System

Abstract

A system is provided.SOLUTION: A system comprising: means for inputting desired terms; means for generating an initial candidate list based on the user's desired terms; means for displaying the initial candidate list and receiving feedback and additional terms from the user; means for re-evaluating and updating the candidate list based on the feedback and additional terms; means for displaying the re-evaluated candidate list and receiving a final selection from the user; and means for supporting an entry procedure for the finally selected company.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] When job hunting, it is extremely difficult for users to find the best job for them. Collecting a lot of information and comparing and analyzing it is time-consuming, making it a cumbersome process. It is also difficult to find a company that perfectly matches the user's desired criteria. In addition, the application process itself is time-consuming, hindering efficient job hunting. A system that can resolve this situation is needed. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for inputting desired conditions, a means for generating an initial candidate list based on the user's desired conditions, a means for displaying the initial candidate list and receiving feedback and additional conditions from the user, a means for reevaluating and updating the candidate list based on the feedback and additional conditions, a means for displaying the reevaluated candidate list and accepting a final selection from the user, and a means for supporting the application process to the final selected company. This system allows users to efficiently find the optimal job based on their desired conditions and smoothly proceed through the application process. Furthermore, the system includes functions for searching company information using a big database and generating and updating the candidate list using a generative AI model, allowing it to quickly and accurately respond to user needs.

[0006] "Means for entering desired conditions" refers to the input interface that allows users to enter desired conditions such as salary, industry, type of business, company size, area, and employee benefits.

[0007] "Means for generating an initial candidate list" refers to a function that uses a big database and generative AI model to create an initial list of candidate companies for employment based on the user's desired conditions.

[0008] The "means for displaying the initial candidate list" refers to a display or screen for visually presenting the generated initial candidate list to a user.

[0009] "Means for receiving feedback and additional conditions" refers to an input interface and communication function for allowing the user to input and receive feedback and further detailed conditions.

[0010] "Means to reevaluate and update the candidate list" refers to the functionality to review the initial candidate list and narrow it down based on user feedback and additional criteria.

[0011] "Means for displaying the re-evaluated candidate list" refers to a display or screen for visually presenting the updated candidate list to the user again.

[0012] "Means for accepting a final selection from a user" refers to an input interface and communication function for the user to confirm the final selection of potential employers.

[0013] "Means to support the entry procedures for the final selected companies" refers to the support function for collecting the necessary information for entry for the final selected companies and for smoothly carrying out the entry process.

[0014] A "big database" refers to a large data set containing corporate information, and is a database that can be used to search and analyze data based on the user's desired criteria.

[0015] A "generative AI model" refers to a model that uses machine learning and artificial intelligence algorithms to generate and update candidate lists based on user preferences and feedback. [Brief explanation of the drawings]

[0016] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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, a 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), and an APU (Accelerated Processing Unit).

[0020] 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.

[0021] 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.

[0022] 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), Bluetooth (registered trademark), etc.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0028] 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.

[0029] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0030] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0036] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0037] ---

[0038] The system of the present invention proposes the most suitable employment based on the user's desired conditions and efficiently supports the procedures up to application. The flow of processing of the entire system and a specific example will be explained below.

[0039] 1. Enter the user's desired conditions

[0040] Device:

[0041] When a user logs in, a screen for entering desired conditions is displayed.

[0042] Users enter their desired conditions such as salary, industry, type of business, company size, area, and employee benefits.

[0043] Example: A user enters the following requirements:

[0044] Salary: 4 million yen or more

[0045] Industry: IT industry

[0046] Area: Tokyo

[0047] Working style:Remote work available

[0048] Device:

[0049] The entered desired conditions are converted into JSON format and sent to the server.

[0050] 2. Initial candidate list generation

[0051] server:

[0052] Analyze the received JSON data and obtain the user's desired conditions.

[0053] Search for company information that matches your desired criteria from a big database.

[0054] The search results are passed as input conditions to the generative AI model to generate an initial candidate list.

[0055] The initial candidate list is converted into JSON format and sent to the terminal.

[0056] Example: The server selects 20 companies out of 100 as initial candidates and sends the list to the terminal.

[0057] 3. View candidate lists and receive feedback

[0058] Device:

[0059] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user as a list.

[0060] user:

[0061] Review the shortlist and enter your feedback and any additional preferences for each company.

[0062] example:

[0063] The user enters additional conditions such as "fully compatible with remote work, work that allows the use of English."

[0064] Device:

[0065] User feedback and additional conditions are converted into JSON format and sent to the server.

[0066] 4. Reevaluate and update the candidate list

[0067] server:

[0068] Parse the JSON data for received feedback and additional conditions.

[0069] Use generative AI models to narrow down the shortlist by re-evaluating based on feedback and additional criteria.

[0070] The updated candidate list is converted into JSON format and sent to the terminal.

[0071] Example: The server narrows down the initial candidate list from 20 companies to 10 companies and sends the re-evaluated candidate list to the terminal.

[0072] 5. Selection of finalists and assistance with application procedures

[0073] Device:

[0074] Display the updated candidate list to the user.

[0075] user:

[0076] Select the final job from the updated candidate list.

[0077] Express your intention to apply to the selected employer.

[0078] Device:

[0079] Display a form or link to collect application information for finalist companies.

[0080] The entry information entered by the user is converted into JSON format and sent to the server.

[0081] server:

[0082] The received entry information will be analyzed and the information necessary to complete the entry process will be sent to the relevant company.

[0083] Manage entry status and provide feedback to users.

[0084] example:

[0085] The user initiates an application to the company they have finally selected, the device displays the necessary form, and the server then sends the application information to the selected company.

[0086] In this way, the system of the present invention can propose optimal employment opportunities based on the user's desired conditions and provide consistent support up to the application process, allowing users to efficiently advance their job search and making it easier for them to find a job that meets their needs.

[0087] ---

[0088] The processing flow will be explained below.

[0089] ---

[0090] Step 1:

[0091] user:

[0092] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[0093] Device:

[0094] Receives the entered desired conditions, converts them into JSON format data, and sends the converted JSON format data to the server.

[0095] Step 2:

[0096] server:

[0097] The received JSON data is analyzed to extract the user's desired conditions. A big database is used to search for company information that matches the desired conditions. The search results are input into the generative AI model to generate an initial candidate list. The generated initial candidate list is converted into JSON format and sent to the terminal.

[0098] Step 3:

[0099] Device:

[0100] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[0101] user:

[0102] Review the list of candidates displayed and enter your feedback and any additional requirements for each company.

[0103] Device:

[0104] Receives feedback and additional conditions from the user, converts them into JSON format, and sends them to the server.

[0105] Step 4:

[0106] server:

[0107] Parse the JSON data of the received feedback and additional conditions. Use the generative AI model to reevaluate the initial candidate list based on the feedback and additional conditions and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[0108] Step 5:

[0109] Device:

[0110] The update candidate list received from the server is analyzed and displayed to the user.

[0111] user:

[0112] Select the final employer from the updated candidate list that is displayed. Indicate your intention to apply to the selected employer.

[0113] Device:

[0114] It displays an information form and link for the user to submit an entry for the final candidate they have selected. It receives the entry information entered by the user, converts it into JSON format, and sends it to the server.

[0115] Step 6:

[0116] server:

[0117] Analyze the received entry information. Send the necessary information to the relevant companies to process the entry. Monitor the entry status and provide feedback to the user.

[0118] ---

[0119] In this way, by performing specific actions at each step, users can efficiently find the best job based on their desired conditions and can also complete the application process smoothly.

[0120] Example 1

[0121] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0122] Previous job-hunting support systems lacked the efficiency to find companies that matched users' desired conditions, and the process for evaluating and updating candidate lists was insufficient, resulting in users spending a lot of time and effort finding the job they wanted.Furthermore, the application process lacked consistency and efficiency, placing a heavy burden on users when applying to each company.

[0123] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0124] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for analyzing the received feedback and additional conditions and re-evaluating the candidate list, means for updating the re-evaluated candidate list, means for displaying the re-evaluated candidate list and accepting a final selection from the user, and means for supporting the application procedure to the finally selected company. This enables users to efficiently and effectively find their desired job and simplifies the application procedure.

