System

Abstract

An object of a system according to an embodiment is to efficiently utilize information of an in-house database or a communication tool and obtain an appropriate answer to an inquiry of a user.SOLUTION: A system includes a database creation part, an inquiry analysis part, an information retrieval part, and a candidate specification part. The database creation unit creates a database of information posted to an in-house database or an open channel of a communication tool. The inquiry analysis part analyzes inquiry contents from a user. The information search unit searches the database based on the content of the inquiry analyzed by the inquiry analysis unit. A candidate specification part specifies a highly relevant employee from the information retrieved by the information retrieval part.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 technologies have had the problem of making it difficult to efficiently utilize information from in-house databases and communication tools to obtain appropriate answers to user inquiries.

[0005] The system according to the embodiment aims to efficiently utilize information from in-house databases and communication tools to obtain appropriate answers to user inquiries. [Means for solving the problem]

[0006] The system according to the embodiment includes a database creation unit, an inquiry analysis unit, an information search unit, and a candidate identification unit. The database creation unit creates a database of information posted to an internal company database or an open channel of a communication tool. The inquiry analysis unit analyzes the content of inquiries from users. The information search unit searches the database based on the content of inquiries analyzed by the inquiry analysis unit. The candidate identification unit identifies highly relevant employees from the information searched by the information search unit. [Effects of the Invention]

[0007] The system according to the embodiment can efficiently utilize information from in-house databases and communication tools to obtain appropriate answers to user inquiries. [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 information provision system according to an embodiment of the present invention is a system that stores information posted to an internal database or an open channel of a communication tool in a database, and uses a generation AI to analyze the content of an inquiry, search for similar posts or related registered users in the database, and respond with highly relevant employees. This makes the information provision system more efficient for information sharing within the company and facilitates smooth communication between employees.

[0029] An information provision system according to an embodiment includes a database creation unit, an inquiry analysis unit, an information search unit, and a candidate identification unit. The database creation unit creates a database of information posted to an internal database or an open channel of a communication tool. For example, the database creation unit collects information posted to an internal database or an open channel of a communication tool and stores it in a database. The database creation unit also builds a database containing information about the posted content and the poster. For example, project progress reports, technical questions, and solutions are posted. The inquiry analysis unit analyzes the content of inquiries from users. For example, if an inquiry is made such as "I would like to know your opinion on the introduction of a new project management tool," the generation AI analyzes the content and extracts related keywords and topics. The information search unit searches the database based on the inquiry content analyzed by the inquiry analysis unit. For example, if a similar question has been posted in the past, the information search unit searches for the posted content and answers. The information search unit also searches for information on employees who are knowledgeable about related topics. The candidate identification unit identifies highly relevant employees from the information searched by the information search unit. For example, the candidate identification unit provides a list of relevant employees in the form of "The following employees have opinions about a new project management tool." The candidate identification unit also provides past postings to provide information that users can refer to. This allows the information provision system according to the embodiment to improve the efficiency of information sharing within the company and facilitate smooth communication between employees. For example, past success stories can be used as reference when launching a new project, and solutions to technical problems can be found quickly. Furthermore, by identifying relevant employees, appropriate advice and opinions can be obtained.

[0030] The database creation unit can evaluate the reliability of the posted content based on the poster's expertise and past posting history, and prioritize highly reliable information for database creation. The database creation unit, for example, registers the poster's expertise and past posting history in a database, and evaluates the reliability of the posted content based on that information. For example, it prioritizes storing information about posters with specialized knowledge. The database creation unit also builds a system for evaluating the feasibility and market demand of posted content based on the poster's industry experience. For example, it highly evaluates and stores information about posters with many years of industry experience in the database. The database creation unit also collects background information about the poster, such as their educational background and work history, and evaluates the reliability of the posted content based on that information. For example, it prioritizes storing information about posters with high educational backgrounds and professional qualifications. This allows the quality of information to be improved by prioritizing highly reliable information for database creation.

[0031] The database creation unit can refer to external data and add supplemental information to the database to understand the context of the posted content. For example, the database creation unit automatically collects related industry news and technical literature to understand the context of the posted content and adds it to the database as supplemental information. For example, it reflects the latest technological trends and market needs. The database creation unit also analyzes external data related to the posted content and builds a system that understands the context of the posted content based on that information. For example, it refers to related technical literature and industry reports. The database creation unit also complements background information of the posted content based on external data and stores it in the database. For example, it adds technical details and market trends related to the posted content. In this way, by referring to external data, the context of the posted content can be more deeply understood and supplemental information can be added.

[0032] The database creation unit can also create a database of posts in audio or video format, integrating multimodal information. For example, the database creation unit allows audio or video data to be uploaded at the time of posting, and evaluates the content of the post based on visual and auditory information. For example, the database creation unit grasps the details of the post using a prototype video or explanatory audio. The database creation unit also uses voice recognition technology to extract the content of the post from the uploaded audio data and save it in the database. Specifically, the audio data is converted into text and saved as the content of the post. The database creation unit also uses video analysis technology to automatically extract the main points of the content of the post from the uploaded video data and save them in the database. In this way, visual and auditory information is integrated with text data and saved in the database. In this way, multimodal information can be integrated by creating a database of information in audio and video format.

[0033] The database creation department can add a function to cross-reference the database to promote information sharing between different departments and project teams. The database creation department, for example, adds a cross-reference function to the database to promote information sharing between different departments and project teams. For example, it links related posts. The database creation department also builds a system that cross-references information in the database and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The database creation department also adds a cross-reference function to the database and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0034] The query analysis unit can improve the analysis accuracy based on background information of the query content. The query analysis unit, for example, collects background information of the query content and improves the analysis accuracy based on that information. For example, it takes into account past query history and the user's expertise. The query analysis unit also registers the user's expertise and past query history in a database and improves the analysis accuracy of the query content based on that information. For example, it prioritizes analysis of queries from users with specialized knowledge. The query analysis unit also builds a system that improves the analysis accuracy based on the background information of the query content. For example, it adjusts the analysis results by taking into account past query history and the user's expertise. In this way, the analysis accuracy can be improved by taking into account the background information.

[0035] The inquiry analysis unit can refer to external data to understand the context of the inquiry and add supplemental information to the analysis results. For example, the inquiry analysis unit automatically collects related industry news and technical literature to understand the context of the inquiry and adds it to the analysis results as supplemental information. For example, it reflects the latest technological trends and market needs. The inquiry analysis unit also analyzes external data related to the inquiry and builds a system that understands the context of the inquiry based on that information. For example, it refers to related technical literature and industry reports. The inquiry analysis unit also complements background information of the inquiry based on external data and saves it in the analysis results. For example, it adds technical details and market trends related to the inquiry. In this way, by referring to external data, the context of the inquiry can be understood more deeply and supplemental information can be added.

[0036] The query analysis unit can add a multilingual analysis function so that it can handle queries in different languages. The query analysis unit adds a multilingual analysis function so that it can handle queries in different languages, for example. For example, it supports multiple languages ​​such as English, French, and Chinese. The query analysis unit also uses the multilingual analysis function to build a system that automatically translates query content in different languages ​​and reflects this in the analysis results. For example, it automatically translates and analyzes query content. The query analysis unit also develops a system that analyzes query content in different languages ​​and provides analysis results in multiple languages ​​based on the results. For example, it analyzes query content in different languages ​​and provides the analysis results in multiple languages. This makes it possible to handle queries in different languages.

