System

Abstract

An object of a system according to an embodiment is to enable a disabled person to check a desired workplace environment in advance.SOLUTION: A system according to an embodiment includes a recommendation unit and a virtual tour generation unit. The recommendation unit recommends a candidate company to work based on the desired condition of the disabled person. A virtual tour generation part generates a virtual office tour video based on the office photograph or the design drawing of the company recommended by the recommendation 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] With conventional technology, there were limited ways for people with disabilities to check in advance what kind of work environment they wanted, making it difficult for them to find a suitable workplace.

[0005] The system according to the embodiment aims to enable people with disabilities to check their desired working environment in advance. [Means for solving the problem]

[0006] The system according to the embodiment includes a recommendation unit and a virtual tour generation unit. The recommendation unit recommends companies as potential work locations based on the desired conditions of the person with a disability. The virtual tour generation unit generates a virtual office tour video based on office photos or blueprints of the companies recommended by the recommendation unit. [Effects of the Invention]

[0007] The system according to the embodiment can enable a person with a disability to check in advance the workplace environment that he or she desires. [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 recommendation system according to an embodiment of the present invention is a system that recommends potential companies for employment based on the type of job or industry desired by a person with a disability, the location and environment of the office, working conditions, etc., and automatically generates a virtual office tour video using a generation AI. This makes it easier for people with disabilities to find their desired workplace and allows them to experience the office environment in advance through a virtual tour.

[0029] A recommendation system according to an embodiment includes a recommendation unit and a virtual tour generation unit. The recommendation unit recommends potential companies based on the desired conditions of a person with a disability. For example, the generation AI receives input information such as the person's desired job type or industry, office location, office environment, and working conditions, and recommends potential companies based on that information. For example, when a person with a disability inputs preferences such as "I want to work in the IT industry," "I prefer a barrier-free office," or "I prefer a company with a flexible working hours system," the generation AI lists companies that match those preferences. The virtual tour generation unit generates a virtual office tour video based on office photos and blueprints of the companies recommended by the recommendation unit. For example, the generation AI receives several office photos and blueprints as input and automatically generates a virtual office tour video based on them. For example, the generation AI receives input photos and blueprints of the office entrance, conference rooms, workspaces, break rooms, etc., and combines them to generate a realistic virtual tour video. This allows people with disabilities to experience the office environment in advance without visiting the site. Persons with disabilities: The specific definition and scope of persons with disabilities must be clearly defined. For example, physical disabilities, intellectual disabilities, mental disabilities, etc. Desired conditions: The specific content and criteria of desired conditions must be clearly defined. For example, work location, working hours, salary, etc. Company: The specific type and scope of the company must be clearly defined. For example, industry, size, location, etc. Office photos: The specific type and criteria of office photos must be clearly defined. For example, interior photos, exterior photos, and facility photos. Blueprints: The specific type and criteria of blueprints must be clearly defined. For example, floor plans, elevations, detailed drawings, etc. Virtual office tour video: The specific content and criteria of the virtual office tour video must be clearly defined. For example, video length, resolution, interactivity, etc. This makes it easier for people with disabilities to find their desired workplace and experience the office environment in advance through a virtual tour.

[0030] The recommendation unit can analyze a person with a disability's past work experience and skill set and, based on that, suggest the most suitable job type and industry. For example, the generation AI retrieves a person with a disability's past work experience and skill set from a database and, based on that, suggests the most suitable job type and industry. For example, if the person has past experience in the IT industry, it will prioritize IT-related jobs. The generation AI can also analyze a person with a disability's skill set and suggest the most suitable job type based on that. For example, if the person has programming skills, it can suggest an engineering job. The generation AI can also comprehensively analyze a person with a disability's work experience and skill set to suggest the most suitable industry. For example, if the person's past work experience and skill set are suitable for the manufacturing industry, it can suggest a manufacturing job. Work experience - The specific content and scope of the work experience must be clarified. For example, past job content, position, and length of employment. Skill set - The specific content and criteria of the skill set must be clarified. For example, technical skills, soft skills, qualifications, etc. Occupation - The specific type and scope of the occupation must be clarified. For example, engineer, designer, marketing, etc. Industry - The specific type and scope of industry must be clearly defined. For example, IT, manufacturing, services, etc. This will allow the company to suggest the most suitable job and industry based on the person's previous experience and skills.

[0031] The recommendation unit can recommend optimal office locations by taking into account the lifestyle and commute time of individuals with disabilities. For example, the generation AI retrieves the lifestyle and commute time of individuals with disabilities from a database and uses that information to propose optimal office locations. For example, it prioritizes recommending offices with short commute times. The generation AI also considers the lifestyle of individuals with disabilities and proposes optimal office locations based on that. For example, it can suggest offices that allow night shifts for individuals with nocturnal lifestyles. The generation AI also considers individuals with disabilities' commute times and proposes optimal office locations based on that. For example, it can suggest offices with good public transportation access. Lifestyle - The specific content and criteria of lifestyle must be clarified. For example, wake-up time, bedtime, meal timing, etc. Commuting time - The specific criteria and range of commuting time must be clarified. For example, commuting method, commuting distance, commuting time, etc. Office location - The specific type and range of office locations must be clarified. For example, urban, suburban, specific area, etc. This allows the system to propose optimal office locations by taking into account the lifestyle and commute time of individuals with disabilities.

[0032] The virtual tour generation unit can also reproduce the office's audio environment and lighting conditions, providing a more realistic virtual tour. For example, the generation AI analyzes the office's audio environment and incorporates it into the virtual tour video. For example, it reproduces office noise and conversation sounds. The generation AI can also analyze the office's lighting conditions and incorporate them into the virtual tour video. For example, it can reproduce illuminance and color temperature. The generation AI can also comprehensively reproduce the office's audio environment and lighting conditions to provide a more realistic virtual tour. For example, it can reproduce the acoustic characteristics and type of light source in the office. Audio environment - The specific content and criteria of the audio environment must be clarified. For example, background noise, noise level, and acoustic characteristics. Lighting conditions - The specific content and criteria of the lighting conditions must be clarified. For example, illuminance, color temperature, and type of light source. This allows the office's audio environment and lighting conditions to be reproduced, providing a more realistic virtual tour.

[0033] The virtual tour generation unit can add interactive elements to the virtual tour, allowing users to freely explore the office. For example, the generation AI adds interactive elements to the virtual tour video, allowing users to freely explore the office. For example, it provides a function that allows users to change the viewpoint by clicking and dragging. The generation AI also adds a navigation function to the virtual tour video, allowing users to freely move around the office. For example, clicking a specific location will take users to that location. The generation AI also adds interactive content to the virtual tour video, allowing users to check information about the office in detail. For example, clicking on a specific piece of equipment will display detailed information about that equipment. Interactive elements - The specific content and criteria for interactive elements must be clarified. For example, user operation, navigation function, interactive content, etc. This makes it possible to provide an interactive virtual tour that allows users to freely explore the office.

[0034] The virtual tour generation unit can incorporate interviews and daily life of the office employees into the virtual tour video. For example, the virtual tour generation unit uses a generation AI to incorporate interview videos of actual office employees into the virtual tour. For example, the AI ​​adds scenes in which employees talk about their work and the atmosphere in the workplace. The AI ​​also incorporates the daily life of office employees into the virtual tour video. For example, the AI ​​adds scenes of employees performing their work and scenes of break time. The AI ​​also comprehensively combines employee interviews and daily life to provide a more realistic work environment. For example, alternating between interview videos and daily life can convey the workplace atmosphere in more detail. Employees - The specific definition and scope of employees must be clearly defined. For example, full-time employees, contract employees, part-time employees, etc. Interviews - The specific content and format of the interview must be clearly defined. For example, the questions asked, the length of the interview, and the format of the interview. Daily Life - The specific content and criteria for daily life must be clearly defined. For example, work flow, how employees spend their breaks, internal events, etc. This allows you to experience a more realistic work environment by incorporating interviews with actual employees working in the office and their daily lives into the virtual tour video.