[0125] "Desired conditions" refers to the specific requirements and wishes that a user has for a job, such as salary, industry, type of business, company size, area, and employee benefits.

[0126] An "initial candidate list" refers to a list of multiple companies that is initially generated based on the user's desired conditions.

[0127] "Feedback" refers to the opinions, ratings, and additional requirements that users provide regarding the initial candidate list.

[0128] "Re-evaluated shortlist" refers to the list of companies that have been re-evaluated and filtered based on user feedback and additional criteria.

[0129] A "big database" refers to a database that stores a large amount of company information, and is used by job support systems to search for company information based on users' desired conditions.

[0130] "Generative AI model" refers to a model that uses artificial intelligence techniques to generate and update initial and reevaluated candidate lists, for example, by utilizing natural language processing or machine learning techniques.

[0131] A "prompt" is a text sentence that is input to a generative AI model to obtain a specific output, and includes the user's desired conditions and feedback.

[0132] "Application procedure support" refers to the process of supporting users to effectively apply to the company of their choice, including providing application forms and submitting required information.

[0133] MODE FOR CARRYING OUT THE INVENTION

[0134] The system of the present invention proposes suitable employment opportunities based on the user's desired employment conditions and efficiently supports the application process. This system effectively finds companies that match the user's preferences using a server, terminals, a generative AI model, and a big database.

[0135] Specific hardware and software used:

[0136] Server: A server capable of high-performance data processing and AI model execution

[0137] Device: The device used by the user, such as a PC, smartphone, or tablet

[0138] Database: A big database that stores corporate information (e.g., MongoDB or PostgreSQL)

[0139] Generative AI models: AI models capable of natural language processing and data analysis (e.g., "OpenAI GPT-4")

[0140] Program processing

[0141] 1. Enter your desired conditions:

[0142] Terminal: After the user logs in, a screen for inputting desired conditions is displayed. The user fills in the input form with desired conditions such as salary, industry, type of business, company size, area, and employee benefits. The input conditions are validated in real time, converted to JSON format, and sent to the server.

[0143] 2. Generate initial candidate list:

[0144] Server: Analyzes the received JSON data and extracts the user's desired conditions. Then, retrieves company information that matches the conditions from a big database and inputs the conditions as prompts into the generative AI model to generate an initial candidate list.

[0145] Example prompt: "Generate a list of companies that meet the following criteria: salary over ¥4 million, industry IT, location Tokyo, work style remote work available."

[0146] The generated initial candidate list is also converted into JSON format and sent to the terminal.

[0147] 3. View candidate list and receive feedback:

[0148] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted back to JSON format and sent to the server.

[0149] 4. Reevaluate and update the candidate list:

[0150] Server: Analyzes the received feedback and additional conditions, re-evaluates and narrows down the candidate list using the generative AI model, converts the re-evaluated candidate list into JSON format, and sends it to the device.

[0151] Example prompt: "Please reassess your shortlist based on the following feedback and additional criteria: Fully remote-friendly, English-speaking roles."

[0152] 5. Finalist selection and entry process assistance:

[0153] Terminal: The re-evaluated candidate list is displayed to the user. The user selects a final job and enters information to indicate their intention to apply. The application information is converted to JSON format and sent to the server.

[0154] Server: Analyzes entry information, sends it to related companies to assist with entry procedures, manages entry status, and provides feedback to users.

[0155] As a result, this system helps users efficiently apply to companies that meet their desired criteria. As a specific example, when the above prompt sentence is passed to the generative AI model, the generated list of companies can be used to smoothly advance the user's job search.

[0156] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0157] Step 1:

[0158] Input of user's desired conditions

[0159] Terminal: When the user logs in, a screen for inputting desired conditions is displayed. The user enters desired conditions such as salary, industry, type of business, company size, area, and employee benefits in the displayed form. The input is validated in real time, and an error message is displayed immediately if there are any omissions or errors.

[0160] input:

[0161] The desired conditions entered by the user in the form (e.g. salary, industry, area, etc.)

[0162] output:

[0163] Desired conditions data converted to JSON format

[0164] Specific behavior:

[0165] When the user completes the input, the submit button is activated. When the user presses the submit button, the input data is converted to JSON format and sent to the server as an HTTP request.

[0166] Step 2:

[0167] Initial candidate list generation

[0168] Server: Parses the received JSON-formatted desired conditions data and extracts them as key-value pairs. Next, it queries the big database to search for company information that matches the desired conditions. The search results are input as prompts to the generative AI model, and an initial candidate list is generated.

[0169] input:

[0170] JSON data containing the user's preferences

[0171] output:

[0172] Initial candidate list in JSON format

[0173] Specific behavior:

[0174] The server uses a parsing library to parse the JSON data. It then issues an SQL or NoSQL query to retrieve company information that matches the desired criteria from the database. The retrieved data is input to the generative AI model in the form of a prompt statement, which generates an initial candidate list. The generated list is then converted to JSON format and sent back to the device.

[0175] Step 3:

[0176] View candidate lists and receive feedback

[0177] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted into JSON format and sent to the server.

[0178] input:

[0179] Initial candidate list received from the server

[0180] User-entered feedback and additional requirements

[0181] output:

[0182] Feedback data in JSON format

[0183] Specific behavior:

[0184] The device parses the initial candidate list received from the server and displays it in the user interface. Once the user has entered their feedback and additional preferences, the device converts this into JSON format and sends it to the server.

[0185] Step 4:

[0186] Reevaluate and update the candidate list

[0187] Server: Analyzes the received feedback and JSON data for additional conditions, and re-evaluates it using the generative AI model. Passes a new prompt to the generative AI model to narrow down the candidate list. Converts the re-evaluated candidate list into JSON format and sends it to the device.

[0188] input:

[0189] JSON data of feedback received from users and additional conditions

[0190] output:

[0191] Re-evaluated candidate list in JSON format

[0192] Specific behavior:

[0193] The server analyzes the feedback and additional conditions and generates a new prompt. Example prompt: "Please reevaluate the candidate list based on the following feedback and additional conditions: fully compatible with remote work, work that utilizes English." This prompt is input into the generative AI model, which generates a reevaluated candidate list. The reevaluated list is converted into JSON format and sent back to the device.

[0194] Step 5:

[0195] Selection of finalists and assistance with application procedures

[0196] Terminal: Parses the re-evaluated candidate list received from the server and displays it to the user. The user selects the final job and enters application information. The application information is converted to JSON format and sent to the server.

[0197] input:

[0198] Re-evaluated candidate list received from the server

[0199] Entry information entered by the user

[0200] output:

[0201] Entry information in JSON format

[0202] Specific behavior:

[0203] The device parses the re-evaluated candidate list and displays it in a user-friendly format. Once the user makes their final selection and enters their entry information, the information is converted to JSON format and sent to the server.

[0204] Step 6:

[0205] Entry status management and feedback

[0206] Server: Analyzes the received entry information and sends it to the relevant companies. Manages the entry process and provides feedback to users on the status.

[0207] input:

[0208] JSON data of the entry information received from the user

[0209] output:

[0210] Feedback information regarding the status of the entry process

[0211] Specific behavior:

[0212] The server analyzes the entry information and sends the necessary data to the relevant companies via API, email, etc. The progress of the entry is monitored in real time and feedback is sent to the user's device. This feedback includes whether the entry was accepted and instructions for the next step.

[0213] (Application example 1)

[0214] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0215] In conventional job-hunting systems, even if users input their desired conditions, it can be difficult to efficiently find suitable employers based on those conditions. Furthermore, the time and effort required to gather company information and complete application procedures can make job hunting a burden for users. In particular, with the introduction of remote work and the growing need for virtual interviews, traditional methods present challenges that cannot be fully addressed. To address these challenges, the present invention provides a system that quickly and efficiently suggests optimal employers based on users' desired conditions and also supports interviews and browsing of company information in a virtual space.

