on the activity frequency of the information sender and the company during matching. Activity frequency includes, but is not limited to, posting frequency and update frequency. Weighting methods include, but are not limited to, frequency-based weighting and importance-based weighting. For example, the matching unit may increase the weighting if the activity frequency of the information sender is high. Furthermore, the matching unit may decrease the weighting if the activity frequency of the information sender is low. Furthermore, the matching unit may adjust the matching weighting based on the activity frequency of the information sender and the company. This allows the matching weighting to be based on the activity frequency of the information sender and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without AI. For example, the matching unit may use a generation AI to analyze the activity frequency of the information sender and the company and weight the matching.

[0119] The matching unit can estimate the user's emotion and adjust the order in which the matching results are displayed based on the estimated user emotion. The matching unit, for example, estimates the user's emotion and adjusts the order in which the matching results are displayed based on the estimated user emotion. Methods for estimating emotion include, but are not limited to, facial expression recognition, text analysis, and voice analysis. Methods for displaying the results include, but are not limited to, priority-based ordering and category-based ordering. For example, if the user is relaxed, the matching unit may prioritize displaying detailed matching results. If the user is in a hurry, the matching unit may prioritize displaying key matching results. If the user is excited, the matching unit may prioritize displaying visually stimulating matching results. In this way, the order in which the matching results are displayed is adjusted according to the user's emotion. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI may be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may use a generation AI to estimate the user's emotions and adjust the order in which the matching results are displayed.

[0120] The matching unit may perform matching by taking into account the geographical distribution of information senders and companies. For example, the matching unit may perform matching by taking into account the geographical distribution of information senders and companies. Examples of geographical distribution include, but are not limited to, company locations and job information by region. Examples of matching include, but are not limited to, scoring systems and similarity calculations. For example, the matching unit may perform matching by taking into account the residence of the information sender and the location of the company. The matching unit may also perform matching by taking into account the information sender's desired work location and the location of the company. The matching unit may also improve the accuracy of matching based on the geographical distribution of information senders and companies. This allows optimal matching to be performed based on the geographical distribution of information senders and companies. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without using AI. For example, the matching unit may use a generation AI to analyze the geographical distribution of information senders and companies and perform matching.

[0121] The matching unit may improve the accuracy of matching by referring to related literature between the information provider and the company during matching. For example, the matching unit may improve the accuracy of matching by referring to related literature between the information provider and the company during matching. Examples of related literature include, but are not limited to, industry reports, academic papers, and patent documents. Methods for improving the accuracy of matching include, but are not limited to, accuracy evaluation indices and model retraining. For example, the matching unit may perform matching by referring to the information provider's past performance and papers. The matching unit may also improve the accuracy of matching based on related literature between the company. The matching unit may also adjust the matching criteria by taking into account related literature between the information provider and the company. By doing so, the accuracy of matching is improved by referring to related literature between the information provider and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without AI. For example, the matching unit may use a generation AI to analyze related literature between the information provider and the company to improve the accuracy of matching.

[0122] The matching unit may perform matching by taking into account the market value of the information sender and the company. For example, the matching unit may perform matching by taking into account the market value of the information sender and the company. Market value may include, but is not limited to, a company's sales, stock price, and industry position. Matching may include, but is not limited to, a scoring system, similarity calculation, or other methods. For example, the matching unit may increase weighting if the market value of the information sender is high. Furthermore, the matching unit may decrease weighting if the market value of the information sender is low. Furthermore, the matching unit may adjust the matching weighting based on the market value of the information sender and the company. This allows optimal matching to be performed based on the market value of the information sender and the company. Some or all of the above-described processing in the matching unit may be performed using, for example, AI, or may be performed without AI. For example, the matching unit may analyze the market value of the information sender and the company using a generation AI and perform matching.

[0123] The sending unit can estimate the user's emotions and adjust the sending method of the offer letter based on the estimated user emotions. The sending unit, for example, estimates the user's emotions and adjusts the sending method of the offer letter based on the estimated user emotions. Emotion estimation includes, but is not limited to, facial expression recognition, text analysis, and voice analysis. Sending methods include, but are not limited to, email, mail, and messaging apps. For example, the sending unit can send a detailed offer letter if the user is relaxed. The sending unit can also send a simplified offer letter if the user is in a hurry. The sending unit can also send a visually stimulating offer letter if the user is excited. In this way, the sending method of the offer letter is adjusted according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI can be, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit may use a generation AI to estimate the user's emotions and adjust the method of sending the offer letter.