[0037] The inquiry analysis unit can convert the inquiry content into a visual note or mind map to make it easier to understand visually. For example, the inquiry analysis unit converts the inquiry content into a visual note to visually display the main points of the inquiry. For example, it shows important points with diagrams or icons. The inquiry analysis unit can also convert the inquiry content into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the inquiry to be understood at a glance. The inquiry analysis unit can also develop tools that automatically generate visual notes or mind maps to enable users to easily visually display the inquiry content. For example, it can provide a function to visualize the inquiry content with drag and drop. This makes it easier to visually understand the inquiry content.

[0038] The information search unit can evaluate the reliability of search results and prioritize displaying highly reliable information. For example, to evaluate the reliability of search results, the information search unit calculates a reliability score based on the poster's expertise and past posting history. For example, it prioritizes displaying information from posters with specialized knowledge. In addition, to evaluate the reliability of search results, the information search unit references external data (e.g., industry news and technical literature) and prioritizes displaying highly reliable information. For example, it references related technical literature and industry reports. In addition, to evaluate the reliability of search results, the information search unit understands the context of the posted content and builds a system that prioritizes displaying highly reliable information. For example, it adds technical details and market trends related to the posted content. This allows the quality of information to be improved by preferentially displaying highly reliable information.

[0039] The information search unit can refer to external data to understand the context of the search results and add supplemental information to the search results. For example, the information search unit automatically collects related industry news and technical literature to understand the context of the search results and adds it as supplemental information to the search results. For example, it reflects the latest technological trends and market needs. The information search unit also analyzes external data related to the search results and builds a system that understands the context of the search results based on that information. For example, it refers to related technical literature and industry reports. The information search unit also complements background information of the search results based on external data and saves it in the search results. For example, it adds technical details and market trends related to the search results. In this way, by referring to external data, the context of the search results can be more deeply understood and supplemental information can be added.

[0040] The information search unit can also include information in audio or video format in its search targets and integrate multimodal information. For example, the information search unit also includes audio and video data in its search targets during a search and evaluates search results based on visual and auditory information. For example, it uses prototype videos or explanatory audio to understand the details of the search results. The information search unit also uses voice recognition technology to extract search content from uploaded audio data and display it in the search results. Specifically, it converts the audio data into text and displays it as a search result. The information search unit also uses video analysis technology to automatically extract the main points of the search content from uploaded video data and display them in the search results. In this way, visual and auditory information is integrated with text data and displayed in the search results. In this way, multimodal information can be integrated by including information in audio and video format in its search targets.

[0041] The information search unit can add a function to cross-reference search results to promote information sharing between different departments and project teams. The information search unit, for example, adds a cross-reference function to search results to promote information sharing between different departments and project teams. For example, related posts are linked together. The information search unit also builds a system that cross-references information within search results and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The information search unit also adds a cross-reference function to search results and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0042] The candidate identification unit can evaluate the reliability of candidates based on their expertise and past posting history, and preferentially display highly reliable candidates. The candidate identification unit, for example, registers the expertise and past posting history of candidates in a database, and evaluates the reliability of candidates based on that information. For example, it preferentially displays information about candidates with specialized knowledge. The candidate identification unit also builds a system that evaluates the feasibility and market demand of candidates based on their industry experience. For example, it displays information about candidates with many years of industry experience as highly rated. The candidate identification unit also collects background information such as the candidates' educational background and work history, and evaluates the reliability of candidates based on that information. For example, it preferentially displays information about candidates with high educational backgrounds and professional qualifications. This makes it possible to improve the quality of information by preferentially displaying highly reliable candidates.

[0043] The candidate identification unit can refer to external data to understand the candidate's context and add supplemental information to the candidate information. For example, the candidate identification unit automatically collects related industry news and technical literature to understand the candidate's context and adds it to the candidate information as supplemental information. For example, it reflects the latest technological trends and market needs. The candidate identification unit also analyzes external data related to the candidate and builds a system that understands the candidate's context based on that information. For example, it refers to related technical literature and industry reports. The candidate identification unit also complements the candidate's background information based on external data and saves it in the candidate information. For example, it adds technical details and market trends related to the candidate. In this way, by referring to external data, the candidate's context can be understood more deeply and supplemental information can be added.

[0044] The candidate identification department can share candidate information between different departments and project teams and form cross-functional teams. The candidate identification department, for example, builds a system for sharing candidate information between different departments and project teams and forming cross-functional teams. For example, it links related candidates. The candidate identification department also builds a system that cross-references candidate information and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The candidate identification department also cross-references candidate information and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This makes it possible to share candidate information between different departments and project teams and form cross-functional teams.

[0045] The candidate identification unit can convert candidate information into visual notes or mind maps to make it easier to understand visually. For example, the candidate identification unit converts candidate information into visual notes to visually display the key points of the candidate. For example, it shows important points using diagrams or icons. The candidate identification unit can also convert candidate information into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the candidate to be understood at a glance. The candidate identification unit can also develop tools that automatically generate visual notes and mind maps to enable users to easily display candidate information visually. For example, it can provide a function to visualize candidate information using drag and drop. This makes it easier to understand candidate information visually.

[0046] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0047] The information provision system can also analyze a user's behavioral history and provide the most appropriate information based on past behavioral patterns. For example, it can analyze what information a user has searched for in the past and what posts they responded to, and provide similar information preferentially. It can also provide information appropriate to specific time periods or situations based on a user's behavioral history. For example, if a project deadline is approaching, it can suggest past success stories or efficient work methods. It can also customize the information provision method that is optimal for each individual user based on the user's behavioral history. For example, it can provide information that makes extensive use of graphs and diagrams to users who prefer visual information, and provide detailed text to users who prefer text information. This makes it possible to provide more personalized information by utilizing a user's behavioral history.

[0048] The database creation unit can evaluate the reliability of the posted content based on the poster's expertise and past posting history, and prioritize highly reliable information for database creation. For example, the poster's expertise and past posting history are registered in a database, and the reliability of the posted content is evaluated based on that information. For example, information about posters with specialized knowledge is preferentially saved. The database creation unit also builds a system for evaluating the feasibility and market demand of posted content based on the poster's industry experience. For example, information about posters with many years of industry experience is highly rated and saved in the database. The database creation unit also collects background information such as the poster's educational background and work history, and evaluates the reliability of the posted content based on that information. For example, information about posters with high educational backgrounds and professional qualifications is preferentially saved. This allows the quality of information to be improved by prioritizing highly reliable information for database creation.

[0049] The database creation unit can refer to external data to understand the context of the posted content and add supplementary information to the database. For example, to understand the context of the posted content, it can automatically collect related industry news and technical literature and add it to the database as supplementary information. For example, it can reflect the latest technological trends and market needs. The database creation unit can also analyze external data related to the posted content and build a system that understands the context of the posted content based on that information. For example, it can refer to related technical literature and industry reports. The database creation unit can also complement background information of the posted content based on external data and store it in the database. For example, it can add technical details and market trends related to the posted content. This makes it possible to more deeply understand the context of the posted content and add supplementary information by referring to external data.

[0050] The database creation unit can also create a database of posts in audio or video format, integrating multimodal information. For example, it can allow users to upload audio or video data at the same time as posting, and evaluate the content of the post based on visual and auditory information. For example, it can grasp the details of the post using a prototype video or explanatory audio. The database creation unit also uses voice recognition technology to extract the content of the post from the uploaded audio data and store it in the database. Specifically, it converts the audio data into text and stores it as the content of the post. The database creation unit also uses video analysis technology to automatically extract the main points of the content of the post from the uploaded video data and store them in the database. In this way, visual and auditory information is integrated with the text data and stored in the database. In this way, multimodal information can be integrated by creating a database of information in audio and video format.