[0216] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0217] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, means for supporting the application process to the finally selected company, and means for viewing company information in a virtual space and virtually experiencing interviews and job hunting. This enables users to efficiently find jobs that meet their desired conditions and smoothly conduct their job search by viewing company information and conducting interviews in a virtual space.

[0218] The "means for inputting desired conditions" is an interface that allows users to input their desired employment conditions, such as salary, industry, work location, and work style.

[0219] The "means for generating an initial candidate list" is a function for generating a list of suitable candidate companies at an early stage based on the desired conditions entered by the user.

[0220] The "means for displaying the initial candidate list and receiving feedback and additional conditions from the user" is a mechanism for displaying the generated initial candidate list to the user and accepting opinions and input of additional items from the user.

[0221] "Means to reevaluate and update candidate list" refers to the functionality to reevaluate the initial candidate list based on feedback received from users and additional criteria, and update the list as needed to reflect new information.

[0222] The "means for displaying the re-evaluated candidate list and accepting a final selection from the user" refers to an interface for presenting the updated candidate list to the user again and accepting the user's final selection of the company.

[0223] "Means to support the application process to the final selected company" refers to a support function that helps the user smoothly go through the application process to the company they have selected, and supports them in entering the necessary information and submitting documents, etc.

[0224] "A means of viewing company information in a virtual space and virtually experiencing interviews and job interviews" is a function that allows users to use smart glasses or a head-mounted display to check company information in a virtual environment and virtually experience interviews and job interviews.

[0225] The system of the present invention is designed to enable users to efficiently conduct job hunting, and to achieve this, it uses smart glasses and a head-mounted display to provide an experience in a virtual space.

[0226] 1. System Configuration

[0227] The system consists of the following main components:

[0228] Terminal: A device that provides an interface for users to input their desired conditions, view company information, and conduct interviews and job interviews in a virtual space. Examples of this include smart glasses and head-mounted displays.

[0229] Server: A central control unit that analyzes preferences, generates and updates candidate lists, processes feedback, and assists with the entry process.

[0230] Generative AI model: An algorithm that uses OpenAI's API to suggest suitable companies based on the user's desired criteria.

[0231] 2. Program Overview

[0232] Below is an overview of the system's main functions: company proposals based on the user's desired conditions and virtual interview functions.

[0233] Input and analysis of desired conditions

[0234] The user enters their desired job search conditions from their device, including salary, industry, work location, and work style. The entered information is converted into JSON format and sent to the server.

[0235] Generate and display candidate lists

[0236] The server analyzes the received requirements and searches for relevant company information in a big database. It then uses a generative AI model to create an initial candidate list and sends it to the device. The device then displays it to the user and accepts feedback and additional requirements.

[0237] Reevaluate and update the candidate list

[0238] After receiving user feedback, the server re-evaluates and updates the candidate list using the generative AI model, which is then sent back to the device and displayed to the user.

[0239] Viewing company information and conducting interviews in a virtual space

[0240] Users can enter the virtual space by wearing smart glasses or a head-mounted display and check detailed information about companies. Interviews and job interviews can also be conducted in the virtual space. This allows users to conduct job hunting remotely without having to visit a company in person.

[0241] 3. Examples and prompts

[0242] As a specific use case, the following shows how a user inputs their desired conditions in a virtual space and the generative AI model suggests suitable companies.

[0243] Example prompt sentence:

[0244] Use a generative AI model to generate a list of companies that meet the following criteria:

[0245] Salary: 4 million yen or more

[0246] Industry: IT industry

[0247] Area: Tokyo

[0248] Working style:Remote work available

[0249] By sending this prompt to the system, a list of companies that match the user's desired criteria is automatically generated, allowing the user to proceed with their job search efficiently and effectively.

[0250] The above is an embodiment of the present invention.

[0251] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0252] Step 1:

[0253] Enter your desired criteria and submit:

[0254] Users log in to the virtual space using smart glasses or a head-mounted display. A desired conditions input screen is displayed, and the user inputs conditions such as desired salary, industry, work location, and working style. The input information is converted to JSON format on the device and sent to the server.

[0255] Input: User's desired conditions (e.g. salary, industry, work location, work style)

[0256] Output: JSON format desired conditions data

[0257] Step 2:

[0258] Generate the initial candidate list:

[0259] The server analyzes the received JSON data and obtains the user's desired conditions. It then searches the big database to extract company information that matches the desired conditions. The search results are passed as input conditions to the generative AI model, which generates an initial candidate list. The generated initial candidate list is converted to JSON format and sent to the device.

[0260] Input: JSON format desired conditions data

[0261] Data calculation: Big database search, initial candidate list generation using generative AI models

[0262] Output: Initial candidate list in JSON format

[0263] Step 3:

[0264] View initial candidate list and receive feedback:

[0265] The device parses the JSON data received from the server and displays an initial candidate list to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted to JSON format on the device and sent to the server.

[0266] Input: Initial candidate list in JSON format

[0267] Output: User feedback and additional conditions (JSON format)

[0268] Step 4:

[0269] Reevaluate and update the candidate list:

[0270] The server parses the received feedback and additional conditions in JSON data and re-evaluates them using the generative AI model. The re-evaluated candidate list is converted into JSON format and sent to the device. The device then displays the updated candidate list to the user.

[0271] Input: Feedback and additional conditions data in JSON format

[0272] Data Computing: Reevaluating and Updating Candidate Lists with Generative AI Models

[0273] Output: Updated candidate list in JSON format

[0274] Step 5:

[0275] Finalist selection and entry assistance:

[0276] The user selects a final employer from the updated candidate list and indicates their intention to apply. The device displays a form and links for collecting application information for the final candidate companies. The application information entered by the user is converted to JSON format on the device and sent to the server. The server analyzes the application information and sends the necessary information to the relevant companies to complete the application process.

[0277] Input: Updated candidate list in JSON format

[0278] Output: User entry information (JSON format)

[0279] Step 6:

[0280] Virtual company information viewing and interviews:

[0281] Users wear smart glasses or a head-mounted display and can view company information in a virtual space. They can also access company booths, view presentation videos and detailed company information, and virtually experience interviews and job interviews in the virtual space.

[0282] Input: Company information in virtual space

[0283] Output: Company information browsing results and interview experience

[0284] The above are the specific processing steps of the system that realizes this application example. This processing flow allows users to consistently conduct their job search efficiently and effectively.

[0285] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0286] ---

[0287] The system of the present invention not only proposes optimal employment opportunities based on the user's desired conditions and supports the application process, but also realizes more accurate job hunting by combining it with an emotion engine that recognizes the user's emotions. The following explains the overall processing flow of the system and a specific example.

[0288] 1. User preference input and emotion recognition

[0289] Device:

[0290] When a user logs in, a screen for entering desired conditions is displayed.

[0291] Users enter their desired conditions, such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[0292] user:

[0293] When users input their desired conditions, the device's emotion engine analyzes their facial expressions and voice to collect emotional data.

[0294] Device:

[0295] The emotion data along with the entered desired conditions is converted into JSON format and sent to the server.

[0296] 2. Initial candidate list generation and use of emotion data

[0297] server:

[0298] The received JSON data of desired conditions and emotional data is analyzed to extract the user's desired conditions.

[0299] Use a big database to search for company information that matches your desired criteria.

[0300] Search results are fed into a generative AI model, which takes sentiment data into account when generating an initial candidate list.

[0301] The initial candidate list is converted into JSON format and sent to the terminal.

[0302] 3. View candidate lists and receive feedback

[0303] Device:

[0304] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user.

[0305] user:

[0306] While reviewing the displayed list of candidates, users can enter their feedback and any additional requirements for each company. The emotion engine also collects their emotions when providing feedback.

[0307] Device:

[0308] User feedback, additional conditions, and collected emotional data are converted into JSON format and sent to the server.

[0309] 4. Reevaluate and update the candidate list

[0310] server:

[0311] Parse the JSON data for received feedback, additional conditions, and sentiment data.

[0312] A generative AI model is used to re-evaluate the initial candidate list based on feedback, additional criteria, and sentiment data to generate an updated candidate list.