[0124] The sending unit can select the optimal sending method by referring to the information sender's past communication history when sending the offer letter. For example, the sending unit can select the optimal sending method by referring to the information sender's past communication history when sending the offer letter. Examples of past communication history include, but are not limited to, email tracking and chat log storage. Examples of optimal sending methods include, but are not limited to, email, mail, and messaging apps. For example, the sending unit selects the optimal sending method based on a sending method previously preferred by the information sender. The sending unit can also analyze the information sender's past communication history and select the optimal sending method. The sending unit can also adjust the sending method by referring to the information sender's past feedback. In this way, the optimal sending method is selected based on the information sender's past communication history. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the information sender's past communication history using a generation AI and select the optimal sending method.

[0125] The sending unit can customize the content of the offer letter based on the current activity status of the information sender when sending the offer letter. For example, the sending unit customizes the content of the offer letter based on the current activity status of the information sender when sending the offer letter. Examples of the current activity status include, but are not limited to, the latest posts and online status. Examples of customizing the content of the offer letter include, but are not limited to, creating an individual message and adjusting a template. For example, the sending unit sends an offer letter including content related to a topic that the information sender is currently interested in. The sending unit can also analyze the current activity status of the information sender and send an offer letter including highly relevant content. The sending unit can also customize the content of the offer letter based on the information sender's areas of interest. As a result, the content of the offer letter is customized based on the current activity status of the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the current activity status of the information sender using a generation AI and customize the content of the offer letter.

[0126] The sending unit can improve the sending method by reflecting feedback from the information sender when sending an offer letter. For example, the sending unit improves the sending method by reflecting feedback from the information sender when sending an offer letter. Examples of feedback include, but are not limited to, questionnaires, interviews, and reviews. Examples of improving the sending method include, but are not limited to, parameter adjustments and changes to the sending means based on the feedback. For example, the sending unit adjusts the sending method based on feedback previously provided by the information sender. The sending unit can also analyze past feedback from the information sender and select an optimal sending method. The sending unit can also adjust the sending content by reflecting feedback from the information sender. This improves the sending method based on feedback from the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze feedback from the information sender using a generation AI and improve the sending method.

[0127] The sending unit can estimate the user's emotions and determine the priority of offer letters based on the estimated user emotions. The sending unit, for example, estimates the user's emotions and determines the priority of offer letters based on the estimated user emotions. Emotion estimation includes, but is not limited to, methods such as facial expression recognition, text analysis, and voice analysis. Prioritization includes, but is not limited to, methods such as importance scoring and urgency assessment. For example, the sending unit may prioritize sending detailed offer letters when the user is relaxed. Furthermore, the sending unit may prioritize sending simplified offer letters when the user is in a hurry. Furthermore, the sending unit may prioritize sending visually stimulating offer letters when the user is excited. In this way, the priority of offer letters is determined according to the user's emotions. Emotion estimation is realized using an emotion estimation function, for example, using an emotion engine or a generation AI. The generation AI may include, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit may use a generation AI to estimate the user's emotions and determine the priority of offer letters.

[0128] The sending unit can select the optimal sending method by taking into consideration the geographical location information of the information sender when sending the offer letter. For example, the sending unit selects the optimal sending method by taking into consideration the geographical location information of the information sender when sending the offer letter. Examples of geographical location information include, but are not limited to, GPS data, IP addresses, location information services, etc. Examples of optimal sending methods include, but are not limited to, email, mail, messaging apps, etc. For example, the sending unit selects the optimal sending method based on the location of the information sender. The sending unit can also adjust the sending method by taking into consideration the geographical location information of the information sender. The sending unit can also select the optimal sending method based on the geographical location information of the information sender. In this way, the optimal sending method is selected based on the geographical location information of the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the geographical location information of the information sender using a generation AI and select the optimal sending method.

[0129] The sending unit can customize the content of the offer letter by analyzing the social media activity of the information sender when sending the offer letter. For example, the sending unit analyzes the social media activity of the information sender when sending the offer letter to customize the content of the offer letter. Examples of social media activity include, but are not limited to, analyzing posted content and engagement analysis. Examples of customizing the content of the offer letter include, but are not limited to, creating individual messages and adjusting templates. For example, the sending unit customizes the content of the offer letter based on information shared by the information sender on social media. The sending unit can also analyze the social media activity history of the information sender and send an offer letter containing highly relevant content. The sending unit can also refer to the activity of the information sender's friends on social media to send an offer letter containing relevant content. In this way, the content of the offer letter is customized based on the social media activity of the information sender. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the social media activity of the information sender using a generation AI to customize the content of the offer letter.

