System

Abstract

An object of a system according to an embodiment is to identify an appropriate candidate based on the content of an inquiry and respond quickly.SOLUTION: A system includes an inquiry analysis part, a candidate specification part, and a response part. The query analysis unit analyzes the query content by using the generated AI. The candidate specification unit specifies a candidate based on the inquiry content analyzed by the inquiry analysis unit. The response unit responds with information on the candidate specified by the candidate specifying 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 techniques have had the problem of making it difficult to identify suitable candidates based on the content of inquiries and to respond quickly.

[0005] The system according to the embodiment aims to identify suitable candidates based on the content of an inquiry and provide a quick response. [Means for solving the problem]

[0006] The system according to the embodiment includes an inquiry analysis unit, a candidate identification unit, and a response unit. The inquiry analysis unit analyzes the content of the inquiry using a generation AI. The candidate identification unit identifies a candidate based on the content of the inquiry analyzed by the inquiry analysis unit. The response unit responds with information about the candidate identified by the candidate identification unit. [Effects of the Invention]

[0007] The system according to the embodiment can identify suitable candidates based on the inquiry content and respond quickly. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The candidate identification system according to the embodiment of the present invention is a system that uses a generation AI to search for candidates according to the inquiry content and respond with highly relevant employees. This enables the candidate identification system to quickly and appropriately identify candidates according to the inquiry content and respond with highly relevant employees.

[0029] A candidate identification system according to an embodiment includes a query analysis unit, a candidate identification unit, and a response unit. The query analysis unit analyzes the query content using a generation AI. For example, the generation AI analyzes the query content entered by a user and understands the content. The generation AI can analyze the query content using a text generation AI (e.g., GPT-3) or a multimodal generation AI. The candidate identification unit identifies candidates based on the query content analyzed by the query analysis unit. For example, the generation AI identifies the most suitable candidate from an internal database, taking into account the employee's skill set, past project experience, evaluations, etc. The response unit responds with information about the candidate identified by the candidate identification unit. For example, the generation AI responds with information about the identified candidate to the user. This makes it possible to quickly and appropriately identify candidates based on the query content and respond with a highly relevant employee.

[0030] The inquiry analysis unit can perform more accurate analysis by referencing the user's past inquiry history. For example, when the generation AI analyzes the content of an inquiry, the inquiry analysis unit retrieves the user's past inquiry history from a database and references similar inquiries. This increases the relevance between the past inquiry content and the current inquiry content, resulting in more accurate analysis. The inquiry analysis unit also analyzes the content of inquiries made by the user in the past and complements the current inquiry content based on that history. For example, if a user who was previously looking for a project leader makes a similar inquiry again, the past history can be referenced to identify an appropriate candidate. The inquiry analysis unit also allows the generation AI to learn the user's past inquiry history and analyze the patterns of the inquiry content. This allows the generation AI to understand the user's inquiry trends and provide more appropriate analysis results. As a result, referring to the past inquiry history enables more accurate analysis.

[0031] The inquiry analysis unit can refer to the latest industry trends and news to provide more appropriate analysis results. For example, the generation AI in the inquiry analysis unit automatically collects the latest industry trends and news and reflects them in the analysis of the inquiry content. For example, the analysis unit provides analysis results that take into account the latest technological trends and market changes. The inquiry analysis unit also analyzes industry news and trend information to provide the latest information related to the inquiry content. For example, when searching for a new project leader, the latest leadership trends are reflected. The generation AI in the inquiry analysis unit also collects the latest industry news in real time and uses it in the analysis of the inquiry content. For example, when searching for a marketing expert, the analysis results take into account the latest marketing strategies. This allows the generation AI to refer to the latest industry trends and news to provide more appropriate analysis results.

[0032] The query analysis unit can also handle voice or image input, enabling multimodal analysis. For example, the query analysis unit uses a generative AI to analyze voice input and convert the query content into text. For example, if a user makes a voice inquiry, the unit analyzes the voice and provides appropriate analysis results. The query analysis unit also analyzes image input to understand the query content. For example, if a user uploads a sketch or diagram of a project, the unit analyzes the image and provides appropriate analysis results. The query analysis unit also performs multimodal analysis that combines voice input and image input to more accurately understand the query content. For example, if a user uploads an image while explaining something via voice, the unit analyzes both and provides appropriate analysis results. This enables more accurate analysis by supporting both voice and image input.

[0033] The query analysis unit can also handle inquiries in different languages ​​and provide global analysis results. For example, the generation AI in the query analysis unit automatically translates and analyzes inquiries in different languages. For example, it can handle inquiries in multiple languages, such as English and Chinese, and provide appropriate analysis results. The query analysis unit also builds a multilingual analysis system that translates and analyzes inquiry content in different languages ​​in real time. For example, if a user makes an inquiry in Japanese, the content is translated into English and analyzed. The query analysis unit also analyzes inquiry content in different languages ​​using the generation AI and provides appropriate analysis results from a global perspective. For example, it can provide multilingual analysis results for inquiries regarding international projects. This allows it to handle inquiries in different languages ​​and provide global analysis results.

[0034] The candidate identification unit can identify candidates by taking into account employees' internal interpersonal relationships and team dynamics. For example, the candidate identification unit uses a generative AI to analyze employees' internal interpersonal relationships and identify candidates by taking team dynamics into consideration. For example, it may prioritize employees who have worked together in the past in the selection of candidates. The candidate identification unit also analyzes internal team dynamics to identify the most suitable candidate. For example, it may prioritize employees who have leadership experience in a specific team. The candidate identification unit also builds a candidate identification system that takes team dynamics into consideration based on internal interpersonal data. For example, it may select candidates by taking into account collaborative relationships in past projects. This makes it possible to identify more suitable candidates by taking into account employees' internal interpersonal relationships and team dynamics.