[0313] The updated candidate list is converted into JSON format and sent to the terminal.

[0314] 5. Finalist selection and use of sentiment data

[0315] Device:

[0316] Display the updated candidate list to the user.

[0317] user:

[0318] The final job is selected from the updated candidate list. During the selection process, the emotion engine recognizes the user's emotions and collects the data.

[0319] Device:

[0320] An information form or link is displayed for the user to enter the final candidate selected by the user, and the user enters the required information.

[0321] Emotion data is also sent to the server together with the entered entry information.

[0322] 6. Entry procedure support and use of emotion data

[0323] server:

[0324] The received entry information and emotional data are analyzed, and the entry process is carried out with the relevant companies.

[0325] The necessary information will be sent to related companies to provide optimal support for application procedures based on emotional data.

[0326] Manage entry status and provide feedback to users.

[0327] Specific examples

[0328] For example, if a user enters their desired conditions as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system will take this into account when creating an initial candidate list. Upon feedback, the system will add more detailed conditions, such as "fully remote work-enabled, work that utilizes English," and re-evaluate the results using the emotion engine data to present the optimal candidate list. The system will then support a more effective application process based on the emotion data from the final selection.

[0329] ---

[0330] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, thereby realizing more personalized job suggestions and application procedures, allowing users to efficiently find the job that best suits them and conducting a highly satisfying job search.

[0331] The processing flow will be explained below.

[0332] ---

[0333] Step 1:

[0334] user:

[0335] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[0336] Device:

[0337] When a user enters their desired conditions, the emotion engine analyzes their facial expressions and voice to collect emotional data. The entered desired conditions and emotional data are converted into JSON format and sent to the server.

[0338] Step 2:

[0339] server:

[0340] The system analyzes the received JSON data of desired conditions and emotion data to extract the user's desired conditions. It uses a big database to search for company information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list based on the search results and emotion data. It converts the initial candidate list into JSON format and sends it to the device.

[0341] Step 3:

[0342] Device:

[0343] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[0344] user:

[0345] Review the displayed list of candidates and enter your feedback and additional requirements for each company. As you enter your feedback and additional requirements, the emotion engine will collect your emotional data.

[0346] Device:

[0347] User feedback, additional conditions, and emotional data are converted into JSON format and sent to the server.

[0348] Step 4:

[0349] server:

[0350] Parse the received feedback, additional conditions, and emotional data in JSON format. Use the generative AI model to re-evaluate the candidate list based on the feedback, additional conditions, and emotional data, and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[0351] Step 5:

[0352] Device:

[0353] The update candidate list received from the server is analyzed and displayed to the user.

[0354] user:

[0355] The final job is selected from the updated candidate list. At the time of the final selection, the emotion engine recognizes the user's emotions and collects the data.

[0356] Device:

[0357] It displays a form and link for the user to apply to the final candidate company of their choice. The user enters the necessary information, and the application information and emotion data are converted into JSON format and sent to the server.

[0358] Step 6:

[0359] server:

[0360] The system analyzes the received entry information and emotion data. It sends the necessary information to the relevant companies to complete the entry process. It provides optimal support for the entry process based on the emotion data, manages the entry status, and provides feedback to the user.

[0361] ---

[0362] In this way, by performing specific operations at each processing step, a system is realized that takes into account the user's emotions and provides more personalized job candidate suggestions and procedural support.

[0363] Example 2

[0364] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0365] Conventional job-hunting support systems suggested candidate companies based on the user's desired conditions, but did not consider the user's feelings when suggesting candidate companies. As a result, it was difficult for users to find the best job, and they were unable to achieve a satisfying job-hunting experience. In addition, it was difficult to effectively reflect received feedback and additional conditions, and there was also the problem of candidate lists not being updated sufficiently.

[0366] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input desired conditions, means for analyzing the user's facial expressions and voice to collect emotional data, means for transmitting the input desired conditions and emotional data to the server, means for generating an initial candidate list based on the user's desired conditions and emotional data, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the received feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, and means for supporting the application process to the finally selected company. This enables more personalized job suggestions and support that take into account not only the user's desired conditions but also their emotions.

[0367] "User's desired conditions" refers to the conditions the user desires for employment, such as salary, industry, type of business, company size, area, and working style.

[0368] "Emotional data" refers to data that indicates the user's emotional state (e.g., joy, surprise, anxiety, etc.) obtained by analyzing the user's facial expressions and voice.

[0369] "Initial candidate list" refers to a list of candidate companies presented to a user, generated based on the user's desired conditions and emotional data.

[0370] "Feedback" refers to the opinions, ratings, and additional preferences provided by the user regarding the displayed list of candidate companies.

[0371] "Re-evaluated Candidate List" refers to the list of candidate companies that have been re-evaluated and updated based on user feedback and additional criteria and sentiment data.

[0372] "Means to support the entry process" refers to functions that support the procedures required when a user applies to the company they have finally selected (such as filling out information forms and submitting required documents).

[0373] "Big database" refers to a database system (e.g., Google Cloud BigQuery, Amazon Redshift) for efficiently managing and searching large amounts of data.

[0374] "Generative AI model" refers to a model (e.g., ChatGPT) that uses artificial intelligence techniques to generate and update candidate lists.

[0375] The system of the present invention proposes optimal job opportunities based on the user's desired conditions and supports the application process. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system achieves more accurate job hunting. Specific embodiments of the present invention are described in detail below.

[0376] System Overview

[0377] The system includes means for inputting user preferences, means for collecting sentiment data, means for generating an initial candidate list, means for receiving and re-evaluating feedback, means for receiving final selections, and means for assisting the entry process.

[0378] User preference input and emotion recognition

[0379] Device:

[0380] When a user logs in, a screen for entering desired conditions appears. The user enters their desired conditions, such as salary, industry, type of business, company size, location, and working style (e.g., remote work available). At this time, the device uses its built-in webcam and microphone to send the user's facial expressions and voice to an emotion engine, which collects emotional data in real time. The emotional data is analyzed using technologies such as "Affectiva" and "Microsoft Azure Emotion API."

[0381] Generating an initial candidate list

[0382] server:

[0383] The desired conditions and emotion data sent from the device are received and analyzed. Based on the analyzed data, a big database (e.g., Google Cloud BigQuery or Amazon Redshift) is used to search for company information that matches the user's desired conditions. The search results and emotion data are input into a generative AI model (e.g., ChatGPT) to generate an initial candidate list. A prompt such as "Please select companies in the IT industry in Tokyo where the user's desired salary is 4 million yen or more. The user has shown a high interest in remote work" is used.

[0384] View candidate lists and receive feedback

[0385] Device:

[0386] The initial candidate list sent from the server is analyzed and a list of candidates is displayed to the user. The user reviews the displayed candidate list and enters feedback and additional desired conditions for each company. The device also collects emotional data during this process. The collected feedback and emotional data are then sent back to the server.

[0387] Reevaluate and update the candidate list

[0388] server:

[0389] The received feedback and sentiment data is analyzed, and the initial candidate list is re-evaluated and updated using a generative AI model, using prompts such as "Users have a strong preference for full remote work support, so please focus on this." The re-evaluated candidate list is then sent to the device.

[0390] Finalist selection and entry procedures

[0391] Device:

[0392] The updated candidate list is displayed to the user. The user then selects the final employer. Emotional data is also collected during this process. An information form and link for applying to the final selected company are displayed, and the user enters the required information. The entered application information and emotional data are then sent to the server.

[0393] server:

[0394] Analyze the received entry information and emotion data and process the entry with the relevant companies. Send the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manage the entry status and provide feedback to the user.

[0395] Specific examples

[0396] When a user enters their desired conditions, such as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system takes this into account when creating an initial candidate list. If the user provides feedback and adds more detailed conditions, such as "full remote work support, work that utilizes English," the system reevaluates the results using the emotion engine data and presents the optimal candidate list. The system then supports a more effective application process based on the emotion data from the final selection.

[0397] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, allowing for more personalized job suggestions and application procedures, enabling users to efficiently find the job that best suits them and achieving a more satisfying job search experience.