[0130] The sending unit can customize the sending method by reflecting the information sender's past feedback when sending an offer letter. For example, the sending unit customizes the sending method by reflecting the information sender's past feedback when sending an offer letter. Past feedback includes, but is not limited to, survey results, review comments, etc. Customizing the sending method includes, but is not limited to, parameter adjustment based on feedback, changing the sending means, etc. For example, the sending unit adjusts the sending method based on feedback previously provided by the information sender. The sending unit can also analyze the information sender's past feedback and select the optimal sending method. The sending unit can also adjust the sending content by reflecting the information sender's feedback. In this way, the sending method is customized based on the information sender's past feedback. Some or all of the above-described processing in the sending unit may be performed using, for example, AI, or may be performed without using AI. For example, the sending unit can analyze the information sender's past feedback using a generation AI and customize the sending method. === Hard Collateral 1-1 === Each of the multiple elements, including the collection unit, analysis unit, pattern generation unit, matching unit, and sending unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the collection unit is realized by either the data processing device 12 or the smart device 14. For example, the identification processing unit 290 of the data processing device 12 collects various web information posts from information senders on the Internet. The analysis unit, realized, for example, by the identification processing unit 290 of the data processing device 12, analyzes personal characteristics, skills, and business aptitude based on the collected information. The pattern generation unit, realized, for example, by the identification processing unit 290 of the data processing device 12, analyzes and patterns the profile of the person desired by the company. The matching unit, realized, for example, by the identification processing unit 290 of the data processing device 12, lists the information obtained by the analysis unit and pattern generation unit and performs matching. The sending unit, realized, for example, by the control unit 46A of the smart device 14, sends an offer letter to the information sender and the company matched by the matching unit. === Hard Collateral 1-2 === Each of the multiple elements, including the collection unit, analysis unit, pattern generation unit, matching unit, and sending unit, described above, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the collection unit is realized by either the data processing device 12 or the smart glasses 214. For example, the identification processing unit 290 of the data processing device 12 collects various web information posts from information senders on the Internet. The analysis unit, realized, for example, by the identification processing unit 290 of the data processing device 12, analyzes personal characteristics, skills, and business aptitude based on the collected information. The pattern generation unit, realized, for example, by the identification processing unit 290 of the data processing device 12, analyzes and patterns the profile of the person desired by the company. The matching unit, realized, for example, by the identification processing unit 290 of the data processing device 12, lists the information obtained by the analysis unit and pattern generation unit and performs matching. The sending unit, realized, for example, by the control unit 46A of the smart glasses 214, sends an offer letter to the information sender and the company matched by the matching unit. === Hard Collateral 1-3 === Each of the multiple elements, including the collection unit, analysis unit, pattern generation unit, matching unit, and sending unit, described above, is implemented, for example, by at least one of the headset-type terminal 314 and the data processing device 12. For example, the collection unit is implemented by either the data processing device 12 or the headset-type terminal 314. For example, the identification processing unit 290 of the data processing device 12 collects various web information posts from information senders on the Internet. The analysis unit, implemented, for example, by the identification processing unit 290 of the data processing device 12, analyzes personal characteristics, skills, and business aptitude based on the collected information. The pattern generation unit, implemented, for example, by the identification processing unit 290 of the data processing device 12, analyzes and patterns the profile of the person desired by the company. The matching unit, implemented, for example, by the identification processing unit 290 of the data processing device 12, lists the information obtained by the analysis unit and pattern generation unit and performs matching. The sending unit, implemented, for example, by the control unit 46A of the headset-type terminal 314, sends offer letters to the information senders and companies matched by the matching unit. === Hard Collateral 1-4 === Each of the multiple elements, including the collection unit, analysis unit, pattern generation unit, matching unit, and sending unit, described above, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the collection unit is realized by either the data processing device 12 or the robot 414. For example, the identification processing unit 290 of the data processing device 12 collects various web information posts from information senders on the Internet. The analysis unit, realized, for example, by the identification processing unit 290 of the data processing device 12, analyzes personal characteristics, skills, and business aptitude based on the collected information. The pattern generation unit, realized, for example, by the identification processing unit 290 of the data processing device 12, analyzes and patterns the profile of the person desired by the company. The matching unit, realized, for example, by the identification processing unit 290 of the data processing device 12, lists the information obtained by the analysis unit and pattern generation unit and performs matching. The sending unit, realized, for example, by the control unit 46A of the robot 414, sends offer letters to the information senders and companies matched by the matching unit.