[0051] The database creation department can add a function to cross-reference the database to promote information sharing between different departments and project teams. For example, a cross-reference function can be added to the database to promote information sharing between different departments and project teams. For example, related posts can be linked together. The database creation department can also build a system that cross-references information in the database and automatically displays related information to facilitate information sharing between departments. For example, it can display progress information for related projects. The database creation department can also add a cross-reference function to the database to integrate related information to promote information sharing between different project teams. For example, it can share technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0052] The query analysis unit can improve the analysis accuracy based on background information about the query content. For example, it collects background information about the query content and improves the analysis accuracy based on that information. For example, it takes into account past query history and the user's expertise. The query analysis unit also registers the user's expertise and past query history in a database and improves the analysis accuracy of the query content based on that information. For example, it prioritizes the analysis of queries from users with specialized knowledge. The query analysis unit also builds a system that improves the analysis accuracy based on the background information about the query content. For example, it adjusts the analysis results by taking into account past query history and the user's expertise. In this way, the analysis accuracy can be improved by taking background information into account.

[0053] The inquiry analysis unit can refer to external data to understand the context of the inquiry and add supplementary information to the analysis results. For example, to understand the context of the inquiry, it can automatically collect related industry news and technical literature and add it as supplementary information to the analysis results. For example, it can reflect the latest technological trends and market needs. The inquiry analysis unit also analyzes external data related to the inquiry and builds a system that understands the context of the inquiry based on that information. For example, it can refer to related technical literature and industry reports. The inquiry analysis unit also complements background information of the inquiry based on external data and saves it in the analysis results. For example, it can add technical details and market trends related to the inquiry. In this way, by referring to external data, it is possible to gain a deeper understanding of the context of the inquiry and add supplementary information.

[0054] The query analysis unit can add a multilingual analysis function so that it can handle queries in different languages. For example, a multilingual analysis function is added so that it can handle queries in different languages. For example, it can handle multiple languages ​​such as English, French, and Chinese. The query analysis unit also uses the multilingual analysis function to build a system that automatically translates query content in different languages ​​and reflects this in the analysis results. For example, it automatically translates and analyzes the query content. The query analysis unit also develops a system that analyzes query content in different languages ​​and provides analysis results in multiple languages ​​based on the results. For example, it analyzes query content in different languages ​​and provides the analysis results in multiple languages. This makes it possible to handle queries in different languages.

[0055] The inquiry analysis unit can convert the inquiry content into visual notes or mind maps to make it easier to understand visually. For example, it can convert the inquiry content into visual notes to visually display the main points of the inquiry. For example, it can show important points using diagrams or icons. The inquiry analysis unit can also convert the inquiry content into mind map format to visually organize related keywords and concepts. This allows the overall picture of the inquiry to be understood at a glance. The inquiry analysis unit can also develop tools that automatically generate visual notes or mind maps to enable users to easily display the inquiry content visually. For example, it can provide a function to visualize the inquiry content using drag and drop. This makes it easier to visually understand the inquiry content.

[0056] The information search unit can evaluate the reliability of search results and prioritize displaying highly reliable information. For example, to evaluate the reliability of search results, a reliability score is calculated based on the poster's expertise and past posting history. For example, information from posters with specialized knowledge is preferentially displayed. In addition, to evaluate the reliability of search results, the information search unit references external data (e.g., industry news and technical literature) and prioritizes displaying highly reliable information. For example, it references related technical literature and industry reports. In addition, to evaluate the reliability of search results, the information search unit understands the context of the posted content and builds a system that prioritizes displaying highly reliable information. For example, it adds technical details and market trends related to the posted content. This allows the quality of information to be improved by preferentially displaying highly reliable information.

[0057] The information retrieval unit can refer to external data to understand the context of the search results and add supplemental information to the search results. For example, to understand the context of the search results, it can automatically collect related industry news and technical literature and add it as supplemental information to the search results. For example, it can reflect the latest technological trends and market needs. The information retrieval unit can also analyze external data related to the search results and build a system that understands the context of the search results based on that information. For example, it can refer to related technical literature and industry reports. The information retrieval unit can also complement the background information of the search results based on external data and save it in the search results. For example, it can add technical details and market trends related to the search results. This allows the context of the search results to be understood more deeply by referring to external data and adding supplemental information.

[0058] The information search unit can also include information in audio or video format in the search targets and integrate multimodal information. For example, audio and video data can also be included in the search targets when searching, and search results can be evaluated based on visual and auditory information. For example, prototype videos and explanatory audio can be used to understand the details of the search results. The information search unit also uses voice recognition technology to extract search content from uploaded audio data and display it in the search results. Specifically, the audio data is converted into text and displayed as search results. The information search unit also uses video analysis technology to automatically extract the main points of the search content from uploaded video data and display them in the search results. In this way, visual and auditory information is integrated with text data and displayed in the search results. This makes it possible to integrate multimodal information by including information in audio and video format in the search targets.

[0059] The information search department can add a function to cross-reference search results to promote information sharing between different departments and project teams. For example, a cross-reference function is added to search results to promote information sharing between different departments and project teams. For example, related posts are linked together. The information search department can also build a system that cross-references information within search results and automatically displays related information to facilitate information sharing between departments. For example, it can display progress information for related projects. The information search department can also add a cross-reference function to search results and integrate related information to promote information sharing between different project teams. For example, it can share technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0060] The candidate identification unit can evaluate the reliability of candidates based on their expertise and past posting history, and preferentially display highly reliable candidates. For example, the candidate's expertise and past posting history can be registered in a database, and the reliability of the candidate can be evaluated based on that information. For example, information about candidates with specialized knowledge can be preferentially displayed. The candidate identification unit also builds a system to evaluate a candidate's feasibility and market demand based on the candidate's industry experience. For example, information about candidates with many years of industry experience can be displayed with a high rating. The candidate identification unit also collects background information such as the candidate's educational background and work history, and evaluates the candidate's reliability based on that information. For example, information about candidates with a high level of education or professional qualifications can be preferentially displayed. This allows the quality of information to be improved by preferentially displaying highly reliable candidates.

[0061] The candidate identification unit can refer to external data to understand the candidate's context and add supplemental information to the candidate information. For example, to understand the candidate's context, it automatically collects related industry news and technical literature and adds it to the candidate information as supplemental information. For example, it reflects the latest technological trends and market needs. The candidate identification unit also analyzes external data related to the candidate and builds a system that understands the candidate's context based on that information. For example, it refers to related technical literature and industry reports. The candidate identification unit also complements the candidate's background information based on external data and saves it in the candidate information. For example, it adds technical details and market trends related to the candidate. This makes it possible to understand the candidate's context more deeply and add supplemental information by referring to external data.

[0062] The candidate identification department can share candidate information between different departments and project teams and form cross-functional teams. For example, it builds a system for sharing candidate information between different departments and project teams and forming cross-functional teams. For example, it links related candidates. The candidate identification department also builds a system that cross-references candidate information and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The candidate identification department also cross-references candidate information and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This makes it possible to share candidate information between different departments and project teams and form cross-functional teams.