[0398] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0399] Step 1:

[0400] User: When a user logs in, a screen for entering desired conditions is displayed on the device. The user enters desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed). The input information is saved on the device.

[0401] Input: User's desired criteria (e.g. salary, industry, business type, etc.).

[0402] Output: Generate data (e.g., JSON format) based on the desired conditions.

[0403] Step 2:

[0404] Device: The user's facial expressions and voice are collected in real time on the input screen using a webcam and microphone. The collected data is analyzed using an emotion engine (e.g., "Affectiva" or "Microsoft Azure Emotion API"). Emotional data (happiness, surprise, anxiety, etc.) is generated as a result of the analysis.

[0405] Input: User facial and voice data.

[0406] Output: Generate emotion data (e.g., JSON format).

[0407] Step 3:

[0408] Device: The desired conditions and emotional data are combined into a single JSON file and sent to the server. The combined data includes the user's desired conditions and emotional state.

[0409] Input: Desired condition data, emotion data.

[0410] Output: Consolidated preference and sentiment data in JSON format.

[0411] Step 4:

[0412] Server: Analyzes the received desired conditions and sentiment data to extract the user's desired conditions. Uses a big database (e.g., Google Cloud BigQuery or Amazon Redshift) to search for company information that matches the desired conditions. Filters the company information in the database using the search query.

[0413] Input: Integrated desire criteria and emotion data.

[0414] Output: Company information as search results.

[0415] Step 5:

[0416] Server: Input the search results and sentiment data into a generative AI model (e.g., "ChatGPT") to generate an initial candidate list. Input a prompt such as "The user's desired salary is 4 million yen or more, and please select companies in the IT industry in Tokyo. The user has a high interest in remote work." Create an initial candidate list as a result and convert it to JSON format.

[0417] Input: Search results, sentiment data.

[0418] Output: Initial candidate list (JSON format).

[0419] Step 6:

[0420] Terminal: Analyzes the initial candidate list received from the server and displays a list of candidates to the user. The displayed candidate list includes information about each company (e.g., salary, industry, location, etc.).

[0421] Input: Initial candidate list (JSON format).

[0422] Output: A candidate list that can be viewed by the user.

[0423] Step 7:

[0424] User: Review the list of candidates and enter feedback and additional desired conditions for each company. When providing feedback, the device also collects the user's facial expressions and voice, which are analyzed by the emotion engine. Additional emotional data is generated.

[0425] Input: Feedback on candidate list, facial expression and speech data.

[0426] Output: Feedback, additional conditions, and additional emotion data (JSON format).

[0427] Step 8:

[0428] Terminal: Collects feedback, additional conditions, and additional emotion data, integrates them into a single JSON data, and sends it to the server.

[0429] Input: Feedback, additional conditions, additional emotion data.

[0430] Output: Consolidated feedback data in JSON format.

[0431] Step 9:

[0432] Server: Analyzes the received feedback, additional conditions, and emotional data. The generative AI model is given another prompt, such as "The user strongly desires full remote work support, so please focus on this." This prompt reevaluates the initial candidate list and generates an updated candidate list. The updated candidate list is converted to JSON format and sent to the device.

[0433] Input: Feedback, additional conditions, emotional data.

[0434] Output: The updated candidate list in JSON format.

[0435] Step 10:

[0436] On the device: Show the updated candidate list to the user.

[0437] Input: The updated candidate list (in JSON format).

[0438] Output: An updated candidate list that can be viewed by the user.

[0439] Step 11:

[0440] User: Selects a final job from the updated candidate list. Emotional data is collected and analyzed during the selection process.

[0441] Input: Updated candidate list, facial expression and speech data.

[0442] Output: Final selection data, emotion data (JSON format).

[0443] Step 12:

[0444] Terminal: Displays an information form and link for the final candidates to enter, and the user enters the required information. The entered entry information and emotion data are sent to the server.

[0445] Input: Final selection data, input information, emotion data.

[0446] Output: Consolidated entry data (JSON format).

[0447] Step 13:

[0448] Server: Analyzes the received entry information and emotion data and carries out the entry process with the relevant companies. Sends the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manages the entry status and provides feedback to the user.

[0449] Input: Entry information, emotion data.

[0450] Output: Entry information to companies, feedback to users.

[0451] (Application example 2)

[0452] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0453] Conventional content recommendation systems generate candidate lists based on a user's desired conditions, but they are unable to consider the user's emotions and moods, making it difficult to recommend the optimal content that matches the user's current mood. Furthermore, because they update lists based only on user feedback and additional conditions, they lack an understanding of actual user experiences. Therefore, there is a need for a method to recommend more personalized content that takes into account the user's emotional data.

[0454] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0455] In this invention, the server includes an emotion recognition means for recognizing a user's emotion and collecting the data, a means for adjusting a candidate list based on the emotion data and desired conditions, a means for searching for information corresponding to the user's desired conditions using a big database, and a means for generating and updating the candidate list using a generative AI model. This makes it possible to dynamically provide optimal content for the user's emotional state and improve user satisfaction.

[0456] "Desired conditions" refers to the genre, keywords, format, etc. of the content the user wants to watch.

[0457] "Initial candidate list" refers to a list of content candidates generated based on the user's desired conditions.

[0458] "Feedback" refers to the ratings and opinions that users give to the displayed list of candidates.

[0459] "Additional Terms" refers to any further detailed desired terms provided by the User along with their Feedback.

[0460] "Emotion recognition means" refers to the function of analyzing the user's facial expressions and voice and recognizing their emotional state.

[0461] "Emotion Data" refers to data regarding a user's emotions collected by an emotion recognition means.

[0462] A "big database" refers to a database for storing and searching large amounts of data, such as users' viewing history, desired conditions, and emotional data.

[0463] "Generative AI model" refers to an artificial intelligence model that generates and updates optimal content candidate lists based on user preferences and emotional data.

[0464] "Entry Procedure" refers to the various procedures to facilitate access to and viewing of the Final Selected Content.

[0465] The present invention is a content recommendation system that uses an emotion recognition engine and provides optimal content based on a user's desired conditions and emotion data. The system of the present invention is implemented as follows.

[0466] System configuration

[0467] Hardware and software used

[0468] Smartphones / Smart Glasses / Head-Mounted Displays

[0469] Device camera: Collects user facial expression data.

[0470] Device microphone: Collects user voice data.

[0471] server

[0472] Big database: Stores user viewing history, preferences, and emotional data.

[0473] Generative AI model: Generates and updates a list of optimal content candidates based on desired conditions and sentiment data.

[0474] software

[0475] OpenCV (facial expression recognition)

[0476] TensorFlow (voice emotion recognition)

[0477] Flask (Server-side API construction)

[0478] Program processing

[0479] 1. Collect user requirements

[0480] Users launch the app on their smartphone, smart glasses, or head-mounted display and enter their desired content preferences.

[0481] The device camera and microphone collect emotion data from the user's facial expressions and voice, which is then converted into JSON format and sent to the server.

[0482] 2. Initial candidate list generation and use of emotion data

[0483] The server analyzes the received desired conditions and emotional data, searches a big database, and generates an initial candidate list.

[0484] The generative AI model takes into account emotional data and desired conditions to generate an optimal list of content candidates.

[0485] 3. View candidate lists and receive feedback

[0486] An initial candidate list is sent to the device and displayed to the user, who can then provide feedback or additional criteria.

[0487] User feedback, additional conditions, and newly collected emotional data are sent to the server.

[0488] 4. Reevaluate and update the candidate list

[0489] The server analyzes the feedback, additional conditions, and emotional data, and re-evaluates and updates the candidate list using a generative AI model.

[0490] The updated list is sent to the device and displayed to the user again.

[0491] 5. Selection of Finalists and Entry Procedure

[0492] The user selects the final content, and sentiment data is collected at the time of the final selection.

[0493] The necessary information for the entry procedure is displayed, and the entry procedure is supported.

[0494] Examples of concrete examples and prompts

[0495] Specific examples

[0496] The user inputs their preference for "action movies" and the emotion recognition engine simultaneously recognizes that the user is excited. Based on this information, the server generates a list of suitable action movies and provides them to the user. Emotional data is also continuously collected during viewing and used for subsequent recommendations.