[0035] The candidate identification department can also consider employees' outside activities and hobbies to identify more suitable candidates. For example, the generative AI analyzes employees' outside activities and hobbies and takes this into consideration to identify candidates. For example, if a specific hobby or activity is related to a project, those employees will be given priority in selection. The candidate identification department also collects data on employees' outside activities and builds a system to identify candidates based on that data. For example, employees with experience in volunteer activities or community participation will be given priority in selection. The candidate identification department can also develop a candidate identification system that takes outside activities and hobbies into consideration to identify more suitable candidates. For example, employees with specific skills and knowledge will be given priority in selection. In this way, more suitable candidates can be identified by taking employees' outside activities and hobbies into consideration.

[0036] The candidate identification unit can also consider experts from different industries and fields as candidates. For example, the generative AI in the candidate identification unit considers experts from different industries and fields as candidates and identifies the most suitable candidate. For example, an expert in a technical field may be selected as a candidate for a marketing project. The candidate identification unit may also collect data from different industries and build a system to identify candidates based on that data. For example, it may select candidates using participant data from an inter-industry networking event. Furthermore, by considering experts from different fields as candidates, the candidate identification unit can identify candidates with more diverse perspectives. For example, it may select an expert in the design field as a candidate for a technology project. This makes it possible to identify candidates with more diverse perspectives by considering experts from different industries and fields as candidates.

[0037] The candidate identification department can identify candidates who are suitable in the long term, taking into account employees' future career paths and goals. For example, the candidate identification department uses generative AI to analyze employees' future career paths and goals to identify candidates who are suitable in the long term. For example, it may prioritize selecting employees who aspire to become leaders in the future. The candidate identification department also collects employee career path data and builds a system to identify candidates based on that data. For example, it may prioritize selecting employees with specific career goals. The candidate identification department also develops a candidate identification system that takes into account future career paths and goals to identify candidates who are suitable in the long term. For example, it may prioritize selecting employees with specific skills and experience. This makes it possible to identify candidates who are suitable in the long term by taking into account employees' future career paths and goals.

[0038] The response section can include a detailed profile of the candidate and examples of past project successes. For example, the response section may use a generative AI to analyze a candidate's detailed profile and include it in the response. For example, the response section may include detailed information about the candidate's educational background, work history, and skill set. The response section may also include examples of past project successes in the response to highlight the candidate's achievements. For example, the response section may describe leadership experience and achievements in specific projects. The response section may also provide a response that combines the candidate's detailed profile and past successes. For example, the candidate's skill set may be described together with examples of related project successes. This allows for a more reliable response by including a detailed profile of the candidate and examples of past project successes.

[0039] The response unit can also include the candidate's future career path and goals in its response. For example, the response unit uses a generation AI to analyze the candidate's future career path and goals and include them in the response. For example, if the candidate is aiming for leadership in the future, the response unit will emphasize that goal. The response unit also collects candidate career path data and builds a system that provides responses based on that data. For example, information about candidates with specific career goals will be included in the response. The response unit also emphasizes the candidate's long-term aptitude by providing a response that takes future career path and goals into consideration. For example, if the candidate has a plan to acquire specific skills, the plan will be included in the response. This makes it possible to emphasize the candidate's long-term aptitude by including the candidate's future career path and goals in the response.

[0040] The response section can also include a video message or audio message from the candidate. For example, the response section may use a generation AI to analyze the candidate's video message and include it in the response. For example, a video message may be provided in which the candidate introduces themselves or explains the project. The response section may also analyze the audio message and include the candidate's voice-over explanation in the response. For example, a message may be provided in which the candidate explains the project's success stories in audio. The response section may also provide a response that combines a video message and an audio message. For example, a message may be provided in which the candidate introduces themselves in a video, followed by an audio message providing a detailed explanation. This makes it possible to provide a more personalized response by including the candidate's video message or audio message.

[0041] The response unit can also handle replies in different languages ​​and provide global replies. For example, the generation AI automatically translates replies in different languages ​​to provide global replies. For example, the response unit can handle replies in multiple languages, such as English and Chinese. The response unit also builds a multilingual response system and provides replies in different languages ​​in real time. For example, if a user makes an inquiry in Japanese, the response is translated into English and provided. The response unit also analyzes replies in different languages ​​using the generation AI and provides an appropriate response from a global perspective. For example, a multilingual response is provided to an inquiry about an international project. This makes it possible to handle replies in different languages ​​and provide global replies.

[0042] The Internal Database Utilization Department will increase the frequency of database updates, allowing it to always reflect the latest information. For example, the Internal Database Utilization Department will build a system in which generative AI increases the frequency of updates to the internal database and always reflects the latest information. For example, the database will be updated daily to obtain the latest employee information. The Internal Database Utilization Department will also introduce an automatic database update function to reflect the latest information in real time. For example, additional information on new projects or skills will be immediately updated in the database. The Internal Database Utilization Department will also increase the frequency of updates to the internal database, thereby achieving more accurate candidate identification. For example, candidates will be identified based on the latest evaluation data and qualification information. In this way, by increasing the frequency of database updates, it will always reflect the latest information.

[0043] The Internal Database Utilization Department can automatically organize and classify information in the database, improving search efficiency. For example, the Internal Database Utilization Department builds a system in which generative AI automatically organizes and classifies information in the internal database, improving search efficiency. For example, it organizes skill sets and project experience by category. The Internal Database Utilization Department also automatically classifies information in the database, improving search efficiency. For example, it tags and organizes employee evaluation data and qualification information. The Internal Database Utilization Department also introduces an automatic organization and classification function to improve database search efficiency. For example, it makes it possible to quickly search for employees with specific skills and experience. This automatically organizes and classifies information in the database, improving search efficiency.

[0044] The internal database utilization department can also link with external databases to provide a wider range of information. For example, the internal database utilization department builds a system in which the generative AI links with external databases to provide a wider range of information. For example, it links with industry databases and expert databases. The internal database utilization department also integrates information from external databases into the internal database to provide a wider range of information. For example, it imports external qualification information and evaluation data into the internal database. The internal database utilization department also strengthens collaboration with external databases to provide a wider range of information. For example, it integrates external project data and skill data into the internal database. This allows it to link with external databases to provide a wider range of information.