[0063] The candidate identification unit can convert candidate information into visual notes or mind maps to make it easier to understand visually. For example, it can convert candidate information into visual notes to visually display the key points of a candidate. For example, it can show important points using diagrams or icons. The candidate identification unit can also convert candidate information into mind map format to visually organize related keywords and concepts. This allows for an overall understanding of the candidate at a glance. The candidate identification unit can also develop tools to automatically generate visual notes and mind maps, allowing users to easily display candidate information visually. For example, it can provide a function to visualize candidate information using drag and drop. This makes it easier to understand candidate information visually.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The database creation department creates a database of information posted to an internal database or an open channel of a communication tool. For example, the database creation department collects information posted to an internal database or an open channel of a communication tool and stores it in a database. The database creation department also builds a database that includes information about the posted content and posters. For example, project progress reports, technical questions, and solutions are posted. Step 2: The inquiry analysis unit analyzes the content of the inquiry from the user. For example, if an inquiry is made such as "I would like to know your opinion on the introduction of a new project management tool," the generation AI will analyze this content and extract related keywords and topics. Step 3: The information search unit searches the database based on the inquiry analyzed by the inquiry analysis unit. For example, if a similar question has been posted in the past, the information search unit searches for the posting and answers. The information search unit also searches for information on employees who are knowledgeable about related topics. Step 4: The candidate identification unit identifies highly relevant employees from the information searched by the information search unit. For example, the candidate identification unit provides a list of relevant employees in the form of "The following employees have opinions about a new project management tool." The candidate identification unit also provides past postings, providing information that users can refer to.

[0066] (Example 2) The information provision system according to an embodiment of the present invention is a system that stores information posted to an internal database or an open channel of a communication tool in a database, and uses a generation AI to analyze the content of an inquiry, search for similar posts or related registered users in the database, and respond with highly relevant employees. This makes the information provision system more efficient for information sharing within the company and facilitates smooth communication between employees.

[0067] An information provision system according to an embodiment includes a database creation unit, an inquiry analysis unit, an information search unit, and a candidate identification unit. The database creation unit creates a database of information posted to an internal database or an open channel of a communication tool. For example, the database creation unit collects information posted to an internal database or an open channel of a communication tool and stores it in a database. The database creation unit also builds a database containing information about the posted content and the poster. For example, project progress reports, technical questions, and solutions are posted. The inquiry analysis unit analyzes the content of inquiries from users. For example, if an inquiry is made such as "I would like to know your opinion on the introduction of a new project management tool," the generation AI analyzes the content and extracts related keywords and topics. The information search unit searches the database based on the inquiry content analyzed by the inquiry analysis unit. For example, if a similar question has been posted in the past, the information search unit searches for the posted content and answers. The information search unit also searches for information on employees who are knowledgeable about related topics. The candidate identification unit identifies highly relevant employees from the information searched by the information search unit. For example, the candidate identification unit provides a list of relevant employees in the form of "The following employees have opinions about a new project management tool." The candidate identification unit also provides past postings to provide information that users can refer to. This allows the information provision system according to the embodiment to improve the efficiency of information sharing within the company and facilitate smooth communication between employees. For example, past success stories can be used as reference when launching a new project, and solutions to technical problems can be found quickly. Furthermore, by identifying relevant employees, appropriate advice and opinions can be obtained.

[0068] The database creation unit can perform an emotion analysis of the posted content and classify the information in the database based on the intensity and type of emotion. For example, the database creation unit performs an emotion analysis on the posted content and quantifies the intensity and type of emotion based on the emotion score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and posts with high specific emotion scores are preferentially stored in the database. The database creation unit also analyzes the poster's emotional state in real time and automatically filters and stores posts with strong positive emotions. Specifically, the database creation unit analyzes the facial expression and tone of voice at the time of posting and calculates the emotion score. The database creation unit also uses the emotion analysis to build a filtering system that eliminates posts with negative emotions. For example, by not storing posts with high scores for anger or sadness in the database, only positive posts are collected. This allows information to be classified based on the intensity and type of emotion, enabling more appropriate information to be provided.

[0069] The database creation unit can evaluate the reliability of the posted content based on the poster's expertise and past posting history, and prioritize highly reliable information for database creation. The database creation unit, for example, registers the poster's expertise and past posting history in a database, and evaluates the reliability of the posted content based on that information. For example, it prioritizes storing information about posters with specialized knowledge. The database creation unit also builds a system for evaluating the feasibility and market demand of posted content based on the poster's industry experience. For example, it highly evaluates and stores information about posters with many years of industry experience in the database. The database creation unit also collects background information about the poster, such as their educational background and work history, and evaluates the reliability of the posted content based on that information. For example, it prioritizes storing information about posters with high educational backgrounds and professional qualifications. This allows the quality of information to be improved by prioritizing highly reliable information for database creation.

[0070] The database creation unit can refer to external data and add supplemental information to the database to understand the context of the posted content. For example, the database creation unit automatically collects related industry news and technical literature to understand the context of the posted content and adds it to the database as supplemental information. For example, it reflects the latest technological trends and market needs. The database creation unit also analyzes external data related to the posted content and builds a system that understands the context of the posted content based on that information. For example, it refers to related technical literature and industry reports. The database creation unit also complements background information of the posted content based on external data and stores it in the database. For example, it adds technical details and market trends related to the posted content. In this way, by referring to external data, the context of the posted content can be more deeply understood and supplemental information can be added.

[0071] The database creation unit can also create a database of posts in audio or video format, integrating multimodal information. For example, the database creation unit allows audio or video data to be uploaded at the time of posting, and evaluates the content of the post based on visual and auditory information. For example, the database creation unit grasps the details of the post using a prototype video or explanatory audio. The database creation unit also uses voice recognition technology to extract the content of the post from the uploaded audio data and save it in the database. Specifically, the audio data is converted into text and saved as the content of the post. The database creation unit also uses video analysis technology to automatically extract the main points of the content of the post from the uploaded video data and save them in the database. In this way, visual and auditory information is integrated with text data and saved in the database. In this way, multimodal information can be integrated by creating a database of information in audio and video format.

[0072] The database creation department can add a function to cross-reference the database to promote information sharing between different departments and project teams. The database creation department, for example, adds a cross-reference function to the database to promote information sharing between different departments and project teams. For example, it links related posts. The database creation department also builds a system that cross-references information in the database and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The database creation department also adds a cross-reference function to the database and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0073] The database creation unit can use the emotion estimation function to analyze the poster's emotional state in real time and provide feedback to elicit positive emotions. The database creation unit is equipped with a function to analyze the poster's facial expressions and voice, for example, and estimate emotions in real time. For example, the database creation unit analyzes the poster's emotions using a camera or microphone, and makes positive suggestions if negative emotions are detected. The database creation unit also uses the emotion estimation function to provide an interface for eliciting positive emotions when the poster posts. For example, it presents encouraging messages and success stories. The database creation unit also provides feedback in real time based on the emotion estimation data when the poster posts, and offers advice to strengthen positive emotions. For example, it displays appropriate encouragement or praise based on the input content. This makes it possible to analyze the poster's emotional state in real time and provide feedback to elicit positive emotions.

[0074] The inquiry analysis unit can perform an emotion analysis of the inquiry content and adjust the analysis results based on the intensity and type of emotion. For example, the inquiry analysis unit performs an emotion analysis on the inquiry content and quantifies the intensity and type of emotion based on the emotion score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and inquiries with high specific emotion scores are prioritized for analysis. The inquiry analysis unit also analyzes the emotional state of the inquiry content in real time and automatically filters and analyzes inquiries with strong positive emotions. Specifically, the inquiry analysis unit analyzes facial expressions and tone of voice at the time of the inquiry and calculates an emotion score. The inquiry analysis unit also uses emotion analysis to build a filtering system that eliminates inquiries with negative emotions. For example, by not analyzing inquiries with high scores for anger or sadness, only positive inquiries are analyzed. This allows the analysis results to be adjusted based on the intensity and type of emotion, making it possible to provide more appropriate information.