[0035] The virtual tour generation unit can also recreate the surrounding environment of the office, allowing users to experience a comprehensive work environment. For example, the generation AI analyzes the surrounding environment of the office and incorporates it into the virtual tour video. For example, it displays the locations of the nearest train station and bus stop. The generation AI also incorporates information about restaurants and commercial facilities around the office into the virtual tour video. For example, it can display the locations of nearby restaurants and cafes. The generation AI also comprehensively recreates the surrounding environment of the office to provide a comprehensive work environment. For example, it can combine and display information about transportation access and surrounding facilities. Surrounding environment - The specific details and criteria of the surrounding environment must be clarified. For example, transportation access, restaurants, commercial facilities, etc. Transportation access - The specific details and criteria of transportation access must be clarified. For example, the nearest train station, bus stop, parking lot, etc. Restaurants - The specific types and range of restaurants must be clarified. For example, restaurants, cafes, fast food restaurants, etc. This allows the surrounding environment of the office to be recreated, allowing users to experience a comprehensive work environment.

[0036] The recommendation unit can reflect the hobbies and interests of a person with a disability and suggest companies with a matching work environment and corporate culture. For example, the generation AI retrieves the hobbies and interests of a person with a disability from a database and, based on that, suggests companies with a matching work environment and corporate culture. For example, for a person with a disability who likes sports, the generation AI can recommend sports-related companies. The generation AI can also analyze the hobbies and interests of a person with a disability and suggest the optimal work environment based on that. For example, for a person with a disability who likes music, the generation AI can suggest music-related companies. The generation AI can also comprehensively analyze the hobbies and interests of a person with a disability and suggest the optimal corporate culture. For example, for a person with a disability who likes reading, the generation AI can suggest publishers and bookstores. Hobbies - The specific content and scope of the hobbies must be clarified. For example, sports, music, reading, etc. Interests - The specific content and scope of the interests must be clarified. For example, a specific field, activity, theme, etc. Workplace environment - The specific content and standards of the work environment must be clarified. For example, the office layout, facilities, atmosphere, etc. Corporate culture - The specific content and standards of the corporate culture must be clarified. For example, the company's values, code of conduct, communication style, etc. This allows us to suggest companies that reflect the hobbies and interests of people with disabilities and have a work environment and corporate culture that matches theirs.

[0037] The recommendation unit can recommend family-friendly companies by taking into account the family structure and living environment of the person with a disability. For example, the generation AI retrieves the family structure and living environment of the person with a disability from a database and, based on that, suggests family-friendly companies. For example, the recommendation unit recommends companies with comprehensive childcare support programs. The generation AI also considers the family structure of the person with a disability and suggests optimal companies based on that. For example, it can suggest companies with childcare leave programs for a person with a disability who has children. The generation AI also considers the living environment of the person with a disability and suggests optimal companies based on that. For example, it can suggest companies with care leave programs for a person with a disability who has family members who need care. Family structure - The specific content and scope of the family structure must be clarified. For example, the number of family members, ages, and relationships. Living environment - The specific content and criteria of the living environment must be clarified. For example, the location of the residence, surrounding facilities, and daily routine. Family-friendly - The specific criteria and content of family-friendly must be clarified. For example, childcare support, family allowances, and flextime programs. This allows us to propose family-friendly companies that take into consideration the family structure and living environment of people with disabilities.

[0038] The virtual tour generation unit can use generation AI to reproduce the audio environment and lighting conditions of the office, providing a more realistic virtual tour. For example, the generation AI analyzes the audio environment of the office and incorporates it into the virtual tour video. For example, it reproduces office noise and conversations. The generation AI can also analyze the lighting conditions of the office and incorporate them into the virtual tour video. For example, it can reproduce illuminance and color temperature. The generation AI can also comprehensively reproduce the audio environment and lighting conditions of the office to provide a more realistic virtual tour. For example, it can reproduce the acoustic characteristics and types of light sources in the office. The specific technology and method of generation AI must be clarified. For example, deep learning, generative models, AI algorithms, etc. This allows the audio environment and lighting conditions of the office to be reproduced, providing a more realistic virtual tour.

[0039] The virtual tour generation unit can add interactive elements to the virtual tour, allowing the user to freely explore the office. For example, the generation AI adds interactive elements to the virtual tour video, allowing the user to freely explore the office. For example, the generation AI provides a function that allows the user to change the viewpoint by clicking and dragging. The generation AI also adds a navigation function to the virtual tour video, allowing the user to freely move around the office. For example, clicking a specific location can take the user to that location. The generation AI also adds interactive content to the virtual tour video, allowing the user to check information about the office in detail. For example, clicking on a specific piece of equipment can display detailed information about that equipment. The specific content and criteria for interactive elements must be clarified. For example, user operation, navigation function, interactive content, etc. This allows the user to freely explore the office, providing an interactive virtual tour.

[0040] The virtual tour generation unit can incorporate interviews and daily life of the office employees into the virtual tour video. For example, the virtual tour generation unit uses a generation AI to incorporate interview videos of actual office employees into the virtual tour. For example, the AI ​​adds scenes in which employees talk about their work and the atmosphere in the workplace. The AI ​​also incorporates the daily life of office employees into the virtual tour video. For example, the AI ​​adds scenes of employees performing their work and scenes of break time. The AI ​​also comprehensively combines employee interviews and daily life to provide a more realistic work environment. For example, alternating between interview videos and daily life can convey the workplace atmosphere in more detail. Employees - The specific definition and scope of employees must be clearly defined. For example, full-time employees, contract employees, part-time employees, etc. Interviews - The specific content and format of the interview must be clearly defined. For example, the questions asked, the length of the interview, and the format of the interview. Daily Life - The specific content and criteria for daily life must be clearly defined. For example, work flow, how employees spend their breaks, internal events, etc. This allows you to experience a more realistic work environment by incorporating interviews with actual employees working in the office and their daily lives into the virtual tour video.

[0041] The virtual tour generation unit can also recreate the surrounding environment of the office, allowing users to experience a comprehensive work environment. For example, the generation AI analyzes the surrounding environment of the office and incorporates it into the virtual tour video. For example, it displays the locations of the nearest train station and bus stop. The generation AI also incorporates information about restaurants and commercial facilities around the office into the virtual tour video. For example, it can display the locations of nearby restaurants and cafes. The generation AI also comprehensively recreates the surrounding environment of the office to provide a comprehensive work environment. For example, it can combine and display information about transportation access and surrounding facilities. Surrounding environment - The specific details and criteria of the surrounding environment must be clarified. For example, transportation access, restaurants, commercial facilities, etc. Transportation access - The specific details and criteria of transportation access must be clarified. For example, the nearest train station, bus stop, parking lot, etc. Restaurants - The specific types and range of restaurants must be clarified. For example, restaurants, cafes, fast food restaurants, etc. This allows the surrounding environment of the office to be recreated, allowing users to experience a comprehensive work environment.

[0042] The recommendation unit can use the generation AI to consider the career path and growth goals of the person with a disability and propose the optimal match from a long-term perspective. For example, the generation AI retrieves the career path and growth goals of the person with a disability from a database and proposes the optimal match based on that. For example, the recommendation unit recommends companies where long-term career growth is expected. The generation AI also considers the career path of the person with a disability and proposes the optimal company based on that. For example, it can propose companies with clear promotion steps. The generation AI also considers the growth goals of the person with a disability and proposes the optimal company based on that. For example, it can propose companies where skill improvement is expected. Career path - The specific content and criteria of the career path must be clarified. For example, promotion steps, skill acquisition, career goals, etc. Growth goals - The specific content and criteria of the growth goals must be clarified. For example, short-term goals, long-term goals, skill improvement, etc. This makes it possible to consider the career path and growth goals of the person with a disability and propose the optimal match from a long-term perspective.