[0497] Prompt Sentence Examples

[0498] "I recognize that the user is excited. Please generate a list of action movies. The desired criteria is 'action movies.'"

[0499] As a result, the system of the present invention dynamically recommends content taking into account not only the user's desired conditions but also emotional data, thereby significantly improving user satisfaction.

[0500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0501] Program processing steps

[0502] Step 1:

[0503] The user enters their desired conditions and emotional data is collected.

[0504] Input: User's desired conditions (e.g. genre, keywords, etc.), facial expression data, voice data

[0505] Processing: The device displays a screen for entering desired conditions, and the user enters the conditions. The device also collects facial and voice data using the camera and microphone. The collected data is converted into JSON format.

[0506] Output: JSON formatted preference and emotion data sent to the server

[0507] Step 2:

[0508] Generate an initial candidate list.

[0509] Input: JSON formatted preference and emotion data

[0510] Processing: The server analyzes the received desired conditions and emotional data. It searches a big database to collect content information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list, taking into account the emotional data.

[0511] Output: Initial candidate list sent to the terminal

[0512] Step 3:

[0513] Present an initial list of candidates to the user and receive feedback and additional criteria.

[0514] Input: Initial candidate list

[0515] Processing: The device displays an initial list of candidates. The user can then enter feedback (e.g., a rating of good or bad) or additional criteria (e.g., a more detailed genre specification) based on the displayed list, and new emotional data is collected using the device's camera and microphone. This data is then converted back into JSON format.

[0516] Output: Feedback, additional conditions, and emotion data sent to the server

[0517] Step 4:

[0518] Reassess and update the candidate list.

[0519] Input: Feedback, additional conditions, emotional data

[0520] Processing: The server analyzes the received feedback, additional criteria, and sentiment data. It uses the generative AI model to re-evaluate the initial candidate list and generate an updated list.

[0521] Output: Updated candidate list sent to the terminal

[0522] Step 5:

[0523] The updated candidate list is displayed to the user and a final selection is accepted.

[0524] Input: Updated candidate list

[0525] Processing: The device displays the updated candidate list to the user, who then selects the final viewing content, collecting emotional data at the time of selection.

[0526] Output: Final selection results and emotion data sent to the server

[0527] Step 6:

[0528] Assist with the entry process.

[0529] Input: Final selection results and emotion data

[0530] Processing: The server analyzes the final selection results and emotion data, generates the necessary entry procedure information, and assists the user in completing the necessary viewing procedures.

[0531] Output: Final viewing instructions provided to the user

[0532] Through these steps, the content recommendation system of the present invention can dynamically recommend content that perfectly matches the user's emotional state, optimizing the user's viewing experience.

[0533] 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.

[0534] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0535] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0536] [Second embodiment]

[0537] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0538] 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.

[0539] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0540] 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.

[0541] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0542] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0543] 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.

[0544] 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.

[0545] 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 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.

[0546] 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.

[0547] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0548] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0549] ---

[0550] The system of the present invention proposes the most suitable employment based on the user's desired conditions and efficiently supports the procedures up to application. The flow of processing of the entire system and a specific example will be explained below.

[0551] 1. Enter the user's desired conditions

[0552] Device:

[0553] When a user logs in, a screen for entering desired conditions is displayed.

[0554] Users enter their desired conditions such as salary, industry, type of business, company size, area, and employee benefits.

[0555] Example: A user enters the following requirements:

[0556] Salary: 4 million yen or more

[0557] Industry: IT industry

[0558] Area: Tokyo

[0559] Working style:Remote work available

[0560] Device:

[0561] The entered desired conditions are converted into JSON format and sent to the server.

[0562] 2. Initial candidate list generation

[0563] server:

[0564] Analyze the received JSON data and obtain the user's desired conditions.

[0565] Search for company information that matches your desired criteria from a big database.

[0566] The search results are passed as input conditions to the generative AI model to generate an initial candidate list.

[0567] The initial candidate list is converted into JSON format and sent to the terminal.

[0568] Example: The server selects 20 companies out of 100 as initial candidates and sends the list to the terminal.

[0569] 3. View candidate lists and receive feedback

[0570] Device:

[0571] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user as a list.

[0572] user:

[0573] Review the shortlist and enter your feedback and any additional preferences for each company.

[0574] example:

[0575] The user enters additional conditions such as "fully compatible with remote work, work that allows the use of English."

[0576] Device:

[0577] User feedback and additional conditions are converted into JSON format and sent to the server.

[0578] 4. Reevaluate and update the candidate list

[0579] server:

[0580] Parse the JSON data for received feedback and additional conditions.

[0581] Use generative AI models to narrow down the shortlist by re-evaluating based on feedback and additional criteria.

[0582] The updated candidate list is converted into JSON format and sent to the terminal.

[0583] Example: The server narrows down the initial candidate list from 20 companies to 10 companies and sends the re-evaluated candidate list to the terminal.

[0584] 5. Selection of finalists and assistance with application procedures

[0585] Device:

[0586] Display the updated candidate list to the user.

[0587] user:

[0588] Select the final job from the updated candidate list.

[0589] Express your intention to apply to the selected employer.

[0590] Device:

[0591] Display a form or link to collect application information for finalist companies.

[0592] The entry information entered by the user is converted into JSON format and sent to the server.

[0593] server:

[0594] The received entry information will be analyzed and the information necessary to complete the entry process will be sent to the relevant company.

[0595] Manage entry status and provide feedback to users.

[0596] example:

[0597] The user initiates an application to the company they have finally selected, the device displays the necessary form, and the server then sends the application information to the selected company.

[0598] In this way, the system of the present invention can propose optimal employment opportunities based on the user's desired conditions and provide consistent support up to the application process, allowing users to efficiently advance their job search and making it easier for them to find a job that meets their needs.

[0599] ---

[0600] The processing flow will be explained below.

[0601] ---

[0602] Step 1:

[0603] user:

[0604] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[0605] Device:

[0606] Receives the entered desired conditions, converts them into JSON format data, and sends the converted JSON format data to the server.

[0607] Step 2:

[0608] server:

[0609] The received JSON data is analyzed to extract the user's desired conditions. A big database is used to search for company information that matches the desired conditions. The search results are input into the generative AI model to generate an initial candidate list. The generated initial candidate list is converted into JSON format and sent to the terminal.

[0610] Step 3:

[0611] Device:

[0612] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[0613] user:

[0614] Review the list of candidates displayed and enter your feedback and any additional requirements for each company.

[0615] Device:

[0616] Receives feedback and additional conditions from the user, converts them into JSON format, and sends them to the server.

[0617] Step 4:

[0618] server:

[0619] Parse the JSON data of the received feedback and additional conditions. Use the generative AI model to reevaluate the initial candidate list based on the feedback and additional conditions and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[0620] Step 5:

[0621] Device:

[0622] The update candidate list received from the server is analyzed and displayed to the user.

[0623] user:

[0624] Select the final employer from the updated candidate list that is displayed. Indicate your intention to apply to the selected employer.

[0625] Device:

[0626] It displays an information form and link for the user to submit an entry for the final candidate they have selected. It receives the entry information entered by the user, converts it into JSON format, and sends it to the server.

[0627] Step 6:

[0628] server:

[0629] Analyze the received entry information. Send the necessary information to the relevant companies to process the entry. Monitor the entry status and provide feedback to the user.

[0630] ---

[0631] In this way, by performing specific actions at each step, users can efficiently find the best job based on their desired conditions and can also complete the application process smoothly.

[0632] Example 1

[0633] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0634] Previous job-hunting support systems lacked the efficiency to find companies that matched users' desired conditions, and the process for evaluating and updating candidate lists was insufficient, resulting in users spending a lot of time and effort finding the job they wanted.Furthermore, the application process lacked consistency and efficiency, placing a heavy burden on users when applying to each company.