[0075] The query analysis unit can improve the analysis accuracy based on background information of the query content. The query analysis unit, for example, collects background information of the query content and improves the analysis accuracy based on that information. For example, it takes into account past query history and the user's expertise. The query analysis unit also registers the user's expertise and past query history in a database and improves the analysis accuracy of the query content based on that information. For example, it prioritizes analysis of queries from users with specialized knowledge. The query analysis unit also builds a system that improves the analysis accuracy based on the background information of the query content. For example, it adjusts the analysis results by taking into account past query history and the user's expertise. In this way, the analysis accuracy can be improved by taking into account the background information.

[0076] The inquiry analysis unit can refer to external data to understand the context of the inquiry and add supplemental information to the analysis results. For example, the inquiry analysis unit automatically collects related industry news and technical literature to understand the context of the inquiry and adds it to the analysis results as supplemental information. For example, it reflects the latest technological trends and market needs. The inquiry analysis unit also analyzes external data related to the inquiry and builds a system that understands the context of the inquiry based on that information. For example, it refers to related technical literature and industry reports. The inquiry analysis unit also complements background information of the inquiry based on external data and saves it in the analysis results. For example, it adds technical details and market trends related to the inquiry. In this way, by referring to external data, the context of the inquiry can be understood more deeply and supplemental information can be added.

[0077] The query analysis unit can add a multilingual analysis function so that it can handle queries in different languages. The query analysis unit adds a multilingual analysis function so that it can handle queries in different languages, for example. For example, it supports multiple languages ​​such as English, French, and Chinese. The query analysis unit also uses the multilingual analysis function to build a system that automatically translates query content in different languages ​​and reflects this in the analysis results. For example, it automatically translates and analyzes query content. The query analysis unit also develops a system that analyzes query content in different languages ​​and provides analysis results in multiple languages ​​based on the results. For example, it analyzes query content in different languages ​​and provides the analysis results in multiple languages. This makes it possible to handle queries in different languages.

[0078] The inquiry analysis unit can convert the inquiry content into a visual note or mind map to make it easier to understand visually. For example, the inquiry analysis unit converts the inquiry content into a visual note to visually display the main points of the inquiry. For example, it shows important points with diagrams or icons. The inquiry analysis unit can also convert the inquiry content into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the inquiry to be understood at a glance. The inquiry analysis unit can also develop tools that automatically generate visual notes or mind maps to enable users to easily visually display the inquiry content. For example, it can provide a function to visualize the inquiry content with drag and drop. This makes it easier to visually understand the inquiry content.

[0079] The query analysis unit can use the emotion estimation function to analyze the user's emotional response to the query content in real time and provide feedback to elicit positive emotions. The query analysis unit, for example, collects the user's emotional response to the query content in real time and provides feedback to elicit positive emotions based on the data. For example, feedback with a high number of positive emotional responses is provided preferentially. The query analysis unit also uses the emotion estimation function to analyze the user's emotional score for the query content and provides feedback to elicit positive emotions. For example, feedback with a high emotional score is provided preferentially. The query analysis unit also builds a system for providing feedback to elicit positive emotions based on the user's emotional response data. For example, feedback with a high emotional score is provided preferentially. This makes it possible to analyze the user's emotional response in real time and provide feedback to elicit positive emotions.

[0080] The information search unit can perform sentiment analysis of the search results and filter them based on the intensity and type of emotion. For example, the information search unit performs sentiment analysis on the search results and quantifies the intensity and type of emotion based on the resulting sentiment score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and search results with high specific sentiment scores are preferentially displayed. The information search unit also analyzes the emotional state of the search results in real time and automatically filters and displays search results with strong positive sentiment. Specifically, the information search unit analyzes the text and metadata of the search results and calculates the sentiment score. The information search unit also uses sentiment analysis to build a filtering system that eliminates search results with negative sentiment. For example, by not displaying search results with high scores for anger or sadness, only positive search results are displayed. This allows for more appropriate information to be provided by filtering search results based on the intensity and type of emotion.

[0081] The information search unit can evaluate the reliability of search results and prioritize displaying highly reliable information. For example, to evaluate the reliability of search results, the information search unit calculates a reliability score based on the poster's expertise and past posting history. For example, it prioritizes displaying information from posters with specialized knowledge. In addition, to evaluate the reliability of search results, the information search unit references external data (e.g., industry news and technical literature) and prioritizes displaying highly reliable information. For example, it references related technical literature and industry reports. In addition, to evaluate the reliability of search results, the information search unit understands the context of the posted content and builds a system that prioritizes displaying highly reliable information. For example, it adds technical details and market trends related to the posted content. This allows the quality of information to be improved by preferentially displaying highly reliable information.

[0082] The information search unit can refer to external data to understand the context of the search results and add supplemental information to the search results. For example, the information search unit automatically collects related industry news and technical literature to understand the context of the search results and adds it as supplemental information to the search results. For example, it reflects the latest technological trends and market needs. The information search unit also analyzes external data related to the search results and builds a system that understands the context of the search results based on that information. For example, it refers to related technical literature and industry reports. The information search unit also complements background information of the search results based on external data and saves it in the search results. For example, it adds technical details and market trends related to the search results. In this way, by referring to external data, the context of the search results can be more deeply understood and supplemental information can be added.

[0083] The information search unit can also include information in audio or video format in its search targets and integrate multimodal information. For example, the information search unit also includes audio and video data in its search targets during a search and evaluates search results based on visual and auditory information. For example, it uses prototype videos or explanatory audio to understand the details of the search results. The information search unit also uses voice recognition technology to extract search content from uploaded audio data and display it in the search results. Specifically, it converts the audio data into text and displays it as a search result. The information search unit also uses video analysis technology to automatically extract the main points of the search content from uploaded video data and display them in the search results. In this way, visual and auditory information is integrated with text data and displayed in the search results. In this way, multimodal information can be integrated by including information in audio and video format in its search targets.

[0084] The information search unit can add a function to cross-reference search results to promote information sharing between different departments and project teams. The information search unit, for example, adds a cross-reference function to search results to promote information sharing between different departments and project teams. For example, related posts are linked together. The information search unit also builds a system that cross-references information within search results and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The information search unit also adds a cross-reference function to search results and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0085] The information search unit can use the emotion estimation function to analyze the user's emotional response to the search results in real time and provide feedback to elicit positive emotions. The information search unit, for example, collects the user's emotional responses to the search results in real time and provides feedback to elicit positive emotions based on the data. For example, feedback with a high number of positive emotional responses is provided preferentially. The information search unit also uses the emotion estimation function to analyze the user's emotional score for the search results and provides feedback to elicit positive emotions. For example, feedback with a high emotional score is provided preferentially. The information search unit also builds a system that provides feedback to elicit positive emotions based on the user's emotional response data. For example, feedback with a high emotional score is provided preferentially. This makes it possible to analyze the user's emotional response in real time and provide feedback to elicit positive emotions.

[0086] The candidate identification unit can perform an emotion analysis of candidates and filter candidates based on the intensity and type of emotion. For example, the candidate identification unit performs an emotion analysis on candidates and quantifies the intensity and type of emotion based on the emotion score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and candidates with high specific emotion scores are preferentially displayed. The candidate identification unit also analyzes the emotional state of candidates in real time and automatically filters and displays candidates with strong positive emotions. Specifically, it analyzes the candidate's facial expressions and tone of voice to calculate an emotion score. The candidate identification unit also uses the emotion analysis to build a filtering system that eliminates candidates with negative emotions. For example, by not displaying candidates with high scores for anger or sadness, only positive candidates are displayed. This makes it possible to identify more suitable candidates by filtering candidates based on the intensity and type of emotion.