[0043] The recommendation unit can analyze the company's culture and values ​​and recommend the company that matches the personal values ​​of the person with a disability. For example, the recommendation unit uses a generation AI to retrieve a company's culture and values ​​from a database and, based on that, recommend companies that match the personal values ​​of the person with a disability. For example, the recommendation unit evaluates the company's mission and vision. The generation AI can also analyze a company's culture and values ​​and, based on that, recommend the most suitable company. For example, it can recommend companies that emphasize teamwork. The generation AI can also consider the personal values ​​of the person with a disability and, based on that, recommend the most suitable company. For example, it can recommend companies that emphasize social responsibility. Culture - The specific content and standards of culture must be clarified. For example, the company's values, code of conduct, communication style, etc. Values ​​- The specific content and standards of values ​​must be clarified. For example, attitude toward work, importance of teamwork, social responsibility, etc. Personal values ​​- The specific content and standards of personal values ​​must be clarified. For example, attitude toward work, importance of teamwork, social responsibility, etc. This allows the recommendation unit to analyze a company's culture and values ​​and recommend companies that match the personal values ​​of the person with a disability.

[0044] The recommendation unit can use the generation AI to recommend companies that offer optimal working conditions by taking into account the health condition and lifestyle of the person with a disability. For example, the generation AI retrieves the health condition and lifestyle of the person with a disability from a database and, based on that, recommends companies that offer optimal working conditions. For example, the recommendation unit can recommend companies that offer remote work or flextime. The generation AI can also consider the health condition of the person with a disability and recommend optimal companies based on that. For example, for a person with a chronic illness, it can recommend companies that offer comprehensive medical support. The generation AI can also consider the person's lifestyle and recommend optimal companies based on that. For example, for a person with a nocturnal lifestyle, it can suggest companies that offer night shifts. Health condition - The specific details and criteria of the health condition must be clarified. For example, chronic illness, physical strength, stress level, etc. Working conditions - The specific details and criteria of the working conditions must be clarified. For example, working hours, salary, benefits, etc. This allows the recommendation unit to recommend companies that offer optimal working conditions by taking into account the health condition and lifestyle of the person with a disability.

[0045] The recommendation unit can analyze the company's employee benefits and support system and recommend the company that is most beneficial to the person with a disability. For example, the generation AI retrieves the employee benefits and support systems offered by companies from a database and, based on that, recommends the company that is most beneficial to the person with a disability. For example, the recommendation unit recommends companies with comprehensive childcare support systems and nursing care leave systems. The generation AI can also analyze a company's employee benefits and recommend the most suitable company based on that. For example, it can recommend companies with comprehensive health insurance and pension systems. The generation AI can also analyze a company's support system and recommend the most suitable company based on that. For example, it can recommend companies with comprehensive mental health support and career counseling. Employee benefits - The specific content and standards of employee benefits must be clarified. For example, health insurance, pension system, vacation system, etc. Support system - The specific content and standards of the support system must be clarified. For example, mental health support, career counseling, disability support programs, etc. Benefits - The specific standards and content of beneficial companies must be clarified. For example, the comprehensiveness of employee benefits, the quality of the support system, and ease of working. This allows us to analyze companies' employee benefits and support systems and recommend companies that are most beneficial for people with disabilities.

[0046] The virtual tour generation unit uses the generation AI to develop an automatic update function for the virtual office tour video, so that the latest office environment can always be reflected. The virtual tour generation unit, for example, develops a system in which the generation AI automatically collects the latest office information and automatically updates the virtual office tour video. For example, new equipment and layout changes can be reflected in real time. The generation AI also analyzes the latest office information and updates the virtual office tour video based on that information. For example, the introduction of new equipment and layout changes can be reflected. The generation AI also comprehensively reflects the latest office information, always providing an up-to-date office environment. For example, the latest equipment and layout can be reflected in real time. Automatic update function: The specific content and criteria for the automatic update function must be clarified. For example, the update frequency, update method, and updated content. This allows the development of an automatic update function for the virtual office tour video, so that the latest office environment can always be reflected.

[0047] The virtual tour generation unit can propose ways to maximize the use of the company's existing digital assets and minimize the costs. For example, the virtual tour generation unit uses a generation AI to analyze the company's existing digital assets (e.g., photos and blueprints) and generate a virtual tour video based on them. For example, costs can be reduced by reusing existing photos and blueprints. The generation AI can also maximize the use of the company's digital assets and generate an optimal virtual tour video based on them. For example, it can combine existing photos and blueprints to generate a realistic virtual tour video. The generation AI can also propose ways to comprehensively utilize the company's digital assets and minimize costs. For example, it can propose a method that reuses existing digital assets to eliminate the need for new filming or design. Digital assets: The specific type and scope of digital assets must be clarified. For example, photos, blueprints, videos, etc. Costs: The specific content and criteria of costs must be clarified. For example, production costs, operation costs, maintenance costs, etc. This allows the unit to propose ways to maximize the use of the company's existing digital assets and minimize costs.

[0048] The virtual tour generation unit can use the generation AI to propose the best practices for cost reduction by referring to the success stories of other companies or industries. For example, the generation AI retrieves success stories of other companies or industries from a database and proposes best practices for cost reduction based on them. For example, it refers to methods for automatically generating and updating virtual tour videos. The generation AI can also analyze success stories of other companies or industries and propose optimal cost reduction measures based on them. For example, it can propose efficient methods and effective strategies. The generation AI can also comprehensively analyze success stories of other companies or industries and propose optimal best practices. For example, it can analyze factors for success and propose optimal cost reduction measures based on that. Success stories - The specific content and criteria of success stories must be clarified. For example, implementation cases of other companies, industry best practices, factors for success, etc. Best practices - The specific content and criteria of best practices must be clarified. For example, efficient methods, effective strategies, points for success, etc. This allows best practices for cost reduction to be proposed by referring to success stories of other companies or industries.

[0049] The virtual tour generation unit can reduce the infrastructure costs by utilizing the cloud service to generate the virtual tour video. For example, the virtual tour generation unit builds a system in which a generation AI utilizes cloud services to generate virtual tour videos. For example, the virtual tour generation unit generates videos on the cloud, reducing infrastructure costs. Furthermore, the generation AI utilizes cloud services and generates optimal virtual tour videos based on the cloud services. For example, server costs and maintenance costs can be reduced by generating videos on the cloud. Furthermore, the generation AI can propose methods to minimize infrastructure costs by comprehensively utilizing cloud services. For example, it can propose efficient ways to use cloud services. Cloud services - The specific content and types of cloud services must be clarified. For example, IaaS, PaaS, SaaS, etc. Infrastructure costs - The specific content and standards of infrastructure costs must be clarified. For example, server costs, network costs, maintenance costs, etc. This allows infrastructure costs to be reduced by utilizing cloud services to generate virtual tour videos.

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

[0051] The recommendation department can reflect the hobbies and interests of people with disabilities and suggest companies with a matching work environment and corporate culture. For example, for a person with a disability who likes sports, it can recommend sports-related companies. For a person with a disability who likes music, it can suggest music-related companies. Furthermore, for a person with a disability who likes reading, it can suggest publishers and bookstores. This makes it possible to suggest companies with a matching work environment and corporate culture that reflect the hobbies and interests of people with disabilities.

[0052] The recommendation department can recommend family-friendly companies, taking into consideration the family structure and living environment of people with disabilities. For example, it can recommend companies with comprehensive childcare support systems. For people with disabilities who have children, it can suggest companies that offer childcare leave systems. Furthermore, for people with disabilities who have family members who need care, it can suggest companies that offer nursing care leave systems. In this way, it can suggest family-friendly companies, taking into consideration the family structure and living environment of people with disabilities.

[0053] The virtual tour generator can also reproduce the audio environment and lighting conditions of an office, providing a more realistic virtual tour. For example, it can reproduce noise and conversations in the office. It can also reproduce illuminance and color temperature. It can also reproduce the acoustic characteristics and types of light sources in the office. This allows the audio environment and lighting conditions of the office to be reproduced, providing a more realistic virtual tour.

[0054] The virtual tour generation unit can incorporate interviews and daily scenes of office employees into the virtual tour video. For example, it can add scenes in which employees talk about their work and the atmosphere in the workplace. It can also add scenes of employees working and taking breaks. Furthermore, by alternating between the interview video and the daily scenes, it is possible to convey the atmosphere of the workplace in more detail. In this way, by incorporating interviews and daily scenes of actual office employees into the virtual tour video, it is possible to experience a more realistic work environment.