[0635] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0636] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for analyzing the received feedback and additional conditions and re-evaluating the candidate list, means for updating the re-evaluated candidate list, means for displaying the re-evaluated candidate list and accepting a final selection from the user, and means for supporting the application procedure to the finally selected company. This enables users to efficiently and effectively find their desired job and simplifies the application procedure.

[0637] "Desired conditions" refers to the specific requirements and wishes that a user has for a job, such as salary, industry, type of business, company size, area, and employee benefits.

[0638] An "initial candidate list" refers to a list of multiple companies that is initially generated based on the user's desired conditions.

[0639] "Feedback" refers to the opinions, ratings, and additional requirements that users provide regarding the initial candidate list.

[0640] "Re-evaluated shortlist" refers to the list of companies that have been re-evaluated and filtered based on user feedback and additional criteria.

[0641] A "big database" refers to a database that stores a large amount of company information, and is used by job support systems to search for company information based on users' desired conditions.

[0642] "Generative AI model" refers to a model that uses artificial intelligence techniques to generate and update initial and reevaluated candidate lists, for example, by utilizing natural language processing or machine learning techniques.

[0643] A "prompt" is a text sentence that is input to a generative AI model to obtain a specific output, and includes the user's desired conditions and feedback.

[0644] "Application procedure support" refers to the process of supporting users to effectively apply to the company of their choice, including providing application forms and submitting required information.

[0645] MODE FOR CARRYING OUT THE INVENTION

[0646] The system of the present invention proposes suitable employment opportunities based on the user's desired employment conditions and efficiently supports the application process. This system effectively finds companies that match the user's preferences using a server, terminals, a generative AI model, and a big database.

[0647] Specific hardware and software used:

[0648] Server: A server capable of high-performance data processing and AI model execution

[0649] Device: The device used by the user, such as a PC, smartphone, or tablet

[0650] Database: A big database that stores corporate information (e.g., MongoDB or PostgreSQL)

[0651] Generative AI models: AI models capable of natural language processing and data analysis (e.g., "OpenAI GPT-4")

[0652] Program processing

[0653] 1. Enter your desired conditions:

[0654] Terminal: After the user logs in, a screen for inputting desired conditions is displayed. The user fills in the input form with desired conditions such as salary, industry, type of business, company size, area, and employee benefits. The input conditions are validated in real time, converted to JSON format, and sent to the server.

[0655] 2. Generate initial candidate list:

[0656] Server: Analyzes the received JSON data and extracts the user's desired conditions. Then, retrieves company information that matches the conditions from a big database and inputs the conditions as prompts into the generative AI model to generate an initial candidate list.

[0657] Example prompt: "Generate a list of companies that meet the following criteria: salary over ¥4 million, industry IT, location Tokyo, work style remote work available."

[0658] The generated initial candidate list is also converted into JSON format and sent to the terminal.

[0659] 3. View candidate list and receive feedback:

[0660] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted back to JSON format and sent to the server.

[0661] 4. Reevaluate and update the candidate list:

[0662] Server: Analyzes the received feedback and additional conditions, re-evaluates and narrows down the candidate list using the generative AI model, converts the re-evaluated candidate list into JSON format, and sends it to the device.

[0663] Example prompt: "Please reassess your shortlist based on the following feedback and additional criteria: Fully remote-friendly, English-speaking roles."

[0664] 5. Finalist selection and entry process assistance:

[0665] Terminal: The re-evaluated candidate list is displayed to the user. The user selects a final job and enters information to indicate their intention to apply. The application information is converted to JSON format and sent to the server.

[0666] Server: Analyzes entry information, sends it to related companies to assist with entry procedures, manages entry status, and provides feedback to users.

[0667] As a result, this system helps users efficiently apply to companies that meet their desired criteria. As a specific example, when the above prompt sentence is passed to the generative AI model, the generated list of companies can be used to smoothly advance the user's job search.

[0668] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0669] Step 1:

[0670] Input of user's desired conditions

[0671] Terminal: When the user logs in, a screen for inputting desired conditions is displayed. The user enters desired conditions such as salary, industry, type of business, company size, area, and employee benefits in the displayed form. The input is validated in real time, and an error message is displayed immediately if there are any omissions or errors.

[0672] input:

[0673] The desired conditions entered by the user in the form (e.g. salary, industry, area, etc.)

[0674] output:

[0675] Desired conditions data converted to JSON format

[0676] Specific behavior:

[0677] When the user completes the input, the submit button is activated. When the user presses the submit button, the input data is converted to JSON format and sent to the server as an HTTP request.

[0678] Step 2:

[0679] Initial candidate list generation

[0680] Server: Parses the received JSON-formatted desired conditions data and extracts them as key-value pairs. Next, it queries the big database to search for company information that matches the desired conditions. The search results are input as prompts to the generative AI model, and an initial candidate list is generated.

[0681] input:

[0682] JSON data containing the user's preferences

[0683] output:

[0684] Initial candidate list in JSON format

[0685] Specific behavior:

[0686] The server uses a parsing library to parse the JSON data. It then issues an SQL or NoSQL query to retrieve company information that matches the desired criteria from the database. The retrieved data is input to the generative AI model in the form of a prompt statement, which generates an initial candidate list. The generated list is then converted to JSON format and sent back to the device.

[0687] Step 3:

[0688] View candidate lists and receive feedback

[0689] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted into JSON format and sent to the server.

[0690] input:

[0691] Initial candidate list received from the server

[0692] User-entered feedback and additional requirements

[0693] output:

[0694] Feedback data in JSON format

[0695] Specific behavior:

[0696] The device parses the initial candidate list received from the server and displays it in the user interface. Once the user has entered their feedback and additional preferences, the device converts this into JSON format and sends it to the server.

[0697] Step 4:

[0698] Reevaluate and update the candidate list

[0699] Server: Analyzes the received feedback and JSON data for additional conditions, and re-evaluates it using the generative AI model. Passes a new prompt to the generative AI model to narrow down the candidate list. Converts the re-evaluated candidate list into JSON format and sends it to the device.

[0700] input:

[0701] JSON data of feedback received from users and additional conditions

[0702] output:

[0703] Re-evaluated candidate list in JSON format

[0704] Specific behavior:

[0705] The server analyzes the feedback and additional conditions and generates a new prompt. Example prompt: "Please reevaluate the candidate list based on the following feedback and additional conditions: fully compatible with remote work, work that utilizes English." This prompt is input into the generative AI model, which generates a reevaluated candidate list. The reevaluated list is converted into JSON format and sent back to the device.

[0706] Step 5:

[0707] Selection of finalists and assistance with application procedures

[0708] Terminal: Parses the re-evaluated candidate list received from the server and displays it to the user. The user selects the final job and enters application information. The application information is converted to JSON format and sent to the server.

[0709] input:

[0710] Re-evaluated candidate list received from the server

[0711] Entry information entered by the user

[0712] output:

[0713] Entry information in JSON format

[0714] Specific behavior:

[0715] The device parses the re-evaluated candidate list and displays it in a user-friendly format. Once the user makes their final selection and enters their entry information, the information is converted to JSON format and sent to the server.

[0716] Step 6:

[0717] Entry status management and feedback

[0718] Server: Analyzes the received entry information and sends it to the relevant companies. Manages the entry process and provides feedback to users on the status.

[0719] input:

[0720] JSON data of the entry information received from the user

[0721] output:

[0722] Feedback information regarding the status of the entry process

[0723] Specific behavior:

[0724] The server analyzes the entry information and sends the necessary data to the relevant companies via API, email, etc. The progress of the entry is monitored in real time and feedback is sent to the user's device. This feedback includes whether the entry was accepted and instructions for the next step.

[0725] (Application example 1)

[0726] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0727] In conventional job-hunting systems, even if users input their desired conditions, it can be difficult to efficiently find suitable employers based on those conditions. Furthermore, the time and effort required to gather company information and complete application procedures can make job hunting a burden for users. In particular, with the introduction of remote work and the growing need for virtual interviews, traditional methods present challenges that cannot be fully addressed. To address these challenges, the present invention provides a system that quickly and efficiently suggests optimal employers based on users' desired conditions and also supports interviews and browsing of company information in a virtual space.