[0087] The candidate identification unit can evaluate the reliability of candidates based on their expertise and past posting history, and preferentially display highly reliable candidates. The candidate identification unit, for example, registers the expertise and past posting history of candidates in a database, and evaluates the reliability of candidates based on that information. For example, it preferentially displays information about candidates with specialized knowledge. The candidate identification unit also builds a system that evaluates the feasibility and market demand of candidates based on their industry experience. For example, it displays information about candidates with many years of industry experience as highly rated. The candidate identification unit also collects background information such as the candidates' educational background and work history, and evaluates the reliability of candidates based on that information. For example, it preferentially displays information about candidates with high educational backgrounds and professional qualifications. This makes it possible to improve the quality of information by preferentially displaying highly reliable candidates.

[0088] The candidate identification unit can refer to external data to understand the candidate's context and add supplemental information to the candidate information. For example, the candidate identification unit automatically collects related industry news and technical literature to understand the candidate's context and adds it to the candidate information as supplemental information. For example, it reflects the latest technological trends and market needs. The candidate identification unit also analyzes external data related to the candidate and builds a system that understands the candidate's context based on that information. For example, it refers to related technical literature and industry reports. The candidate identification unit also complements the candidate's background information based on external data and saves it in the candidate information. For example, it adds technical details and market trends related to the candidate. In this way, by referring to external data, the candidate's context can be understood more deeply and supplemental information can be added.

[0089] The candidate identification department can share candidate information between different departments and project teams and form cross-functional teams. The candidate identification department, for example, builds a system for sharing candidate information between different departments and project teams and forming cross-functional teams. For example, it links related candidates. The candidate identification department also builds a system that cross-references candidate information and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The candidate identification department also cross-references candidate information and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This makes it possible to share candidate information between different departments and project teams and form cross-functional teams.

[0090] The candidate identification unit can convert candidate information into visual notes or mind maps to make it easier to understand visually. For example, the candidate identification unit converts candidate information into visual notes to visually display the key points of the candidate. For example, it shows important points using diagrams or icons. The candidate identification unit can also convert candidate information into a mind map format to visually organize related keywords and concepts. This allows the overall picture of the candidate to be understood at a glance. The candidate identification unit can also develop tools that automatically generate visual notes and mind maps to enable users to easily display candidate information visually. For example, it can provide a function to visualize candidate information using drag and drop. This makes it easier to understand candidate information visually.

[0091] The candidate identification unit can use the emotion estimation function to analyze the user's emotional reactions to the candidates in real time and provide feedback to elicit positive emotions. The candidate identification unit, for example, collects the user's emotional reactions to the candidates in real time and provides feedback to elicit positive emotions based on that data. For example, it prioritizes providing feedback with a high number of positive emotional reactions. The candidate identification unit also uses the emotion estimation function to analyze the user's emotion score for the candidates and provides feedback to elicit positive emotions. For example, it prioritizes providing feedback with a high emotion score. The candidate identification unit also builds a system that provides feedback to elicit positive emotions based on the user's emotional reaction data. For example, it prioritizes providing feedback with a high emotion score. This makes it possible to analyze the user's emotional reactions in real time and provide feedback to elicit positive emotions.

[0092] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0093] The information provision system can also analyze a user's behavioral history and provide the most appropriate information based on past behavioral patterns. For example, it can analyze what information a user has searched for in the past and what posts they responded to, and provide similar information preferentially. It can also provide information appropriate to specific time periods or situations based on a user's behavioral history. For example, if a project deadline is approaching, it can suggest past success stories or efficient work methods. It can also customize the information provision method that is optimal for each individual user based on the user's behavioral history. For example, it can provide information that makes extensive use of graphs and diagrams to users who prefer visual information, and provide detailed text to users who prefer text information. This makes it possible to provide more personalized information by utilizing a user's behavioral history.

[0094] The database creation unit can perform an emotion analysis of the posted content and classify the information in the database based on the intensity and type of emotion. For example, the database creation unit performs an emotion analysis on the posted content and quantifies the intensity and type of emotion based on the emotion score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and posts with high specific emotion scores are preferentially stored in the database. The database creation unit also analyzes the poster's emotional state in real time and automatically filters and stores posts with strong positive emotions. Specifically, it analyzes the facial expression and tone of voice at the time of posting and calculates the emotion score. The database creation unit also uses the emotion analysis to build a filtering system that eliminates posts with negative emotions. For example, by not storing posts with high scores for anger or sadness in the database, only positive posts are collected. This allows information to be classified based on the intensity and type of emotion, making it possible to provide more appropriate information.

[0095] The database creation unit can evaluate the reliability of the posted content based on the poster's expertise and past posting history, and prioritize highly reliable information for database creation. For example, the poster's expertise and past posting history are registered in a database, and the reliability of the posted content is evaluated based on that information. For example, information about posters with specialized knowledge is preferentially saved. The database creation unit also builds a system for evaluating the feasibility and market demand of posted content based on the poster's industry experience. For example, information about posters with many years of industry experience is highly rated and saved in the database. The database creation unit also collects background information such as the poster's educational background and work history, and evaluates the reliability of the posted content based on that information. For example, information about posters with high educational backgrounds and professional qualifications is preferentially saved. This allows the quality of information to be improved by prioritizing highly reliable information for database creation.

[0096] The database creation unit can refer to external data to understand the context of the posted content and add supplementary information to the database. For example, to understand the context of the posted content, it can automatically collect related industry news and technical literature and add it to the database as supplementary information. For example, it can reflect the latest technological trends and market needs. The database creation unit can also analyze external data related to the posted content and build a system that understands the context of the posted content based on that information. For example, it can refer to related technical literature and industry reports. The database creation unit can also complement background information of the posted content based on external data and store it in the database. For example, it can add technical details and market trends related to the posted content. This makes it possible to more deeply understand the context of the posted content and add supplementary information by referring to external data.

[0097] The database creation unit can also create a database of posts in audio or video format, integrating multimodal information. For example, it can allow users to upload audio or video data at the same time as posting, and evaluate the content of the post based on visual and auditory information. For example, it can grasp the details of the post using a prototype video or explanatory audio. The database creation unit also uses voice recognition technology to extract the content of the post from the uploaded audio data and store it in the database. Specifically, it converts the audio data into text and stores it as the content of the post. The database creation unit also uses video analysis technology to automatically extract the main points of the content of the post from the uploaded video data and store them in the database. In this way, visual and auditory information is integrated with the text data and stored in the database. In this way, multimodal information can be integrated by creating a database of information in audio and video format.

[0098] The database creation department can add a function to cross-reference the database to promote information sharing between different departments and project teams. For example, a cross-reference function can be added to the database to promote information sharing between different departments and project teams. For example, related posts can be linked together. The database creation department can also build a system that cross-references information in the database and automatically displays related information to facilitate information sharing between departments. For example, it can display progress information for related projects. The database creation department can also add a cross-reference function to the database to integrate related information to promote information sharing between different project teams. For example, it can share technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0099] The database creation unit can use the emotion estimation function to analyze the poster's emotional state in real time and provide feedback to elicit positive emotions. For example, it is equipped with a function to analyze the poster's facial expressions and voice and estimate emotions in real time. For example, it can analyze the poster's emotions using a camera or microphone and make positive suggestions if it detects negative emotions. The database creation unit also uses the emotion estimation function to provide an interface for eliciting positive emotions when the poster posts. For example, it can present encouraging messages and success stories. The database creation unit also provides feedback in real time based on the emotion estimation data when the poster posts, and offers advice to strengthen positive emotions. For example, it can display appropriate encouragement or praise based on the input content. This makes it possible to analyze the poster's emotional state in real time and provide feedback to elicit positive emotions.