[0055] The virtual tour generation unit can also recreate the surrounding environment of the office, allowing users to experience a comprehensive work environment. For example, it can display the locations of the nearest train station and bus stop. It can also incorporate information about restaurants and commercial facilities around the office into the virtual tour video. It can also display information about transportation access and surrounding facilities. This allows users to recreate the surrounding environment of the office and experience a comprehensive work environment.

[0056] The recommendation department uses generative AI to consider the career paths and growth goals of people with disabilities and propose optimal matches from a long-term perspective. For example, it can recommend companies where long-term career growth is expected. It can also suggest companies with clear promotion steps. It can also suggest companies where skill improvement is expected. This makes it possible to consider the career paths and growth goals of people with disabilities and propose optimal matches from a long-term perspective.

[0057] The virtual tour generation unit uses generation AI to develop an automatic update function for the virtual office tour video, which allows it to always reflect the latest office environment. For example, it can reflect new equipment and layout changes in real time. It can also reflect the introduction of new equipment and layout changes. It can also reflect the latest equipment and layout in real time. This allows it to develop an automatic update function for the virtual office tour video, which allows it to always reflect the latest office environment.

[0058] The processing flow of the first embodiment will be briefly explained below.

[0059] Step 1: The recommendation department recommends potential companies for employment based on the desired conditions of the person with a disability. For example, the generation AI receives information such as the person with a disability's desired job type or industry, office location, office environment, and working conditions as input, and recommends potential companies for employment based on that information. For example, if a person with a disability inputs their preferences such as "I want to work in the IT industry," "I prefer a barrier-free office," or "I prefer a company with a flextime system," the generation AI will list companies that match those preferences. Step 2: The virtual tour generation unit generates a virtual office tour video based on the company office photos and blueprints recommended by the recommendation unit. For example, the generation AI receives several office photos and blueprints as input and automatically generates a virtual office tour video based on them. For example, when the generation AI inputs photos and blueprints of the office entrance, conference rooms, work spaces, break rooms, etc., it combines them to generate a realistic virtual tour video. This allows people with disabilities to experience the office environment in advance without having to visit the site.

[0060] (Example 2) The recommendation system according to an embodiment of the present invention is a system that recommends potential companies for employment based on the type of job or industry desired by a person with a disability, the location and environment of the office, working conditions, etc., and automatically generates a virtual office tour video using a generation AI. This makes it easier for people with disabilities to find their desired workplace and allows them to experience the office environment in advance through a virtual tour.

[0061] A recommendation system according to an embodiment includes a recommendation unit and a virtual tour generation unit. The recommendation unit recommends potential companies based on the desired conditions of a person with a disability. For example, the generation AI receives input information such as the person's desired job type or industry, office location, office environment, and working conditions, and recommends potential companies based on that information. For example, when a person with a disability inputs preferences such as "I want to work in the IT industry," "I prefer a barrier-free office," or "I prefer a company with a flexible working hours system," the generation AI lists companies that match those preferences. The virtual tour generation unit generates a virtual office tour video based on office photos and blueprints of the companies recommended by the recommendation unit. For example, the generation AI receives several office photos and blueprints as input and automatically generates a virtual office tour video based on them. For example, the generation AI receives input photos and blueprints of the office entrance, conference rooms, workspaces, break rooms, etc., and combines them to generate a realistic virtual tour video. This allows people with disabilities to experience the office environment in advance without visiting the site. Persons with disabilities: The specific definition and scope of persons with disabilities must be clearly defined. For example, physical disabilities, intellectual disabilities, mental disabilities, etc. Desired conditions: The specific content and criteria of desired conditions must be clearly defined. For example, work location, working hours, salary, etc. Company: The specific type and scope of the company must be clearly defined. For example, industry, size, location, etc. Office photos: The specific type and criteria of office photos must be clearly defined. For example, interior photos, exterior photos, and facility photos. Blueprints: The specific type and criteria of blueprints must be clearly defined. For example, floor plans, elevations, detailed drawings, etc. Virtual office tour video: The specific content and criteria of the virtual office tour video must be clearly defined. For example, video length, resolution, interactivity, etc. This makes it easier for people with disabilities to find their desired workplace and experience the office environment in advance through a virtual tour.

[0062] The recommendation unit can analyze a person with a disability's past work experience and skill set and, based on that, suggest the most suitable job type and industry. For example, the generation AI retrieves a person with a disability's past work experience and skill set from a database and, based on that, suggests the most suitable job type and industry. For example, if the person has past experience in the IT industry, it will prioritize IT-related jobs. The generation AI can also analyze a person with a disability's skill set and suggest the most suitable job type based on that. For example, if the person has programming skills, it can suggest an engineering job. The generation AI can also comprehensively analyze a person with a disability's work experience and skill set to suggest the most suitable industry. For example, if the person's past work experience and skill set are suitable for the manufacturing industry, it can suggest a manufacturing job. Work experience - The specific content and scope of the work experience must be clarified. For example, past job content, position, and length of employment. Skill set - The specific content and criteria of the skill set must be clarified. For example, technical skills, soft skills, qualifications, etc. Occupation - The specific type and scope of the occupation must be clarified. For example, engineer, designer, marketing, etc. Industry - The specific type and scope of industry must be clearly defined. For example, IT, manufacturing, services, etc. This will allow the company to suggest the most suitable job and industry based on the person's previous experience and skills.

[0063] The recommendation unit can recommend optimal office locations by taking into account the lifestyle and commute time of individuals with disabilities. For example, the generation AI retrieves the lifestyle and commute time of individuals with disabilities from a database and uses that information to propose optimal office locations. For example, it prioritizes recommending offices with short commute times. The generation AI also considers the lifestyle of individuals with disabilities and proposes optimal office locations based on that. For example, it can suggest offices that allow night shifts for individuals with nocturnal lifestyles. The generation AI also considers individuals with disabilities' commute times and proposes optimal office locations based on that. For example, it can suggest offices with good public transportation access. Lifestyle - The specific content and criteria of lifestyle must be clarified. For example, wake-up time, bedtime, meal timing, etc. Commuting time - The specific criteria and range of commuting time must be clarified. For example, commuting method, commuting distance, commuting time, etc. Office location - The specific type and range of office locations must be clarified. For example, urban, suburban, specific area, etc. This allows the system to propose optimal office locations by taking into account the lifestyle and commute time of individuals with disabilities.

[0064] The recommendation unit can use the emotion estimation function to analyze the emotions of people with disabilities regarding their desired job type or industry and suggest workplaces that elicit positive emotions. For example, the recommendation unit uses the emotion estimation function to analyze people with disabilities' emotions regarding their desired job type or industry in real time. For example, it can analyze facial expressions and voice during an interview to suggest jobs that are associated with strong positive emotions. The emotion estimation function also analyzes people with disabilities' emotions regarding their desired job type or industry and suggests workplaces that elicit positive emotions based on that analysis. For example, it can suggest workplaces that elicit positive emotions based on past work experience and skill sets. The emotion estimation function also comprehensively analyzes people with disabilities' emotions and suggests optimal workplaces. For example, it can suggest workplaces that elicit positive emotions based on emotion scores. Emotion estimation function - The specific technologies and methods for the emotion estimation function must be clarified. For example, facial expression recognition, voice analysis, text analysis, etc. Emotion - The specific types and criteria of emotions must be clarified. For example, joy, sadness, anger, etc. Positive emotions - The specific types and criteria of positive emotions must be clarified. For example, satisfaction, happiness, relief, etc. This makes it possible to suggest workplaces that elicit positive emotions by taking people with disabilities' emotions into consideration.

[0065] The virtual tour generation unit can also reproduce the office's audio environment and lighting conditions, providing a more realistic virtual tour. For example, the generation AI analyzes the office's audio environment and incorporates it into the virtual tour video. For example, it reproduces office noise and conversation sounds. The generation AI can also analyze the office's lighting conditions and incorporate them into the virtual tour video. For example, it can reproduce illuminance and color temperature. The generation AI can also comprehensively reproduce the office's audio environment and lighting conditions to provide a more realistic virtual tour. For example, it can reproduce the acoustic characteristics and type of light source in the office. Audio environment - The specific content and criteria of the audio environment must be clarified. For example, background noise, noise level, and acoustic characteristics. Lighting conditions - The specific content and criteria of the lighting conditions must be clarified. For example, illuminance, color temperature, and type of light source. This allows the office's audio environment and lighting conditions to be reproduced, providing a more realistic virtual tour.