[0045] The Internal Database Utilization Department can also link with databases in different industries and fields to provide information from different fields. For example, the Internal Database Utilization Department builds a system in which the generative AI links with databases in different industries and fields to provide information from different fields. For example, databases in the technical field and the design field are integrated. The Internal Database Utilization Department also integrates databases from different industries into the internal database to provide information from different fields. For example, it links with a database in the medical field to identify candidates suitable for a medical project. The Internal Database Utilization Department also strengthens its link with databases in different fields to provide more diverse information. For example, it links with a database in the marketing field to identify candidates suitable for a marketing project. In this way, by linking with databases in different industries and fields, it is possible to provide information from different fields.

[0046] The inquiry content diversity response unit can provide a more appropriate response by referring to the user's past inquiry history. For example, in the inquiry content diversity response unit, the generation AI retrieves the user's past inquiry history from a database and references similar inquiry content. This increases the relevance between the past inquiry content and the current inquiry content, providing a more appropriate response. The inquiry content diversity response unit also analyzes the user's past inquiries and complements the current inquiry content based on that history. For example, if a user who previously searched for a marketing expert makes a similar inquiry again, the past history can be referenced to identify an appropriate candidate. The inquiry content diversity response unit also has the generation AI learn the user's past inquiry history and analyze the inquiry content patterns. This allows the system to understand the user's inquiry trends and provide a more appropriate response. As a result, referring to the user's past inquiry history enables a more appropriate response.

[0047] The inquiry diversity response unit can refer to the latest industry trends and news to provide a more appropriate response. For example, the generation AI in the inquiry diversity response unit automatically collects the latest industry trends and news and reflects them in the response to the inquiry. For example, the response takes into account the latest technological trends and market changes. The inquiry diversity response unit also analyzes industry news and trend information to provide the latest information related to the inquiry. For example, when searching for employees knowledgeable in the development of a new system, the latest technological trends are reflected. The inquiry diversity response unit also uses the generation AI to collect the latest industry news in real time and use it in the response to the inquiry. For example, when searching for a marketing expert, the response takes into account the latest marketing strategies. This enables a more appropriate response by referring to the latest industry trends and news.

[0048] The inquiry diversity response unit can also respond to voice input or image input, providing multimodal responses. In the inquiry diversity response unit, for example, a generation AI analyzes voice input and converts the inquiry content into text. For example, if a user makes an inquiry by voice, the voice is analyzed and an appropriate response is provided. The inquiry diversity response unit also analyzes image input and understands the inquiry content. For example, if a user uploads a sketch or diagram of a project, the image is analyzed and an appropriate response is provided. The inquiry diversity response unit also provides multimodal responses that combine voice input and image input to more accurately understand the inquiry content. For example, if a user uploads an image while explaining it by voice, both are analyzed and an appropriate response is provided. This enables more accurate responses by supporting both voice input and image input.

[0049] The inquiry content diversity response unit can also respond to inquiries in different languages, enabling global response. For example, the inquiry content diversity response unit uses a generation AI to automatically translate inquiries in different languages ​​and respond accordingly. For example, it can respond to inquiries in multiple languages, such as English and Chinese, and provide appropriate responses. The inquiry content diversity response unit also builds a multilingual system that translates and analyzes inquiry content in different languages ​​in real time. For example, if a user makes an inquiry in Japanese, the content is translated into English and responded to. The inquiry content diversity response unit also uses a generation AI to analyze inquiry content in different languages ​​and provide appropriate responses from a global perspective. For example, it can respond in multiple languages ​​to inquiries regarding international projects. This enables global response by responding to inquiries in different languages.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The inquiry analysis unit can take into account the user's past behavioral history and interests when analyzing the content entered by the user. For example, it can analyze pages the user has viewed in the past and links the user has clicked, and provide information related to the current inquiry. The inquiry analysis unit can also analyze the user's social media activity and provide analysis results based on their interests. For example, if a user frequently posts about a particular topic, it can prioritize providing information related to that topic. The inquiry analysis unit can also analyze the user's purchasing history and suggest related products and services. This makes it possible to provide more personalized analysis results by taking into account the user's past behavioral history and interests.

[0052] The candidate identification department can identify candidates by taking into account the employee's health status and work-life balance. For example, it can analyze employee health data and prioritize employees who are currently in good health. The candidate identification department can also select employees who have a good work-life balance by taking into account the employee's working hours and vacation status. For example, it can prioritize employees who have a history of working long hours. The candidate identification department can also monitor the stress levels of employees and select employees who are less stressed. This makes it possible to identify more suitable candidates by taking into account the employee's health status and work-life balance.

[0053] The response unit can provide relevant educational resources and training programs in response to the user's inquiry. For example, if the user is looking for employees with specific skills, the response unit can suggest online courses and training programs related to those skills. The response unit can also provide information on relevant webinars and seminars based on the user's inquiry. For example, the response unit can provide information on webinars on the latest technology trends. The response unit can also provide a list of books and papers related to the user's inquiry. This makes it possible to help the user improve their knowledge and skills by providing relevant educational resources and training programs in response to the user's inquiry.

[0054] The Candidate Identification Department can identify more suitable candidates by taking into account employees' activities and hobbies outside the company. For example, if a particular hobby or activity is related to a project, it will give priority to selecting that employee. The Candidate Identification Department also collects data on employees' activities outside the company and builds a system to identify candidates based on that data. For example, it will give priority to selecting employees who have experience in volunteer activities or community participation. The Candidate Identification Department can also develop a candidate identification system that takes into account employees' activities and hobbies outside the company to identify more suitable candidates. For example, it will give priority to selecting employees with specific skills and knowledge. In this way, it is possible to identify more suitable candidates by taking into account employees' activities and hobbies outside the company.

[0055] The inquiry analysis unit can refer to the latest industry trends and news to provide more appropriate analysis results. For example, the generation AI automatically collects the latest industry trends and news and reflects them in the analysis of the inquiry content. For example, it provides analysis results that take into account the latest technological trends and market changes. The inquiry analysis unit also analyzes industry news and trend information to provide the latest information related to the inquiry content. For example, when searching for a new project leader, it reflects the latest leadership trends. The inquiry analysis unit also uses the generation AI to collect the latest industry news in real time and use it in analyzing the inquiry content. For example, when searching for a marketing expert, it provides analysis results that take into account the latest marketing strategies. This allows for more appropriate analysis results to be provided by referring to the latest industry trends and news.