[0100] The inquiry analysis unit can perform sentiment analysis of the inquiry content and adjust the analysis results based on the intensity and type of emotion. For example, it performs sentiment analysis on the inquiry content and quantifies the intensity and type of emotion based on the resulting sentiment score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and inquiries with high specific sentiment scores are prioritized for analysis. The inquiry analysis unit also analyzes the emotional state of the inquiry content in real time and automatically filters out inquiries with strong positive sentiments for analysis. Specifically, it analyzes facial expressions and voice tones at the time of the inquiry and calculates sentiment scores. The inquiry analysis unit also uses sentiment analysis to build a filtering system that eliminates inquiries with negative sentiments. For example, by not analyzing inquiries with high scores for anger or sadness, it analyzes only positive inquiries. This allows the analysis results to be adjusted based on the intensity and type of emotion, making it possible to provide more appropriate information.

[0101] The query analysis unit can improve the analysis accuracy based on background information about the query content. For example, it collects background information about the query content and improves the analysis accuracy based on that information. For example, it takes into account past query history and the user's expertise. The query analysis unit also registers the user's expertise and past query history in a database and improves the analysis accuracy of the query content based on that information. For example, it prioritizes the analysis of queries from users with specialized knowledge. The query analysis unit also builds a system that improves the analysis accuracy based on the background information about the query content. For example, it adjusts the analysis results by taking into account past query history and the user's expertise. In this way, the analysis accuracy can be improved by taking background information into account.

[0102] The inquiry analysis unit can refer to external data to understand the context of the inquiry and add supplementary information to the analysis results. For example, to understand the context of the inquiry, it can automatically collect related industry news and technical literature and add it as supplementary information to the analysis results. For example, it can reflect the latest technological trends and market needs. The inquiry analysis unit also analyzes external data related to the inquiry and builds a system that understands the context of the inquiry based on that information. For example, it can refer to related technical literature and industry reports. The inquiry analysis unit also complements background information of the inquiry based on external data and saves it in the analysis results. For example, it can add technical details and market trends related to the inquiry. In this way, by referring to external data, it is possible to gain a deeper understanding of the context of the inquiry and add supplementary information.

[0103] The query analysis unit can add a multilingual analysis function so that it can handle queries in different languages. For example, a multilingual analysis function is added so that it can handle queries in different languages. For example, it can handle multiple languages ​​such as English, French, and Chinese. The query analysis unit also uses the multilingual analysis function to build a system that automatically translates query content in different languages ​​and reflects this in the analysis results. For example, it automatically translates and analyzes the query content. The query analysis unit also develops a system that analyzes query content in different languages ​​and provides analysis results in multiple languages ​​based on the results. For example, it analyzes query content in different languages ​​and provides the analysis results in multiple languages. This makes it possible to handle queries in different languages.

[0104] The inquiry analysis unit can convert the inquiry content into visual notes or mind maps to make it easier to understand visually. For example, it can convert the inquiry content into visual notes to visually display the main points of the inquiry. For example, it can show important points using diagrams or icons. The inquiry analysis unit can also convert the inquiry content into mind map format to visually organize related keywords and concepts. This allows the overall picture of the inquiry to be understood at a glance. The inquiry analysis unit can also develop tools that automatically generate visual notes or mind maps to enable users to easily display the inquiry content visually. For example, it can provide a function to visualize the inquiry content using drag and drop. This makes it easier to visually understand the inquiry content.

[0105] The query analysis unit can use the emotion estimation function to analyze the user's emotional response to the query content in real time and provide feedback to elicit positive emotions. For example, the query analysis unit can collect the user's emotional response to the query content in real time and provide feedback to elicit positive emotions based on the data. For example, feedback with a high number of positive emotional responses can be provided preferentially. The query analysis unit can also use the emotion estimation function to analyze the user's emotional score for the query content and provide feedback to elicit positive emotions. For example, feedback with a high emotional score can be provided preferentially. The query analysis unit can also build a system that provides feedback to elicit positive emotions based on the user's emotional response data. For example, feedback with a high emotional score can be provided preferentially. This makes it possible to analyze the user's emotional response in real time and provide feedback to elicit positive emotions.

[0106] The information search unit can perform sentiment analysis of search results and filter them based on the intensity and type of emotion. For example, sentiment analysis is performed on search results and the intensity and type of emotion are quantified based on the resulting sentiment score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and search results with high specific sentiment scores are preferentially displayed. The information search unit also analyzes the emotional state of search results in real time and automatically filters and displays search results with strong positive sentiment. Specifically, it analyzes the text and metadata of search results and calculates the sentiment score. The information search unit also uses sentiment analysis to build a filtering system that eliminates search results with negative sentiment. For example, by not displaying search results with high scores for anger or sadness, only positive search results are displayed. This allows for more appropriate information to be provided by filtering search results based on the intensity and type of emotion.

[0107] The information search unit can evaluate the reliability of search results and prioritize displaying highly reliable information. For example, to evaluate the reliability of search results, a reliability score is calculated based on the poster's expertise and past posting history. For example, information from posters with specialized knowledge is preferentially displayed. In addition, to evaluate the reliability of search results, the information search unit references external data (e.g., industry news and technical literature) and prioritizes displaying highly reliable information. For example, it references related technical literature and industry reports. In addition, to evaluate the reliability of search results, the information search unit understands the context of the posted content and builds a system that prioritizes displaying highly reliable information. For example, it adds technical details and market trends related to the posted content. This allows the quality of information to be improved by preferentially displaying highly reliable information.

[0108] The information retrieval unit can refer to external data to understand the context of the search results and add supplemental information to the search results. For example, to understand the context of the search results, it can automatically collect related industry news and technical literature and add it as supplemental information to the search results. For example, it can reflect the latest technological trends and market needs. The information retrieval unit can also analyze external data related to the search results and build a system that understands the context of the search results based on that information. For example, it can refer to related technical literature and industry reports. The information retrieval unit can also complement the background information of the search results based on external data and save it in the search results. For example, it can add technical details and market trends related to the search results. This allows the context of the search results to be understood more deeply by referring to external data and adding supplemental information.

[0109] The information search unit can also include information in audio or video format in the search targets and integrate multimodal information. For example, audio and video data can also be included in the search targets when searching, and search results can be evaluated based on visual and auditory information. For example, prototype videos and explanatory audio can be used to understand the details of the search results. The information search unit also uses voice recognition technology to extract search content from uploaded audio data and display it in the search results. Specifically, the audio data is converted into text and displayed as search results. The information search unit also uses video analysis technology to automatically extract the main points of the search content from uploaded video data and display them in the search results. In this way, visual and auditory information is integrated with text data and displayed in the search results. This makes it possible to integrate multimodal information by including information in audio and video format in the search targets.

[0110] The information search department can add a function to cross-reference search results to promote information sharing between different departments and project teams. For example, a cross-reference function is added to search results to promote information sharing between different departments and project teams. For example, related posts are linked together. The information search department can also build a system that cross-references information within search results and automatically displays related information to facilitate information sharing between departments. For example, it can display progress information for related projects. The information search department can also add a cross-reference function to search results and integrate related information to promote information sharing between different project teams. For example, it can share technical solutions for different projects. This can promote information sharing between different departments and project teams.