[0066] The virtual tour generation unit can add interactive elements to the virtual tour, allowing users to freely explore the office. For example, the generation AI adds interactive elements to the virtual tour video, allowing users to freely explore the office. For example, it provides a function that allows users to change the viewpoint by clicking and dragging. The generation AI also adds a navigation function to the virtual tour video, allowing users to freely move around the office. For example, clicking a specific location will take users to that location. The generation AI also adds interactive content to the virtual tour video, allowing users to check information about the office in detail. For example, clicking on a specific piece of equipment will display detailed information about that equipment. Interactive elements - The specific content and criteria for interactive elements must be clarified. For example, user operation, navigation function, interactive content, etc. This makes it possible to provide an interactive virtual tour that allows users to freely explore the office.

[0067] The virtual tour generation unit can use the emotion estimation function to analyze the user's emotional reactions during the virtual tour and generate videos that elicit positive emotions. The virtual tour generation unit, for example, uses the emotion estimation function to analyze the user's emotional reactions during the virtual tour in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The emotion estimation function also analyzes the user's emotional reactions and generates videos that elicit positive emotions based on the analysis. For example, it can highlight scenes with high emotion scores. The emotion estimation function also comprehensively analyzes the user's emotional reactions and generates optimal videos. For example, it can generate videos that elicit positive emotions based on the emotion score. Emotional reactions - The specific types and criteria of emotional reactions need to be clarified. For example, changes in facial expressions, tone of voice, changes in behavior, etc. This makes it possible to analyze the user's emotional reactions and generate videos that elicit positive emotions.

[0068] The virtual tour generation unit can incorporate interviews and daily life of the office employees into the virtual tour video. For example, the virtual tour generation unit uses a generation AI to incorporate interview videos of actual office employees into the virtual tour. For example, the AI ​​adds scenes in which employees talk about their work and the atmosphere in the workplace. The AI ​​also incorporates the daily life of office employees into the virtual tour video. For example, the AI ​​adds scenes of employees performing their work and scenes of break time. The AI ​​also comprehensively combines employee interviews and daily life to provide a more realistic work environment. For example, alternating between interview videos and daily life can convey the workplace atmosphere in more detail. Employees - The specific definition and scope of employees must be clearly defined. For example, full-time employees, contract employees, part-time employees, etc. Interviews - The specific content and format of the interview must be clearly defined. For example, the questions asked, the length of the interview, and the format of the interview. Daily Life - The specific content and criteria for daily life must be clearly defined. For example, work flow, how employees spend their breaks, internal events, etc. This allows you to experience a more realistic work environment by incorporating interviews with actual employees working in the office and their daily lives into the virtual tour video.

[0069] The virtual tour generation unit can also recreate the surrounding environment of the office, allowing users to experience a comprehensive work environment. For example, the generation AI analyzes the surrounding environment of the office and incorporates it into the virtual tour video. For example, it displays the locations of the nearest train station and bus stop. The generation AI also incorporates information about restaurants and commercial facilities around the office into the virtual tour video. For example, it can display the locations of nearby restaurants and cafes. The generation AI also comprehensively recreates the surrounding environment of the office to provide a comprehensive work environment. For example, it can combine and display information about transportation access and surrounding facilities. Surrounding environment - The specific details and criteria of the surrounding environment must be clarified. For example, transportation access, restaurants, commercial facilities, etc. Transportation access - The specific details and criteria of transportation access must be clarified. For example, the nearest train station, bus stop, parking lot, etc. Restaurants - The specific types and range of restaurants must be clarified. For example, restaurants, cafes, fast food restaurants, etc. This allows the surrounding environment of the office to be recreated, allowing users to experience a comprehensive work environment.

[0070] The virtual tour generation unit can use the emotion estimation function to monitor the user's emotional reactions during the virtual tour in real time and continuously improve the optimal tour content. The virtual tour generation unit, for example, uses the emotion estimation function to develop a system that monitors the user's emotional reactions during the virtual tour in real time. For example, the emotion estimation function analyzes the user's facial expressions and voice and calculates an emotion score. The emotion estimation function also monitors the user's emotional reactions in real time and continuously improves the optimal tour content based on the monitoring results. For example, scenes with low emotion scores can be improved. The emotion estimation function also comprehensively analyzes the user's emotional reactions to provide optimal tour content. For example, scenes that are most interesting to the user can be highlighted based on the emotion score. Emotional reactions - The specific types and criteria of emotional reactions need to be clarified. For example, changes in facial expressions, tone of voice, changes in behavior, etc. This allows the user's emotional reactions to be monitored in real time and the optimal tour content to be continuously improved.

[0071] The recommendation unit can reflect the hobbies and interests of a person with a disability and suggest companies with a matching work environment and corporate culture. For example, the generation AI retrieves the hobbies and interests of a person with a disability from a database and, based on that, suggests companies with a matching work environment and corporate culture. For example, for a person with a disability who likes sports, the generation AI can recommend sports-related companies. The generation AI can also analyze the hobbies and interests of a person with a disability and suggest the optimal work environment based on that. For example, for a person with a disability who likes music, the generation AI can suggest music-related companies. The generation AI can also comprehensively analyze the hobbies and interests of a person with a disability and suggest the optimal corporate culture. For example, for a person with a disability who likes reading, the generation AI can suggest publishers and bookstores. Hobbies - The specific content and scope of the hobbies must be clarified. For example, sports, music, reading, etc. Interests - The specific content and scope of the interests must be clarified. For example, a specific field, activity, theme, etc. Workplace environment - The specific content and standards of the work environment must be clarified. For example, the office layout, facilities, atmosphere, etc. Corporate culture - The specific content and standards of the corporate culture must be clarified. For example, the company's values, code of conduct, communication style, etc. This allows us to suggest companies that reflect the hobbies and interests of people with disabilities and have a work environment and corporate culture that matches theirs.

[0072] The recommendation unit can recommend family-friendly companies by taking into account the family structure and living environment of the person with a disability. For example, the generation AI retrieves the family structure and living environment of the person with a disability from a database and, based on that, suggests family-friendly companies. For example, the recommendation unit recommends companies with comprehensive childcare support programs. The generation AI also considers the family structure of the person with a disability and suggests optimal companies based on that. For example, it can suggest companies with childcare leave programs for a person with a disability who has children. The generation AI also considers the living environment of the person with a disability and suggests optimal companies based on that. For example, it can suggest companies with care leave programs for a person with a disability who has family members who need care. Family structure - The specific content and scope of the family structure must be clarified. For example, the number of family members, ages, and relationships. Living environment - The specific content and criteria of the living environment must be clarified. For example, the location of the residence, surrounding facilities, and daily routine. Family-friendly - The specific criteria and content of family-friendly must be clarified. For example, childcare support, family allowances, and flextime programs. This allows us to propose family-friendly companies that take into consideration the family structure and living environment of people with disabilities.

[0073] The recommendation unit uses the emotion estimation function to monitor the emotional reactions of people with disabilities to recommended companies in real time and continuously recommend the most suitable companies. The recommendation unit, for example, uses the emotion estimation function to develop a system that monitors the emotional reactions of people with disabilities to recommended companies in real time. For example, it analyzes facial expressions and voice during interviews and calculates an emotion score. The emotion estimation function also monitors the emotional reactions of people with disabilities in real time and continuously recommends the most suitable companies based on that. For example, it can prioritize the recommendation of companies with high emotion scores. The emotion estimation function also comprehensively analyzes the emotional reactions of people with disabilities and recommends the most suitable companies. For example, it can recommend companies that people with disabilities feel the most positive about based on the emotion score. Emotional reactions - The specific types and criteria of emotional reactions need to be clarified. For example, changes in facial expressions, tone of voice, changes in behavior, etc. This allows the emotional reactions of people with disabilities to be monitored in real time and the most suitable companies to be continuously recommended.