[0131] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0132] The collection unit can also analyze the content of past posts by the information provider and adjust the method of collecting information based on the tone and style of the posts. For example, if the information provider has posted in a positive tone in the past, the collection unit can prioritize collecting information with a similar tone. Also, if the information provider has posted a lot of technical content, the collection unit can prioritize collecting technical information. Furthermore, if the information provider uses a lot of visual content, the collection unit can prioritize collecting information including images and videos. This makes it possible to collect more relevant information based on the content of past posts by the information provider.

[0133] The analysis unit can also estimate the emotions of the message sender and adjust the analysis approach based on the estimated emotions. For example, if the message sender is feeling stressed, the analysis unit can provide a concise and to-the-point analysis. If the message sender is feeling relaxed, the analysis unit can provide a detailed analysis. Furthermore, if the message sender is excited, the analysis results can be presented using visually appealing graphs and infographics. This makes it possible to select the optimal analysis approach depending on the message sender's emotions.

[0134] The pattern creation department can also take into account a company's culture and values ​​when creating patterns for the type of person a company is looking for. For example, the pattern creation department analyzes the values ​​that a company values ​​(e.g., innovation, teamwork, customer orientation, etc.) and creates patterns for the type of person they are looking for based on these. It can also create patterns for appropriate types of people by taking into account the company's culture (e.g., flat organizational structure, encouragement of remote work, etc.). Furthermore, it can analyze a company's past hiring data and adjust the criteria for pattern creation based on successful hiring cases. This makes it possible to create patterns for people who match the company's culture and values.

[0135] The matching unit can also estimate the emotions of the information sender and adjust the timing of matching based on the estimated emotions. For example, the matching unit can delay the notification of matching if the information sender is feeling stressed. Also, if the information sender is relaxed, the matching unit can immediately notify the information sender of matching. Furthermore, if the information sender is excited, the matching result can be notified in real time. This makes it possible to notify the information sender of matching at the optimal timing depending on the emotions of the information sender.

[0136] After sending the offer letter, the sending department can track the exchange between the information sender and the company and collect feedback. For example, the sending department can track emails to check whether the offer letter has been opened. The sending department can also save chat logs and analyze the content of the exchanges. Furthermore, the sending department can conduct surveys and collect feedback from both the information sender and the company. This makes it possible to track the exchange between the information sender and the company and improve services based on the feedback.

[0137] The collection unit can also estimate the emotions of the information sender and determine the priority of the information to be collected based on the estimated emotions. For example, if the information sender is feeling stressed, the collection unit can postpone less important information. Also, if the information sender is relaxed, the collection unit can prioritize collecting detailed information. Furthermore, if the information sender is excited, the collection unit can prioritize collecting important information in real time. In this way, the priority of the information to be collected is determined according to the emotions of the information sender.

[0138] The analysis unit can also adjust the use of technical terms in the analysis depending on the information sender's level of expertise. For example, if the information sender's level of expertise is high, the analysis unit can provide an analysis that uses a lot of technical terms. If the information sender's level of expertise is low, the analysis unit can provide an analysis that explains things in simple terms. Furthermore, the analysis unit can adjust the level of detail in the analysis depending on the information sender's level of expertise. This makes it possible to provide an optimal analysis depending on the information sender's level of expertise.

[0139] The pattern generation unit can also take into account the market value of a company when generating patterns for the type of person a company is looking for. For example, the pattern generation unit can analyze a company's sales, stock price, and position within the industry, and generate patterns for the type of person it is looking for based on this. In addition, if the company's market value is high, the pattern generation unit can increase the weighting, and if it is low, the pattern generation unit can decrease the weighting. Furthermore, the pattern generation criteria can be adjusted based on the company's market value. This makes it possible to generate patterns for the optimal type of person based on the company's market value.

[0140] The matching unit can also estimate the emotion of the information sender and adjust the matching criteria based on the estimated emotion. For example, the matching unit can apply detailed matching criteria if the information sender is relaxed. Alternatively, the matching unit can apply simplified matching criteria if the information sender is in a hurry. Furthermore, the matching unit can apply visually stimulating matching criteria if the information sender is excited. In this way, the matching criteria are adjusted according to the emotion of the information sender.