[0111] The information search unit can use the emotion estimation function to analyze the user's emotional response to the search results in real time and provide feedback to elicit positive emotions. For example, the information search unit can collect the user's emotional response to the search results in real time and provide feedback to elicit positive emotions based on the data. For example, feedback with a high number of positive emotional responses can be provided preferentially. The information search unit can also use the emotion estimation function to analyze the user's emotional score for the search results and provide feedback to elicit positive emotions. For example, feedback with a high emotional score can be provided preferentially. The information search unit can also build a system that provides feedback to elicit positive emotions based on the user's emotional response data. For example, feedback with a high emotional score can be provided preferentially. This makes it possible to analyze the user's emotional response in real time and provide feedback to elicit positive emotions.

[0112] The candidate identification unit can perform an emotion analysis of candidates and filter candidates based on the intensity and type of emotion. For example, it performs an emotion analysis on candidates and quantifies the intensity and type of emotion based on the emotion score. For example, emotions such as joy, sadness, and surprise are expressed numerically, and candidates with high specific emotion scores are preferentially displayed. The candidate identification unit also analyzes the emotional state of candidates in real time and automatically filters and displays candidates with strong positive emotions. Specifically, it analyzes the candidate's facial expressions and tone of voice to calculate an emotion score. The candidate identification unit also uses the emotion analysis to build a filtering system that eliminates candidates with negative emotions. For example, by not displaying candidates with high scores for anger or sadness, only positive candidates are displayed. This makes it possible to identify more suitable candidates by filtering candidates based on the intensity and type of emotion.

[0113] The candidate identification unit can evaluate the reliability of candidates based on their expertise and past posting history, and preferentially display highly reliable candidates. For example, the candidate's expertise and past posting history can be registered in a database, and the reliability of the candidate can be evaluated based on that information. For example, information about candidates with specialized knowledge can be preferentially displayed. The candidate identification unit also builds a system to evaluate a candidate's feasibility and market demand based on the candidate's industry experience. For example, information about candidates with many years of industry experience can be displayed with a high rating. The candidate identification unit also collects background information such as the candidate's educational background and work history, and evaluates the candidate's reliability based on that information. For example, information about candidates with a high level of education or professional qualifications can be preferentially displayed. This allows the quality of information to be improved by preferentially displaying highly reliable candidates.

[0114] The candidate identification unit can refer to external data to understand the candidate's context and add supplemental information to the candidate information. For example, to understand the candidate's context, it automatically collects related industry news and technical literature and adds it to the candidate information as supplemental information. For example, it reflects the latest technological trends and market needs. The candidate identification unit also analyzes external data related to the candidate and builds a system that understands the candidate's context based on that information. For example, it refers to related technical literature and industry reports. The candidate identification unit also complements the candidate's background information based on external data and saves it in the candidate information. For example, it adds technical details and market trends related to the candidate. This makes it possible to understand the candidate's context more deeply and add supplemental information by referring to external data.

[0115] The candidate identification department can share candidate information between different departments and project teams and form cross-functional teams. For example, it builds a system for sharing candidate information between different departments and project teams and forming cross-functional teams. For example, it links related candidates. The candidate identification department also builds a system that cross-references candidate information and automatically displays related information to facilitate information sharing between departments. For example, it displays progress information on related projects. The candidate identification department also cross-references candidate information and integrates related information to promote information sharing between different project teams. For example, it shares technical solutions for different projects. This makes it possible to share candidate information between different departments and project teams and form cross-functional teams.

[0116] The candidate identification unit can convert candidate information into visual notes or mind maps to make it easier to understand visually. For example, it can convert candidate information into visual notes to visually display the key points of a candidate. For example, it can show important points using diagrams or icons. The candidate identification unit can also convert candidate information into mind map format to visually organize related keywords and concepts. This allows for an overall understanding of the candidate at a glance. The candidate identification unit can also develop tools to automatically generate visual notes and mind maps, allowing users to easily display candidate information visually. For example, it can provide a function to visualize candidate information using drag and drop. This makes it easier to understand candidate information visually.

[0117] The candidate identification unit can use the emotion estimation function to analyze the user's emotional response to the candidate in real time and provide feedback to elicit positive emotions. For example, the candidate identification unit can collect the user's emotional response to the candidate in real time and provide feedback to elicit positive emotions based on that data. For example, feedback with a high number of positive emotional responses can be provided preferentially. The candidate identification unit can also use the emotion estimation function to analyze the user's emotional score for the candidate and provide feedback to elicit positive emotions. For example, feedback with a high emotional score can be provided preferentially. The candidate identification unit can also build a system that provides feedback to elicit positive emotions based on the user's emotional response data. For example, feedback with a high emotional score can be provided preferentially. This makes it possible to analyze the user's emotional response in real time and provide feedback to elicit positive emotions.

[0118] The processing flow of the second embodiment will be briefly explained below.

[0119] Step 1: The database creation department creates a database of information posted to an internal database or an open channel of a communication tool. For example, the database creation department collects information posted to an internal database or an open channel of a communication tool and stores it in a database. The database creation department also builds a database that includes information about the posted content and posters. For example, project progress reports, technical questions, and solutions are posted. Step 2: The inquiry analysis unit analyzes the content of the inquiry from the user. For example, if an inquiry is made such as "I would like to know your opinion on the introduction of a new project management tool," the generation AI will analyze this content and extract related keywords and topics. Step 3: The information search unit searches the database based on the inquiry analyzed by the inquiry analysis unit. For example, if a similar question has been posted in the past, the information search unit searches for the posting and answers. The information search unit also searches for information on employees who are knowledgeable about related topics. Step 4: The candidate identification unit identifies highly relevant employees from the information searched by the information search unit. For example, the candidate identification unit provides a list of relevant employees in the form of "The following employees have opinions about a new project management tool." The candidate identification unit also provides past postings, providing information that users can refer to.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0124] 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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).

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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).

[0144] 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.

[0145] 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.

[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 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.

[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 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.

[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 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.

[0153] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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).

[0173] 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.

[0174] 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."

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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]

[0187] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a database creation department that creates a database of information posted to an internal database or an open channel of a communication tool; an inquiry analysis unit that analyzes the content of an inquiry from a user; an information search unit that searches a database based on the query content analyzed by the query analysis unit; a candidate specification unit that specifies highly relevant employees from the information searched by the information search unit; A system characterized by:

2. The database creation unit Conducting a sentiment analysis of the posts and categorizing the information in the database based on the intensity and type of sentiment 2. The system of claim 1.

3. The database creation unit Audio and video posts will also be included in the database, integrating multimodal information.

2. The system of claim 1.

4. The query analysis unit Conduct sentiment analysis of inquiries and adjust analysis results based on the intensity and type of sentiment 2. The system of claim 1.

5. The information search unit Performing sentiment analysis on search results and filtering said search results based on the intensity and type of sentiment 2. The system of claim 1.

6. The information search unit Analyzing the user's emotional response to search results in real time and providing feedback to elicit positive emotions 2. The system of claim 1.

7. The candidate identification unit Conducting sentiment analysis of candidates and filtering said candidates based on the intensity and type of sentiment 2. The system of claim 1.

8. The candidate identification unit Analyzing the user's emotional response to the candidate in real time and providing feedback to elicit positive emotions 2. The system of claim 1.

Images