[0074] The virtual tour generation unit can use generation AI to reproduce the audio environment and lighting conditions of the office, providing a more realistic virtual tour. For example, the generation AI analyzes the audio environment of the office and incorporates it into the virtual tour video. For example, it reproduces office noise and conversations. The generation AI can also analyze the lighting conditions of the office and incorporate them into the virtual tour video. For example, it can reproduce illuminance and color temperature. The generation AI can also comprehensively reproduce the audio environment and lighting conditions of the office to provide a more realistic virtual tour. For example, it can reproduce the acoustic characteristics and types of light sources in the office. The specific technology and method of generation AI must be clarified. For example, deep learning, generative models, AI algorithms, etc. This allows the audio environment and lighting conditions of the office to be reproduced, providing a more realistic virtual tour.

[0075] The virtual tour generation unit can add interactive elements to the virtual tour, allowing the user to freely explore the office. For example, the generation AI adds interactive elements to the virtual tour video, allowing the user to freely explore the office. For example, the generation AI provides a function that allows the user to change the viewpoint by clicking and dragging. The generation AI also adds a navigation function to the virtual tour video, allowing the user to freely move around the office. For example, clicking a specific location can take the user to that location. The generation AI also adds interactive content to the virtual tour video, allowing the user to check information about the office in detail. For example, clicking on a specific piece of equipment can display detailed information about that equipment. The specific content and criteria for interactive elements must be clarified. For example, user operation, navigation function, interactive content, etc. This allows the user to freely explore the office, providing an interactive virtual tour.

[0076] The virtual tour generation unit can use an emotion estimation function to analyze the user's emotional response during the virtual tour and generate a video that elicits positive emotions. The virtual tour generation unit, for example, uses the emotion estimation function to analyze the user's emotional response during the virtual tour in real time. For example, the virtual tour generation unit analyzes the user's facial expressions and voice and calculates an emotion score. The emotion estimation function also analyzes the user's emotional response and generates a video that elicits positive emotions based on the analysis. For example, scenes with a high emotion score can be emphasized. The emotion estimation function also comprehensively analyzes the user's emotional response and generates optimal videos. For example, a video that elicits positive emotions can be generated based on the emotion score. Emotional response - The specific type and criteria of the emotional response must be clarified. For example, changes in facial expressions, tone of voice, changes in behavior, etc. This allows the user's emotional response to be analyzed and a video that elicits positive emotions to be generated.

[0077] The virtual tour generation unit can incorporate interviews and daily life of the office employees into the virtual tour video. For example, the virtual tour generation unit uses a generation AI to incorporate interview videos of actual office employees into the virtual tour. For example, the AI ​​adds scenes in which employees talk about their work and the atmosphere in the workplace. The AI ​​also incorporates the daily life of office employees into the virtual tour video. For example, the AI ​​adds scenes of employees performing their work and scenes of break time. The AI ​​also comprehensively combines employee interviews and daily life to provide a more realistic work environment. For example, alternating between interview videos and daily life can convey the workplace atmosphere in more detail. Employees - The specific definition and scope of employees must be clearly defined. For example, full-time employees, contract employees, part-time employees, etc. Interviews - The specific content and format of the interview must be clearly defined. For example, the questions asked, the length of the interview, and the format of the interview. Daily Life - The specific content and criteria for daily life must be clearly defined. For example, work flow, how employees spend their breaks, internal events, etc. This allows you to experience a more realistic work environment by incorporating interviews with actual employees working in the office and their daily lives into the virtual tour video.

[0078] The virtual tour generation unit can also recreate the surrounding environment of the office, allowing users to experience a comprehensive work environment. For example, the generation AI analyzes the surrounding environment of the office and incorporates it into the virtual tour video. For example, it displays the locations of the nearest train station and bus stop. The generation AI also incorporates information about restaurants and commercial facilities around the office into the virtual tour video. For example, it can display the locations of nearby restaurants and cafes. The generation AI also comprehensively recreates the surrounding environment of the office to provide a comprehensive work environment. For example, it can combine and display information about transportation access and surrounding facilities. Surrounding environment - The specific details and criteria of the surrounding environment must be clarified. For example, transportation access, restaurants, commercial facilities, etc. Transportation access - The specific details and criteria of transportation access must be clarified. For example, the nearest train station, bus stop, parking lot, etc. Restaurants - The specific types and range of restaurants must be clarified. For example, restaurants, cafes, fast food restaurants, etc. This allows the surrounding environment of the office to be recreated, allowing users to experience a comprehensive work environment.

[0079] The virtual tour generation unit can use an emotion estimation function to monitor the user's emotional reactions during the virtual tour in real time and continuously improve the optimal tour content. The virtual tour generation unit, for example, uses the emotion estimation function to develop a system that monitors the user's emotional reactions during the virtual tour in real time. For example, the emotion estimation function analyzes the user's facial expressions and voice and calculates an emotion score. The emotion estimation function also monitors the user's emotional reactions in real time and continuously improves the optimal tour content based on the monitoring results. For example, scenes with low emotion scores can be improved. The emotion estimation function also comprehensively analyzes the user's emotional reactions to provide optimal tour content. For example, scenes that interest the user most can be highlighted based on the emotion score. Emotional reactions - The specific types and criteria of emotional reactions need to be clarified. For example, changes in facial expressions, tone of voice, changes in behavior, etc. This allows the user's emotional reactions to be monitored in real time and the optimal tour content to be continuously improved.

[0080] The recommendation unit can use the generation AI to consider the career path and growth goals of the person with a disability and propose the optimal match from a long-term perspective. For example, the generation AI retrieves the career path and growth goals of the person with a disability from a database and proposes the optimal match based on that. For example, the recommendation unit recommends companies where long-term career growth is expected. The generation AI also considers the career path of the person with a disability and proposes the optimal company based on that. For example, it can propose companies with clear promotion steps. The generation AI also considers the growth goals of the person with a disability and proposes the optimal company based on that. For example, it can propose companies where skill improvement is expected. Career path - The specific content and criteria of the career path must be clarified. For example, promotion steps, skill acquisition, career goals, etc. Growth goals - The specific content and criteria of the growth goals must be clarified. For example, short-term goals, long-term goals, skill improvement, etc. This makes it possible to consider the career path and growth goals of the person with a disability and propose the optimal match from a long-term perspective.

[0081] The recommendation unit can analyze the company's culture and values ​​and recommend the company that matches the personal values ​​of the person with a disability. For example, the recommendation unit uses a generation AI to retrieve a company's culture and values ​​from a database and, based on that, recommend companies that match the personal values ​​of the person with a disability. For example, the recommendation unit evaluates the company's mission and vision. The generation AI can also analyze a company's culture and values ​​and, based on that, recommend the most suitable company. For example, it can recommend companies that emphasize teamwork. The generation AI can also consider the personal values ​​of the person with a disability and, based on that, recommend the most suitable company. For example, it can recommend companies that emphasize social responsibility. Culture - The specific content and standards of culture must be clarified. For example, the company's values, code of conduct, communication style, etc. Values ​​- The specific content and standards of values ​​must be clarified. For example, attitude toward work, importance of teamwork, social responsibility, etc. Personal values ​​- The specific content and standards of personal values ​​must be clarified. For example, attitude toward work, importance of teamwork, social responsibility, etc. This allows the recommendation unit to analyze a company's culture and values ​​and recommend companies that match the personal values ​​of the person with a disability.

[0082] The recommendation unit can use an emotion estimation function to analyze the emotion felt by the person with a disability regarding the matching with the company and propose the matching that elicits positive emotions. The recommendation unit, for example, uses the emotion estimation function to analyze the emotion felt by the person with a disability regarding the matching with the company in real time. For example, the emotion estimation function analyzes facial expressions and voice during the interview and calculates an emotion score. The emotion estimation function also analyzes the emotion felt by the person with a disability and proposes a matching that elicits positive emotions based on the analysis. For example, it can preferentially propose companies with high emotion scores. The emotion estimation function also comprehensively analyzes the emotion felt by the person with a disability and proposes an optimal matching. For example, it can propose companies that elicit the most positive emotions from the person with a disability based on the emotion score. Emotion - The specific type and criteria of emotion need to be clarified. For example, joy, sadness, anger, etc. This makes it possible to analyze the emotion felt by the person with a disability regarding the matching with the company and propose a matching that elicits positive emotions.