[0056] The response section can include a detailed candidate profile and examples of past project successes. For example, the generative AI can analyze a candidate's detailed profile and include it in the response. For example, it can describe the candidate's educational background, work history, and skill set in detail. The response section can also highlight the candidate's achievements by including examples of past project successes in the response. For example, it can describe leadership experience and achievements in specific projects. The response section can also provide a response that combines the candidate's detailed profile and past successes. For example, it can describe the candidate's skill set together with examples of related project successes. This allows for a more reliable response by including a detailed candidate profile and examples of past project successes.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The query analysis unit uses the generation AI to analyze the query content. For example, the generation AI analyzes the query content entered by the user and understands its content. The generation AI can analyze the query content using text generation AI (e.g., GPT-3) or multimodal generation AI. Step 2: The candidate identification unit identifies candidates based on the inquiry content analyzed by the inquiry analysis unit. For example, the generation AI identifies the most suitable candidate from the internal database, taking into account employee skill sets, past project experience, and evaluations. Step 3: The response unit responds with information about the candidate identified by the candidate identification unit. For example, the generation AI responds to the user with information about the identified candidate. This allows the system to quickly and appropriately identify candidates based on the inquiry content and respond with highly relevant employees.

[0059] (Example 2) The candidate identification system according to the embodiment of the present invention is a system that uses a generation AI to search for candidates according to the inquiry content and respond with highly relevant employees. This enables the candidate identification system to quickly and appropriately identify candidates according to the inquiry content and respond with highly relevant employees.

[0060] A candidate identification system according to an embodiment includes a query analysis unit, a candidate identification unit, and a response unit. The query analysis unit analyzes the query content using a generation AI. For example, the generation AI analyzes the query content entered by a user and understands the content. The generation AI can analyze the query content using a text generation AI (e.g., GPT-3) or a multimodal generation AI. The candidate identification unit identifies candidates based on the query content analyzed by the query analysis unit. For example, the generation AI identifies the most suitable candidate from an internal database, taking into account the employee's skill set, past project experience, evaluations, etc. The response unit responds with information about the candidate identified by the candidate identification unit. For example, the generation AI responds with information about the identified candidate to the user. This makes it possible to quickly and appropriately identify candidates based on the query content and respond with a highly relevant employee.

[0061] The inquiry analysis unit can perform more accurate analysis by referencing the user's past inquiry history. For example, when the generation AI analyzes the content of an inquiry, the inquiry analysis unit retrieves the user's past inquiry history from a database and references similar inquiries. This increases the relevance between the past inquiry content and the current inquiry content, resulting in more accurate analysis. The inquiry analysis unit also analyzes the content of inquiries made by the user in the past and complements the current inquiry content based on that history. For example, if a user who was previously looking for a project leader makes a similar inquiry again, the past history can be referenced to identify an appropriate candidate. The inquiry analysis unit also allows the generation AI to learn the user's past inquiry history and analyze the patterns of the inquiry content. This allows the generation AI to understand the user's inquiry trends and provide more appropriate analysis results. As a result, referring to the past inquiry history enables more accurate analysis.

[0062] The query analysis unit can estimate the user's emotional state and provide analysis results according to the emotion. For example, the generation AI analyzes the user's tone of voice and text expression when inputting to estimate the emotional state. For example, if the user feels urgent, it provides analysis results that require a quick response. The query analysis unit also analyzes the user's emotional state in real time and provides appropriate analysis results according to the emotion. For example, if the user feels anxious, it provides analysis results that give a sense of security. The query analysis unit also uses an emotion estimation function to analyze the user's emotional state and provide feedback according to the emotion. For example, if the user has positive emotions, it provides analysis results that maintain those emotions. This allows for more appropriate responses by providing analysis results according to the user's emotional state.

[0063] The inquiry analysis unit can refer to the latest industry trends and news to provide more appropriate analysis results. For example, the generation AI in the inquiry analysis unit automatically collects the latest industry trends and news and reflects them in the analysis of the inquiry content. For example, the analysis unit provides analysis results that take into account the latest technological trends and market changes. The inquiry analysis unit also analyzes industry news and trend information to provide the latest information related to the inquiry content. For example, when searching for a new project leader, the latest leadership trends are reflected. The generation AI in the inquiry analysis unit also collects the latest industry news in real time and uses it in the analysis of the inquiry content. For example, when searching for a marketing expert, the analysis results take into account the latest marketing strategies. This allows the generation AI to refer to the latest industry trends and news to provide more appropriate analysis results.

[0064] The query analysis unit can also handle voice or image input, enabling multimodal analysis. For example, the query analysis unit uses a generative AI to analyze voice input and convert the query content into text. For example, if a user makes a voice inquiry, the unit analyzes the voice and provides appropriate analysis results. The query analysis unit also analyzes image input to understand the query content. For example, if a user uploads a sketch or diagram of a project, the unit analyzes the image and provides appropriate analysis results. The query analysis unit also performs multimodal analysis that combines voice input and image input to more accurately understand the query content. For example, if a user uploads an image while explaining something via voice, the unit analyzes both and provides appropriate analysis results. This enables more accurate analysis by supporting both voice and image input.

[0065] The query analysis unit can also handle inquiries in different languages ​​and provide global analysis results. For example, the generation AI in the query analysis unit automatically translates and analyzes inquiries in different languages. For example, it can handle inquiries in multiple languages, such as English and Chinese, and provide appropriate analysis results. The query analysis unit also builds a multilingual analysis system that translates and analyzes inquiry content in different languages ​​in real time. For example, if a user makes an inquiry in Japanese, the content is translated into English and analyzed. The query analysis unit also analyzes inquiry content in different languages ​​using the generation AI and provides appropriate analysis results from a global perspective. For example, it can provide multilingual analysis results for inquiries regarding international projects. This allows it to handle inquiries in different languages ​​and provide global analysis results.