[0141] When sending the offer letter, the sending unit may select the optimal sending method taking into consideration the geographical location information of the information sender. For example, the sending unit may select the optimal sending method based on the location of the information sender. The sending unit may also adjust the sending method taking into consideration the geographical location information of the information sender. Furthermore, the sending unit may select the optimal sending method based on the geographical location information of the information sender. In this way, the optimal sending method is selected based on the geographical location information of the information sender.

[0142] The processing flow of the second embodiment will be briefly explained below.

[0143] Step 1: The collection unit collects various web information posts from online information providers. These web information posts include blog articles, social media posts, and portfolios. The collection unit collects information from social media, blogs, and portfolio sites. For example, information is collected from social media sites such as Twitter, Facebook, and Instagram, personal blogs, corporate blogs, technical blogs, and portfolio sites such as Behance, Dribbble, and GitHub. Step 2: The analysis department analyzes the personality traits, skills, and business aptitude based on the information collected by the collection department. Personality traits include personality traits, behavioral patterns, and values, while skills include technical skills, soft skills, and specialized knowledge. Business aptitude includes leadership, problem-solving skills, and communication skills. For example, the analysis department analyzes personality traits, technical skills, and leadership from the collected information. Step 3: The pattern generation department analyzes the profile of the person a company is looking for and creates a pattern. The profile of the person a company is looking for includes the desired skill set, experience, personality traits, etc. The pattern generation department collects information from job postings published by companies, official websites, and industry reports, and creates a pattern of the profile of the person a company is looking for. For example, information is collected from online job sites, official company websites, market research reports, and industry analysis reports. Step 4: The matching section lists the information obtained by the analysis section and patterning section and performs matching. Matching involves methods such as scoring systems and similarity calculations. For example, the matching section compares the characteristics of the information provider with the profile of the person the company is looking for to find the optimal match. Step 5: The sending department sends offer letters to the information senders and companies matched by the matching department. Offer letters can be sent via email, mail, messaging apps, etc. For example, the sending department collects the contact information of the information senders and sends the offer letters along with the company's job information.

[0144] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0145] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0146] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, 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.

[0147] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0148] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0149] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0150] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0151] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0152] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0153] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0154] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0155] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0156] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0157] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0158] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. 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 the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0159] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0160] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0161] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0162] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0163] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0164] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0165] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0166] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0167] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0168] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0169] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0170] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0171] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0172] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0173] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0174] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0175] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0176] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0177] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0178] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0179] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0180] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0181] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0182] 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, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0183] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0184] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0185] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0186] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0187] The control 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0188] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0189] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0190] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0191] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0192] Note that a device other than the data processing device 12 may 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 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0193] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0194] The data generation model 58 is a so-called generative AI. An example of the 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 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AI other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0195] 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 executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0196] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0197] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0198] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0199] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0200] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0201] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[0202] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0203] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0204] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0205] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0206] 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.

[0207] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0208] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0209] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0210] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0211] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0212] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0213] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0214] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0215] [Explanation of symbols]

[0216] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a collection unit that collects various web information content from information providers on the Internet; an analysis unit that analyzes personality traits, skills, and business aptitude based on the information collected by the collection unit; The patterning department analyzes the type of person that companies are looking for and creates patterns; a matching unit that lists the information obtained by the analysis unit and the patterning unit and performs matching; a sending unit that sends an offer letter to the information sender and the company matched by the matching unit. A system characterized by:

2. The collecting unit Collect information from social media, blogs, and portfolio sites 2. The system of claim 1.

3. The analysis unit Analyze personality traits, skills, and business aptitude from collected information 2. The system of claim 1.

4. The patterning unit is Collect information from job postings, official websites, and industry reports published by companies, and create patterns for the type of person the company is looking for.

2. The system of claim 1.

5. The matching unit Compare the characteristics of the information provider with the profile of the person the company is looking for to find the best match 2. The system of claim 1.

6. The sending unit Collect contact information from the source and send them an offer letter along with the company's job information.

2. The system of claim 1.

7. The sending unit Facilitate smooth communication between the sender and the company when sending an offer letter 2. The system of claim 1.

8. The matching unit To improve matching accuracy, the algorithm learns from past matching results and improves the accuracy.

2. The system of claim 1.

Images