[0083] The recommendation unit can use the generation AI to recommend companies that offer optimal working conditions by taking into account the health condition and lifestyle of the person with a disability. For example, the generation AI retrieves the health condition and lifestyle of the person with a disability from a database and, based on that, recommends companies that offer optimal working conditions. For example, the recommendation unit can recommend companies that offer remote work or flextime. The generation AI can also consider the health condition of the person with a disability and recommend optimal companies based on that. For example, for a person with a chronic illness, it can recommend companies that offer comprehensive medical support. The generation AI can also consider the person's lifestyle and recommend optimal companies based on that. For example, for a person with a nocturnal lifestyle, it can suggest companies that offer night shifts. Health condition - The specific details and criteria of the health condition must be clarified. For example, chronic illness, physical strength, stress level, etc. Working conditions - The specific details and criteria of the working conditions must be clarified. For example, working hours, salary, benefits, etc. This allows the recommendation unit to recommend companies that offer optimal working conditions by taking into account the health condition and lifestyle of the person with a disability.

[0084] The recommendation unit can analyze the company's employee benefits and support system and recommend the company that is most beneficial to the person with a disability. For example, the generation AI retrieves the employee benefits and support systems offered by companies from a database and, based on that, recommends the company that is most beneficial to the person with a disability. For example, the recommendation unit recommends companies with comprehensive childcare support systems and nursing care leave systems. The generation AI can also analyze a company's employee benefits and recommend the most suitable company based on that. For example, it can recommend companies with comprehensive health insurance and pension systems. The generation AI can also analyze a company's support system and recommend the most suitable company based on that. For example, it can recommend companies with comprehensive mental health support and career counseling. Employee benefits - The specific content and standards of employee benefits must be clarified. For example, health insurance, pension system, vacation system, etc. Support system - The specific content and standards of the support system must be clarified. For example, mental health support, career counseling, disability support programs, etc. Benefits - The specific standards and content of beneficial companies must be clarified. For example, the comprehensiveness of employee benefits, the quality of the support system, and ease of working. This allows us to analyze companies' employee benefits and support systems and recommend companies that are most beneficial for people with disabilities.

[0085] The recommendation unit can use the emotion estimation function to monitor the emotional reactions of the person with a disability to the matching with the company in real time and continuously suggest the optimal match. The recommendation unit, for example, uses the emotion estimation function to develop a system that monitors the emotional reactions of the person with a disability to the matching with the company in real time. For example, the emotion estimation function analyzes facial expressions and voice during the interview and calculates an emotion score. The emotion estimation function also monitors the emotional reactions of the person with a disability in real time and continuously suggests optimal matches based on the emotional reactions. For example, it can preferentially suggest companies with high emotion scores. The emotion estimation function also comprehensively analyzes the emotional reactions of the person with a disability and suggests optimal matches. For example, it can suggest companies for which the person with a disability has the most positive emotions based on the emotion score. Emotional reactions - The specific types and criteria of emotional reactions need to be clarified. For example, changes in facial expressions, tone of voice, changes in behavior, etc. This allows the emotional reactions of the person with a disability to be monitored in real time and the optimal matches to be continuously suggested.

[0086] The virtual tour generation unit uses the generation AI to develop an automatic update function for the virtual office tour video, so that the latest office environment can always be reflected. The virtual tour generation unit, for example, develops a system in which the generation AI automatically collects the latest office information and automatically updates the virtual office tour video. For example, new equipment and layout changes can be reflected in real time. The generation AI also analyzes the latest office information and updates the virtual office tour video based on that information. For example, the introduction of new equipment and layout changes can be reflected. The generation AI also comprehensively reflects the latest office information, always providing an up-to-date office environment. For example, the latest equipment and layout can be reflected in real time. Automatic update function: The specific content and criteria for the automatic update function must be clarified. For example, the update frequency, update method, and updated content. This allows the development of an automatic update function for the virtual office tour video, so that the latest office environment can always be reflected.

[0087] The virtual tour generation unit can propose ways to maximize the use of the company's existing digital assets and minimize the costs. For example, the virtual tour generation unit uses a generation AI to analyze the company's existing digital assets (e.g., photos and blueprints) and generate a virtual tour video based on them. For example, costs can be reduced by reusing existing photos and blueprints. The generation AI can also maximize the use of the company's digital assets and generate an optimal virtual tour video based on them. For example, it can combine existing photos and blueprints to generate a realistic virtual tour video. The generation AI can also propose ways to comprehensively utilize the company's digital assets and minimize costs. For example, it can propose a method that reuses existing digital assets to eliminate the need for new filming or design. Digital assets: The specific type and scope of digital assets must be clarified. For example, photos, blueprints, videos, etc. Costs: The specific content and criteria of costs must be clarified. For example, production costs, operation costs, maintenance costs, etc. This allows the unit to propose ways to maximize the use of the company's existing digital assets and minimize costs.

[0088] The virtual tour generation unit can use an emotion estimation function to analyze the effect of the virtual tour video and generate the video with the highest cost performance. The virtual tour generation unit, for example, uses the emotion estimation function to analyze the effect of the virtual tour video in real time. For example, the emotion estimation function analyzes the user's facial expressions and voice to calculate an emotion score. The emotion estimation function also analyzes the effect of the virtual tour video and generates the most cost-effective video based on the analysis. For example, an effective video can be generated by emphasizing scenes with high emotion scores. The emotion estimation function also comprehensively analyzes the effect of the virtual tour video and generates an optimal video. For example, an effective video can be generated by emphasizing scenes that are most interesting to the user based on the emotion score. Effectiveness - The specific content and criteria of the effect must be clarified. For example, user satisfaction, frequency of use, feedback, etc. Cost performance - The specific content and criteria of cost performance must be clarified. For example, cost-effectiveness, return on investment, efficiency, etc. This allows the effect of the virtual tour video to be analyzed and the most cost-effective video to be generated.

[0089] The virtual tour generation unit can use the generation AI to propose the best practices for cost reduction by referring to the success stories of other companies or industries. For example, the generation AI retrieves success stories of other companies or industries from a database and proposes best practices for cost reduction based on them. For example, it refers to methods for automatically generating and updating virtual tour videos. The generation AI can also analyze success stories of other companies or industries and propose optimal cost reduction measures based on them. For example, it can propose efficient methods and effective strategies. The generation AI can also comprehensively analyze success stories of other companies or industries and propose optimal best practices. For example, it can analyze factors for success and propose optimal cost reduction measures based on that. Success stories - The specific content and criteria of success stories must be clarified. For example, implementation cases of other companies, industry best practices, factors for success, etc. Best practices - The specific content and criteria of best practices must be clarified. For example, efficient methods, effective strategies, points for success, etc. This allows best practices for cost reduction to be proposed by referring to success stories of other companies or industries.

[0090] The virtual tour generation unit can reduce the infrastructure costs by utilizing the cloud service to generate the virtual tour video. For example, the virtual tour generation unit builds a system in which a generation AI utilizes cloud services to generate virtual tour videos. For example, the virtual tour generation unit generates videos on the cloud, reducing infrastructure costs. Furthermore, the generation AI utilizes cloud services and generates optimal virtual tour videos based on the cloud services. For example, server costs and maintenance costs can be reduced by generating videos on the cloud. Furthermore, the generation AI can propose methods to minimize infrastructure costs by comprehensively utilizing cloud services. For example, it can propose efficient ways to use cloud services. Cloud services - The specific content and types of cloud services must be clarified. For example, IaaS, PaaS, SaaS, etc. Infrastructure costs - The specific content and standards of infrastructure costs must be clarified. For example, server costs, network costs, maintenance costs, etc. This allows infrastructure costs to be reduced by utilizing cloud services to generate virtual tour videos.