[0066] The query analysis unit can estimate a user's emotions in real time and provide analysis results that elicit positive emotions. For example, the query analysis unit uses a generative AI to analyze a user's emotions in real time and provide analysis results that elicit positive emotions. For example, if a user is feeling anxious, it provides analysis results that give a sense of security. The query analysis unit also uses an emotion estimation function to analyze the user's emotional state and provide feedback to elicit positive emotions. For example, it provides an encouraging message that makes the user feel positive emotions. The query analysis unit also monitors the user's emotions in real time and provides analysis results that elicit positive emotions. For example, it provides analysis results that make the user feel happy. In this way, by estimating a user's emotions in real time and providing analysis results that elicit positive emotions, it is possible to increase user satisfaction.

[0067] The candidate identification unit can identify candidates by taking into account employees' internal interpersonal relationships and team dynamics. For example, the candidate identification unit uses a generative AI to analyze employees' internal interpersonal relationships and identify candidates by taking team dynamics into consideration. For example, it may prioritize employees who have worked together in the past in the selection of candidates. The candidate identification unit also analyzes internal team dynamics to identify the most suitable candidate. For example, it may prioritize employees who have leadership experience in a specific team. The candidate identification unit also builds a candidate identification system that takes team dynamics into consideration based on internal interpersonal data. For example, it may select candidates by taking into account collaborative relationships in past projects. This makes it possible to identify more suitable candidates by taking into account employees' internal interpersonal relationships and team dynamics.

[0068] The candidate identification unit can estimate the emotional state of employees and identify emotionally suitable candidates. For example, the candidate identification unit uses a generative AI to analyze the emotional state of employees in real time and identify emotionally suitable candidates. For example, it may preferentially select employees whose current emotional state is stable. The candidate identification unit also uses an emotion estimation function to build a system that analyzes the emotional state of employees and identifies emotionally suitable candidates. For example, it may preferentially select employees who have positive emotions. The candidate identification unit also monitors the emotional state of employees and identifies emotionally suitable candidates. For example, it may preferentially select employees who are less stressed. In this way, it is possible to identify emotionally suitable candidates by taking the emotional state of employees into consideration.

[0069] The candidate identification department can also consider employees' outside activities and hobbies to identify more suitable candidates. For example, the generative AI analyzes employees' outside activities and hobbies and takes this into consideration to identify candidates. For example, if a specific hobby or activity is related to a project, those employees will be given priority in selection. The candidate identification department also collects data on employees' outside activities and builds a system to identify candidates based on that data. For example, employees with experience in volunteer activities or community participation will be given priority in selection. The candidate identification department can also develop a candidate identification system that takes outside activities and hobbies into consideration to identify more suitable candidates. For example, employees with specific skills and knowledge will be given priority in selection. In this way, more suitable candidates can be identified by taking employees' outside activities and hobbies into consideration.

[0070] The candidate identification unit can also consider experts from different industries and fields as candidates. For example, the generative AI in the candidate identification unit considers experts from different industries and fields as candidates and identifies the most suitable candidate. For example, an expert in a technical field may be selected as a candidate for a marketing project. The candidate identification unit may also collect data from different industries and build a system to identify candidates based on that data. For example, it may select candidates using participant data from an inter-industry networking event. Furthermore, by considering experts from different fields as candidates, the candidate identification unit can identify candidates with more diverse perspectives. For example, it may select an expert in the design field as a candidate for a technology project. This makes it possible to identify candidates with more diverse perspectives by considering experts from different industries and fields as candidates.

[0071] The candidate identification department can identify candidates who are suitable in the long term, taking into account employees' future career paths and goals. For example, the candidate identification department uses generative AI to analyze employees' future career paths and goals to identify candidates who are suitable in the long term. For example, it may prioritize selecting employees who aspire to become leaders in the future. The candidate identification department also collects employee career path data and builds a system to identify candidates based on that data. For example, it may prioritize selecting employees with specific career goals. The candidate identification department also develops a candidate identification system that takes into account future career paths and goals to identify candidates who are suitable in the long term. For example, it may prioritize selecting employees with specific skills and experience. This makes it possible to identify candidates who are suitable in the long term by taking into account employees' future career paths and goals.

[0072] The candidate identification unit can use the emotion estimation function to identify emotionally positive candidates. For example, the candidate identification unit uses the emotion estimation function with a generation AI to identify emotionally positive candidates. For example, it preferentially selects employees whose current emotional state is positive. The candidate identification unit also builds a system to identify emotionally positive candidates based on the emotion estimation data. For example, it preferentially selects employees with high positive emotion scores. The candidate identification unit also uses the emotion estimation function to identify emotionally positive candidates, thereby increasing the probability of project success. For example, it preferentially selects employees who have positive emotions. In this way, the emotion estimation function can be used to identify emotionally positive candidates.

[0073] The response section can include a detailed profile of the candidate and examples of past project successes. For example, the response section may use a generative AI to analyze a candidate's detailed profile and include it in the response. For example, the response section may include detailed information about the candidate's educational background, work history, and skill set. The response section may also include examples of past project successes in the response to highlight the candidate's achievements. For example, the response section may describe leadership experience and achievements in specific projects. The response section may also provide a response that combines the candidate's detailed profile and past successes. For example, the candidate's skill set may be described together with examples of related project successes. This allows for a more reliable response by including a detailed profile of the candidate and examples of past project successes.

[0074] The response unit can estimate the emotional state of the candidate and provide an emotionally appropriate response. For example, the response unit uses a generation AI to analyze the candidate's emotional state in real time and provide an emotionally appropriate response. For example, if the candidate is feeling stressed, it provides a response that helps the candidate to relax. The response unit also uses an emotion estimation function to build a system that analyzes the candidate's emotional state and provides an emotionally appropriate response. For example, it provides an encouraging message to a candidate who is feeling positive. The response unit also monitors the candidate's emotional state and provides an emotionally appropriate response. For example, if the candidate is feeling anxious, it provides a response that gives a sense of security. This makes it possible to provide an emotionally appropriate response by taking the candidate's emotional state into consideration.

[0075] The response unit can also include the candidate's future career path and goals in its response. For example, the response unit uses a generation AI to analyze the candidate's future career path and goals and include them in the response. For example, if the candidate is aiming for leadership in the future, the response unit will emphasize that goal. The response unit also collects candidate career path data and builds a system that provides responses based on that data. For example, information about candidates with specific career goals will be included in the response. The response unit also emphasizes the candidate's long-term aptitude by providing a response that takes future career path and goals into consideration. For example, if the candidate has a plan to acquire specific skills, the plan will be included in the response. This makes it possible to emphasize the candidate's long-term aptitude by including the candidate's future career path and goals in the response.

[0076] The response section can also include a video message or audio message from the candidate. For example, the response section may use a generation AI to analyze the candidate's video message and include it in the response. For example, a video message may be provided in which the candidate introduces themselves or explains the project. The response section may also analyze the audio message and include the candidate's voice-over explanation in the response. For example, a message may be provided in which the candidate explains the project's success stories in audio. The response section may also provide a response that combines a video message and an audio message. For example, a message may be provided in which the candidate introduces themselves in a video, followed by an audio message providing a detailed explanation. This makes it possible to provide a more personalized response by including the candidate's video message or audio message.

[0077] The response unit can also handle replies in different languages ​​and provide global replies. For example, the generation AI automatically translates replies in different languages ​​to provide global replies. For example, the response unit can handle replies in multiple languages, such as English and Chinese. The response unit also builds a multilingual response system and provides replies in different languages ​​in real time. For example, if a user makes an inquiry in Japanese, the response is translated into English and provided. The response unit also analyzes replies in different languages ​​using the generation AI and provides an appropriate response from a global perspective. For example, a multilingual response is provided to an inquiry about an international project. This makes it possible to handle replies in different languages ​​and provide global replies.

[0078] The reply unit can provide an emotionally positive reply using the emotion estimation function. For example, the generation AI in the reply unit uses the emotion estimation function to provide an emotionally positive reply. For example, if the user is feeling anxious, it provides a reply that gives a sense of security. The reply unit also builds a system that provides emotionally positive replies based on the emotion estimation data. For example, it provides an encouraging message to a user who has positive emotions. The reply unit also increases user satisfaction by using the emotion estimation function to provide an emotionally positive reply. For example, it provides a reply that makes the user feel happy. In this way, emotionally positive replies are possible by using the emotion estimation function.

[0079] The Internal Database Utilization Department will increase the frequency of database updates, allowing it to always reflect the latest information. For example, the Internal Database Utilization Department will build a system in which generative AI increases the frequency of updates to the internal database and always reflects the latest information. For example, the database will be updated daily to obtain the latest employee information. The Internal Database Utilization Department will also introduce an automatic database update function to reflect the latest information in real time. For example, additional information on new projects or skills will be immediately updated in the database. The Internal Database Utilization Department will also increase the frequency of updates to the internal database, thereby achieving more accurate candidate identification. For example, candidates will be identified based on the latest evaluation data and qualification information. In this way, by increasing the frequency of database updates, it will always reflect the latest information.

[0080] The internal database utilization department can estimate the emotional state of employees and provide emotionally appropriate information. For example, the internal database utilization department uses a generative AI to analyze the emotional state of employees in real time and provide emotionally appropriate information. For example, if an employee is feeling stressed, it provides information that helps them relax. The internal database utilization department also uses an emotion estimation function to build a system that analyzes the emotional state of employees and provides emotionally appropriate information. For example, it provides an encouraging message to employees who are feeling positive. The internal database utilization department also monitors the emotional state of employees and provides emotionally appropriate information. For example, if an employee is feeling anxious, it provides information that gives a sense of security. In this way, it is possible to provide emotionally appropriate information by taking the emotional state of employees into consideration.

[0081] The Internal Database Utilization Department can automatically organize and classify information in the database, improving search efficiency. For example, the Internal Database Utilization Department builds a system in which generative AI automatically organizes and classifies information in the internal database, improving search efficiency. For example, it organizes skill sets and project experience by category. The Internal Database Utilization Department also automatically classifies information in the database, improving search efficiency. For example, it tags and organizes employee evaluation data and qualification information. The Internal Database Utilization Department also introduces an automatic organization and classification function to improve database search efficiency. For example, it makes it possible to quickly search for employees with specific skills and experience. This automatically organizes and classifies information in the database, improving search efficiency.

[0082] The internal database utilization department can also link with external databases to provide a wider range of information. For example, the internal database utilization department builds a system in which the generative AI links with external databases to provide a wider range of information. For example, it links with industry databases and expert databases. The internal database utilization department also integrates information from external databases into the internal database to provide a wider range of information. For example, it imports external qualification information and evaluation data into the internal database. The internal database utilization department also strengthens collaboration with external databases to provide a wider range of information. For example, it integrates external project data and skill data into the internal database. This allows it to link with external databases to provide a wider range of information.

[0083] The Internal Database Utilization Department can also link with databases in different industries and fields to provide information from different fields. For example, the Internal Database Utilization Department builds a system in which the generative AI links with databases in different industries and fields to provide information from different fields. For example, databases in the technical field and the design field are integrated. The Internal Database Utilization Department also integrates databases from different industries into the internal database to provide information from different fields. For example, it links with a database in the medical field to identify candidates suitable for a medical project. The Internal Database Utilization Department also strengthens its link with databases in different fields to provide more diverse information. For example, it links with a database in the marketing field to identify candidates suitable for a marketing project. In this way, by linking with databases in different industries and fields, it is possible to provide information from different fields.

[0084] The internal database utilization department can use the emotion estimation function to provide emotionally positive information. For example, the generation AI in the internal database utilization department uses the emotion estimation function to provide emotionally positive information. For example, if an employee is feeling anxious, information that gives a sense of security is provided. The internal database utilization department also builds a system that provides emotionally positive information based on the emotion estimation data. For example, an encouraging message is provided to an employee who has positive emotions. The internal database utilization department also uses the emotion estimation function to provide emotionally positive information, thereby increasing employee satisfaction. For example, information that makes employees feel happy is provided. In this way, emotionally positive information can be provided by using the emotion estimation function.