[0091] The virtual tour generation unit can use the emotion estimation function to monitor the effectiveness of the virtual tour video in real time and continuously propose optimal cost reduction measures. The virtual tour generation unit, for example, uses the emotion estimation function to develop a system that monitors the effectiveness of the virtual tour video in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The emotion estimation function also monitors the effectiveness of the virtual tour video in real time and proposes optimal cost reduction measures based on the results. For example, it can propose effective cost reduction measures by improving scenes with low emotion scores. The emotion estimation function also comprehensively analyzes the effectiveness of the virtual tour video and proposes optimal cost reduction measures. For example, it can propose effective cost reduction measures by emphasizing scenes that users are most interested in based on the emotion scores. Cost reduction measures: The specific content and criteria of the cost reduction measures must be clarified. For example, efficiency methods, waste reduction, resource optimization, etc. This allows the effectiveness of the virtual tour video to be monitored in real time and optimal cost reduction measures to be continuously proposed.

[0092] The virtual tour generation unit can use the emotion estimation function to monitor the effectiveness of the virtual tour video in real time and continuously propose optimal cost reduction measures. The virtual tour generation unit, for example, uses the emotion estimation function to develop a system that monitors the effectiveness of the virtual tour video in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The emotion estimation function also monitors the effectiveness of the virtual tour video in real time and proposes optimal cost reduction measures based on the results. For example, it can propose effective cost reduction measures by improving scenes with low emotion scores. The emotion estimation function also comprehensively analyzes the effectiveness of the virtual tour video and proposes optimal cost reduction measures. For example, it can propose effective cost reduction measures by emphasizing scenes that users are most interested in based on the emotion scores. Cost reduction measures: The specific content and criteria of the cost reduction measures must be clarified. For example, efficiency methods, waste reduction, resource optimization, etc. This allows the effectiveness of the virtual tour video to be monitored in real time and optimal cost reduction measures to be continuously proposed.

[0093] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0094] The recommendation department can reflect the hobbies and interests of people with disabilities and suggest companies with a matching work environment and corporate culture. For example, for a person with a disability who likes sports, it can recommend sports-related companies. For a person with a disability who likes music, it can suggest music-related companies. Furthermore, for a person with a disability who likes reading, it can suggest publishers and bookstores. This makes it possible to suggest companies with a matching work environment and corporate culture that reflect the hobbies and interests of people with disabilities.

[0095] The recommendation department can recommend family-friendly companies, taking into consideration the family structure and living environment of people with disabilities. For example, it can recommend companies with comprehensive childcare support systems. For people with disabilities who have children, it can suggest companies that offer childcare leave systems. Furthermore, for people with disabilities who have family members who need care, it can suggest companies that offer nursing care leave systems. In this way, it can suggest family-friendly companies, taking into consideration the family structure and living environment of people with disabilities.

[0096] The recommendation unit uses the emotion estimation function to monitor the emotional reactions of people with disabilities to recommended companies in real time and continuously suggest the most suitable companies. For example, it can analyze facial expressions and voice during interviews to calculate an emotion score. It can also prioritize suggestions of companies with high emotion scores. Furthermore, based on the emotion score, it can suggest companies for which people with disabilities have the most positive emotions. This allows it to monitor the emotional reactions of people with disabilities to recommended companies in real time and continuously suggest the most suitable companies.

[0097] The virtual tour generator can also reproduce the audio environment and lighting conditions of an office, providing a more realistic virtual tour. For example, it can reproduce noise and conversations in the office. It can also reproduce illuminance and color temperature. It can also reproduce the acoustic characteristics and types of light sources in the office. This allows the audio environment and lighting conditions of the office to be reproduced, providing a more realistic virtual tour.

[0098] The virtual tour generation unit can use the emotion estimation function to analyze the user's emotional reactions during the virtual tour and generate videos that elicit positive emotions. For example, it can analyze the user's facial expressions and voice to calculate an emotion score. It can also highlight scenes with high emotion scores. Furthermore, it can generate videos that elicit positive emotions based on the emotion score. This makes it possible to analyze the user's emotional reactions and generate videos that elicit positive emotions.

[0099] The virtual tour generation unit can incorporate interviews and daily scenes of office employees into the virtual tour video. For example, it can add scenes in which employees talk about their work and the atmosphere in the workplace. It can also add scenes of employees working and taking breaks. Furthermore, by alternating between the interview video and the daily scenes, it is possible to convey the atmosphere of the workplace in more detail. In this way, by incorporating interviews and daily scenes of actual office employees into the virtual tour video, it is possible to experience a more realistic work environment.

[0100] The virtual tour generation unit can also recreate the surrounding environment of the office, allowing users to experience a comprehensive work environment. For example, it can display the locations of the nearest train station and bus stop. It can also incorporate information about restaurants and commercial facilities around the office into the virtual tour video. It can also display information about transportation access and surrounding facilities. This allows users to recreate the surrounding environment of the office and experience a comprehensive work environment.

[0101] The recommendation department uses generative AI to consider the career paths and growth goals of people with disabilities and propose optimal matches from a long-term perspective. For example, it can recommend companies where long-term career growth is expected. It can also suggest companies with clear promotion steps. It can also suggest companies where skill improvement is expected. This makes it possible to consider the career paths and growth goals of people with disabilities and propose optimal matches from a long-term perspective.

[0102] The recommendation unit uses the emotion estimation function to analyze the emotions that people with disabilities have about matching with companies and can suggest matches that elicit positive emotions. For example, it can analyze facial expressions and voice during interviews to calculate an emotion score. It can also prioritize suggestions of companies with high emotion scores. Furthermore, based on the emotion score, it can suggest companies that people with disabilities have the most positive emotions about. This makes it possible to analyze the emotions that people with disabilities have about matching with companies and suggest matches that elicit positive emotions.

[0103] The virtual tour generation unit uses generation AI to develop an automatic update function for the virtual office tour video, which allows it to always reflect the latest office environment. For example, it can reflect new equipment and layout changes in real time. It can also reflect the introduction of new equipment and layout changes. It can also reflect the latest equipment and layout in real time. This allows it to develop an automatic update function for the virtual office tour video, which allows it to always reflect the latest office environment.

[0104] The processing flow of the second embodiment will be briefly explained below.

[0105] Step 1: The recommendation department recommends potential companies for employment based on the desired conditions of the person with a disability. For example, the generation AI receives information such as the person with a disability's desired job type or industry, office location, office environment, and working conditions as input, and recommends potential companies for employment based on that information. For example, if a person with a disability inputs their preferences such as "I want to work in the IT industry," "I prefer a barrier-free office," or "I prefer a company with a flextime system," the generation AI will list companies that match those preferences. Step 2: The virtual tour generation unit generates a virtual office tour video based on the company office photos and blueprints recommended by the recommendation unit. For example, the generation AI receives several office photos and blueprints as input and automatically generates a virtual office tour video based on them. For example, when the generation AI inputs photos and blueprints of the office entrance, conference rooms, work spaces, break rooms, etc., it combines them to generate a realistic virtual tour video. This allows people with disabilities to experience the office environment in advance without having to visit the site.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0110] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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).

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0125] 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.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] 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).

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.

[0139] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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).

[0159] 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.

[0160] 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."

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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, in order to avoid confusion and to 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.

[0172] 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]

[0173] 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. The recommendation department recommends potential companies based on the desired conditions of people with disabilities, a virtual tour generation unit that generates a virtual office tour video based on the office photos or blueprints of the company recommended by the recommendation unit. A system characterized by:

2. The recommendation unit Analyzing the disabled person's past work experience and skill set, and based on that, proposing the most suitable job type or industry 2. The system of claim 1.

3. The virtual tour generation unit Reproduces the audio environment and lighting conditions of the office to provide a more realistic virtual tour 2. The system of claim 1.

4. The recommendation unit Using the generative AI, the company will consider the career path and growth goals of the disabled person and propose the best match from a long-term perspective.

2. The system of claim 1.

5. The recommendation unit Analyze the feelings of the disabled person regarding the job or industry they desire, and propose a workplace that will bring out positive feelings.

2. The system of claim 1.

Images