[0085] The inquiry content diversity response unit can provide a more appropriate response by referring to the user's past inquiry history. For example, in the inquiry content diversity response unit, the generation AI retrieves the user's past inquiry history from a database and references similar inquiry content. This increases the relevance between the past inquiry content and the current inquiry content, providing a more appropriate response. The inquiry content diversity response unit also analyzes the user's past inquiries and complements the current inquiry content based on that history. For example, if a user who previously searched for a marketing expert makes a similar inquiry again, the past history can be referenced to identify an appropriate candidate. The inquiry content diversity response unit also has the generation AI learn the user's past inquiry history and analyze the inquiry content patterns. This allows the system to understand the user's inquiry trends and provide a more appropriate response. As a result, referring to the user's past inquiry history enables a more appropriate response.

[0086] The inquiry content diversity response unit can estimate the user's emotional state and respond according to the emotion. For example, the inquiry content diversity response unit uses a generation AI to analyze the user's tone of voice and text expression when inputting information to estimate the emotional state. For example, if the user feels urgent, a response that requires a quick response is provided. The inquiry content diversity response unit also analyzes the user's emotional state in real time and provides an appropriate response according to the emotion. For example, if the user feels anxious, a response that gives a sense of security is provided. The inquiry content diversity response unit also uses an emotion estimation function to analyze the user's emotional state and provide feedback according to the emotion. For example, if the user has positive emotions, a response that maintains that emotion is provided. In this way, by estimating the user's emotional state, it is possible to provide an appropriate response according to the emotion.

[0087] The inquiry diversity response unit can refer to the latest industry trends and news to provide a more appropriate response. For example, the generation AI in the inquiry diversity response unit automatically collects the latest industry trends and news and reflects them in the response to the inquiry. For example, the response takes into account the latest technological trends and market changes. The inquiry diversity response unit also analyzes industry news and trend information to provide the latest information related to the inquiry. For example, when searching for employees knowledgeable in the development of a new system, the latest technological trends are reflected. The inquiry diversity response unit also uses the generation AI to collect the latest industry news in real time and use it in the response to the inquiry. For example, when searching for a marketing expert, the response takes into account the latest marketing strategies. This enables a more appropriate response by referring to the latest industry trends and news.

[0088] The inquiry diversity response unit can also respond to voice input or image input, providing multimodal responses. In the inquiry diversity response unit, for example, a generation AI analyzes voice input and converts the inquiry content into text. For example, if a user makes an inquiry by voice, the voice is analyzed and an appropriate response is provided. The inquiry diversity response unit also analyzes image input and understands the inquiry content. For example, if a user uploads a sketch or diagram of a project, the image is analyzed and an appropriate response is provided. The inquiry diversity response unit also provides multimodal responses that combine voice input and image input to more accurately understand the inquiry content. For example, if a user uploads an image while explaining it by voice, both are analyzed and an appropriate response is provided. This enables more accurate responses by supporting both voice input and image input.

[0089] The inquiry content diversity response unit can also respond to inquiries in different languages, enabling global response. For example, the inquiry content diversity response unit uses a generation AI to automatically translate inquiries in different languages ​​and respond accordingly. For example, it can respond to inquiries in multiple languages, such as English and Chinese, and provide appropriate responses. The inquiry content diversity response unit also builds a multilingual system that translates and analyzes inquiry content in different languages ​​in real time. For example, if a user makes an inquiry in Japanese, the content is translated into English and responded to. The inquiry content diversity response unit also uses a generation AI to analyze inquiry content in different languages ​​and provide appropriate responses from a global perspective. For example, it can respond in multiple languages ​​to inquiries regarding international projects. This enables global response by responding to inquiries in different languages.

[0090] The inquiry content diversity response unit can use the emotion estimation function to provide an emotionally positive response. For example, in the inquiry content diversity response unit, a generation AI uses the emotion estimation function to provide an emotionally positive response. For example, if the user is feeling anxious, a response that provides a sense of security is provided. Furthermore, the inquiry content diversity response unit builds a system that provides an emotionally positive response based on the emotion estimation data. For example, an encouraging message is provided to a user who has positive emotions. Furthermore, the inquiry content diversity response unit increases user satisfaction by using the emotion estimation function to provide an emotionally positive response. For example, a response that makes the user feel happy is provided. In this way, emotionally positive responses are possible by using the emotion estimation function.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The inquiry analysis unit can take into account the user's past behavioral history and interests when analyzing the content entered by the user. For example, it can analyze pages the user has viewed in the past and links the user has clicked, and provide information related to the current inquiry. The inquiry analysis unit can also analyze the user's social media activity and provide analysis results based on their interests. For example, if a user frequently posts about a particular topic, it can prioritize providing information related to that topic. The inquiry analysis unit can also analyze the user's purchasing history and suggest related products and services. This makes it possible to provide more personalized analysis results by taking into account the user's past behavioral history and interests.

[0093] The candidate identification department can identify candidates by taking into account the employee's health status and work-life balance. For example, it can analyze employee health data and prioritize employees who are currently in good health. The candidate identification department can also select employees who have a good work-life balance by taking into account the employee's working hours and vacation status. For example, it can prioritize employees who have a history of working long hours. The candidate identification department can also monitor the stress levels of employees and select employees who are less stressed. This makes it possible to identify more suitable candidates by taking into account the employee's health status and work-life balance.

[0094] The response unit can provide relevant educational resources and training programs in response to the user's inquiry. For example, if the user is looking for employees with specific skills, the response unit can suggest online courses and training programs related to those skills. The response unit can also provide information on relevant webinars and seminars based on the user's inquiry. For example, the response unit can provide information on webinars on the latest technology trends. The response unit can also provide a list of books and papers related to the user's inquiry. This makes it possible to help the user improve their knowledge and skills by providing relevant educational resources and training programs in response to the user's inquiry.

[0095] The query analysis unit can estimate the emotional state of the user and provide analysis results according to the emotion. For example, if the user feels urgent, it provides analysis results that require a quick response. The query analysis unit also analyzes the user's emotional state in real time and provides appropriate analysis results according to the emotion. For example, if the user feels anxious, it provides analysis results that give a sense of security. The query analysis unit also uses the emotion estimation function to analyze the user's emotional state and provide feedback according to the emotion. For example, if the user has positive emotions, it provides analysis results that maintain those emotions. This allows for more appropriate responses by providing analysis results according to the user's emotional state.

[0096] The Candidate Identification Department can identify more suitable candidates by taking into account employees' activities and hobbies outside the company. For example, if a particular hobby or activity is related to a project, it will give priority to selecting that employee. The Candidate Identification Department also collects data on employees' activities outside the company and builds a system to identify candidates based on that data. For example, it will give priority to selecting employees who have experience in volunteer activities or community participation. The Candidate Identification Department can also develop a candidate identification system that takes into account employees' activities and hobbies outside the company to identify more suitable candidates. For example, it will give priority to selecting employees with specific skills and knowledge. In this way, it is possible to identify more suitable candidates by taking into account employees' activities and hobbies outside the company.

[0097] The reply unit can estimate the user's emotional state and provide an emotionally appropriate reply. For example, if the user is feeling stressed, it provides a reply that helps the user relax. The reply unit also uses the emotion estimation function to analyze the user's emotional state and build a system that provides an emotionally appropriate reply. For example, it provides an encouraging message to a user who is feeling positive. The reply unit also monitors the user's emotional state and provides an emotionally appropriate reply. For example, if the user is feeling anxious, it provides a reply that gives a sense of security. In this way, it is possible to provide an emotionally appropriate reply by taking the user's emotional state into consideration.

[0098] The inquiry analysis unit can refer to the latest industry trends and news to provide more appropriate analysis results. For example, the generation AI automatically collects the latest industry trends and news and reflects them in the analysis of the inquiry content. For example, it provides analysis results that take into account the latest technological trends and market changes. The inquiry analysis unit also analyzes industry news and trend information to provide the latest information related to the inquiry content. For example, when searching for a new project leader, it reflects the latest leadership trends. The inquiry analysis unit also uses the generation AI to collect the latest industry news in real time and use it in analyzing the inquiry content. For example, when searching for a marketing expert, it provides analysis results that take into account the latest marketing strategies. This allows for more appropriate analysis results to be provided by referring to the latest industry trends and news.

[0099] The candidate identification unit can estimate the emotional state of employees and identify emotionally suitable candidates. For example, the generative AI analyzes the emotional state of employees in real time to identify emotionally suitable candidates. For example, it may preferentially select employees whose current emotional state is stable. The candidate identification unit also uses the emotion estimation function to build a system that analyzes the emotional state of employees and identifies emotionally suitable candidates. For example, it may preferentially select employees who have positive emotions. The candidate identification unit also monitors the emotional state of employees and identifies emotionally suitable candidates. For example, it may preferentially select employees who are less stressed. In this way, it is possible to identify emotionally suitable candidates by taking the emotional state of employees into consideration.

[0100] The response section can include a detailed candidate profile and examples of past project successes. For example, the generative AI can analyze a candidate's detailed profile and include it in the response. For example, it can describe the candidate's educational background, work history, and skill set in detail. The response section can also highlight the candidate's achievements by including examples of past project successes in the response. For example, it can describe leadership experience and achievements in specific projects. The response section can also provide a response that combines the candidate's detailed profile and past successes. For example, it can describe the candidate's skill set together with examples of related project successes. This allows for a more reliable response by including a detailed candidate profile and examples of past project successes.

[0101] The query analysis unit can estimate a user's emotions in real time and provide analysis results that elicit positive emotions. For example, the generative AI analyzes a user's emotions in real time and provides analysis results that elicit positive emotions. For example, if the user is feeling anxious, it provides analysis results that give a sense of security. The query analysis unit also uses the emotion estimation function to analyze the user's emotional state and provide feedback to elicit positive emotions. For example, it provides an encouraging message that makes the user feel positive emotions. The query analysis unit also monitors the user's emotions in real time and provides analysis results that elicit positive emotions. For example, it provides analysis results that make the user feel happy. In this way, by estimating a user's emotions in real time and providing analysis results that elicit positive emotions, it is possible to increase user satisfaction.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The query analysis unit uses the generation AI to analyze the query content. For example, the generation AI analyzes the query content entered by the user and understands its content. The generation AI can analyze the query content using text generation AI (e.g., GPT-3) or multimodal generation AI. Step 2: The candidate identification unit identifies candidates based on the inquiry content analyzed by the inquiry analysis unit. For example, the generation AI identifies the most suitable candidate from the internal database, taking into account employee skill sets, past project experience, and evaluations. Step 3: The response unit responds with information about the candidate identified by the candidate identification unit. For example, the generation AI responds to the user with information about the identified candidate. This allows the system to quickly and appropriately identify candidates based on the inquiry content and respond with highly relevant employees.

[0104] 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.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> 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.

[0106] 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.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.

[0112] 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).

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0117] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0118] 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.

[0119] 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.

[0120] 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 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.

[0121] 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.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0132] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0133] 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.

[0134] 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.

[0135] 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 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.

[0136] 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.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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).

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0148] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0149] 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.

[0150] 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.

[0151] 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 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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).

[0157] 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 area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] 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."

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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. [Explanation of symbols]

[0171] 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. an inquiry analysis unit that analyzes the inquiry content using a generation AI; a candidate identification unit that identifies a candidate based on the inquiry content analyzed by the inquiry analysis unit; a reply unit that replies with information about the candidate identified by the candidate identification unit A system characterized by:

2. The query analysis unit Supports voice and image input for multimodal analysis 2. The system of claim 1.

3. The candidate identification unit Identify candidates by considering employees' internal relationships and team dynamics 2. The system of claim 1.

4. The reply unit: Include a detailed profile of the candidate and examples of successful projects from previous projects.

2. The system of claim 1.

5. The In-house Database Utilization Department Estimate employees' emotional state and provide emotionally appropriate information 2. The system of claim 1.

6. The query analysis unit Estimate the user's emotional state and provide analysis results according to the emotion 2. The system of claim 1.

Images