[0728] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0729] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, means for supporting the application process to the finally selected company, and means for viewing company information in a virtual space and virtually experiencing interviews and job hunting. This enables users to efficiently find jobs that meet their desired conditions and smoothly conduct their job search by viewing company information and conducting interviews in a virtual space.

[0730] The "means for inputting desired conditions" is an interface that allows users to input their desired employment conditions, such as salary, industry, work location, and work style.

[0731] The "means for generating an initial candidate list" is a function for generating a list of suitable candidate companies at an early stage based on the desired conditions entered by the user.

[0732] The "means for displaying the initial candidate list and receiving feedback and additional conditions from the user" is a mechanism for displaying the generated initial candidate list to the user and accepting opinions and input of additional items from the user.

[0733] "Means to reevaluate and update candidate list" refers to the functionality to reevaluate the initial candidate list based on feedback received from users and additional criteria, and update the list as needed to reflect new information.

[0734] The "means for displaying the re-evaluated candidate list and accepting a final selection from the user" refers to an interface for presenting the updated candidate list to the user again and accepting the user's final selection of the company.

[0735] "Means to support the application process to the final selected company" refers to a support function that helps the user smoothly go through the application process to the company they have selected, and supports them in entering the necessary information and submitting documents, etc.

[0736] "A means of viewing company information in a virtual space and virtually experiencing interviews and job interviews" is a function that allows users to use smart glasses or a head-mounted display to check company information in a virtual environment and virtually experience interviews and job interviews.

[0737] The system of the present invention is designed to enable users to efficiently conduct job hunting, and to achieve this, it uses smart glasses and a head-mounted display to provide an experience in a virtual space.

[0738] 1. System Configuration

[0739] The system consists of the following main components:

[0740] Terminal: A device that provides an interface for users to input their desired conditions, view company information, and conduct interviews and job interviews in a virtual space. Examples of this include smart glasses and head-mounted displays.

[0741] Server: A central control unit that analyzes preferences, generates and updates candidate lists, processes feedback, and assists with the entry process.

[0742] Generative AI model: An algorithm that uses OpenAI's API to suggest suitable companies based on the user's desired criteria.

[0743] 2. Program Overview

[0744] Below is an overview of the system's main functions: company proposals based on the user's desired conditions and virtual interview functions.

[0745] Input and analysis of desired conditions

[0746] The user enters their desired job search conditions from their device, including salary, industry, work location, and work style. The entered information is converted into JSON format and sent to the server.

[0747] Generate and display candidate lists

[0748] The server analyzes the received requirements and searches for relevant company information in a big database. It then uses a generative AI model to create an initial candidate list and sends it to the device. The device then displays it to the user and accepts feedback and additional requirements.

[0749] Reevaluate and update the candidate list

[0750] After receiving user feedback, the server re-evaluates and updates the candidate list using the generative AI model, which is then sent back to the device and displayed to the user.

[0751] Viewing company information and conducting interviews in a virtual space

[0752] Users can enter the virtual space by wearing smart glasses or a head-mounted display and check detailed information about companies. Interviews and job interviews can also be conducted in the virtual space. This allows users to conduct job hunting remotely without having to visit a company in person.

[0753] 3. Examples and prompts

[0754] As a specific use case, the following shows how a user inputs their desired conditions in a virtual space and the generative AI model suggests suitable companies.

[0755] Example prompt sentence:

[0756] Use a generative AI model to generate a list of companies that meet the following criteria:

[0757] Salary: 4 million yen or more

[0758] Industry: IT industry

[0759] Area: Tokyo

[0760] Working style:Remote work available

[0761] By sending this prompt to the system, a list of companies that match the user's desired criteria is automatically generated, allowing the user to proceed with their job search efficiently and effectively.

[0762] The above is an embodiment of the present invention.

[0763] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0764] Step 1:

[0765] Enter your desired criteria and submit:

[0766] Users log in to the virtual space using smart glasses or a head-mounted display. A desired conditions input screen is displayed, and the user inputs conditions such as desired salary, industry, work location, and working style. The input information is converted to JSON format on the device and sent to the server.

[0767] Input: User's desired conditions (e.g. salary, industry, work location, work style)

[0768] Output: JSON format desired conditions data

[0769] Step 2:

[0770] Generate the initial candidate list:

[0771] The server analyzes the received JSON data and obtains the user's desired conditions. It then searches the big database to extract company information that matches the desired conditions. The search results are passed as input conditions to the generative AI model, which generates an initial candidate list. The generated initial candidate list is converted to JSON format and sent to the device.

[0772] Input: JSON format desired conditions data

[0773] Data calculation: Big database search, initial candidate list generation using generative AI models

[0774] Output: Initial candidate list in JSON format

[0775] Step 3:

[0776] View initial candidate list and receive feedback:

[0777] The device parses the JSON data received from the server and displays an initial candidate list to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted to JSON format on the device and sent to the server.

[0778] Input: Initial candidate list in JSON format

[0779] Output: User feedback and additional conditions (JSON format)

[0780] Step 4:

[0781] Reevaluate and update the candidate list:

[0782] The server parses the received feedback and additional conditions in JSON data and re-evaluates them using the generative AI model. The re-evaluated candidate list is converted into JSON format and sent to the device. The device then displays the updated candidate list to the user.

[0783] Input: Feedback and additional conditions data in JSON format

[0784] Data Computing: Reevaluating and Updating Candidate Lists with Generative AI Models

[0785] Output: Updated candidate list in JSON format

[0786] Step 5:

[0787] Finalist selection and entry assistance:

[0788] The user selects a final employer from the updated candidate list and indicates their intention to apply. The device displays a form and links for collecting application information for the final candidate companies. The application information entered by the user is converted to JSON format on the device and sent to the server. The server analyzes the application information and sends the necessary information to the relevant companies to complete the application process.

[0789] Input: Updated candidate list in JSON format

[0790] Output: User entry information (JSON format)

[0791] Step 6:

[0792] Virtual company information viewing and interviews:

[0793] Users wear smart glasses or a head-mounted display and can view company information in a virtual space. They can also access company booths, view presentation videos and detailed company information, and virtually experience interviews and job interviews in the virtual space.

[0794] Input: Company information in virtual space

[0795] Output: Company information browsing results and interview experience

[0796] The above are the specific processing steps of the system that realizes this application example. This processing flow allows users to consistently conduct their job search efficiently and effectively.

[0797] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0798] ---

[0799] The system of the present invention not only proposes optimal employment opportunities based on the user's desired conditions and supports the application process, but also realizes more accurate job hunting by combining it with an emotion engine that recognizes the user's emotions. The following explains the overall processing flow of the system and a specific example.

[0800] 1. User preference input and emotion recognition

[0801] Device:

[0802] When a user logs in, a screen for entering desired conditions is displayed.

[0803] Users enter their desired conditions, such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[0804] user:

[0805] When users input their desired conditions, the device's emotion engine analyzes their facial expressions and voice to collect emotional data.

[0806] Device:

[0807] The emotion data along with the entered desired conditions is converted into JSON format and sent to the server.

[0808] 2. Initial candidate list generation and use of emotion data

[0809] server:

[0810] The received JSON data of desired conditions and emotional data is analyzed to extract the user's desired conditions.

[0811] Use a big database to search for company information that matches your desired criteria.

[0812] Search results are fed into a generative AI model, which takes sentiment data into account when generating an initial candidate list.

[0813] The initial candidate list is converted into JSON format and sent to the terminal.

[0814] 3. View candidate lists and receive feedback

[0815] Device:

[0816] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user.

[0817] user:

[0818] While reviewing the displayed list of candidates, users can enter their feedback and any additional requirements for each company. The emotion engine also collects their emotions when providing feedback.

[0819] Device:

[0820] User feedback, additional conditions, and collected emotional data are converted into JSON format and sent to the server.

[0821] 4. Reevaluate and update the candidate list

[0822] server:

[0823] Parse the JSON data for received feedback, additional conditions, and sentiment data.

[0824] A generative AI model is used to re-evaluate the initial candidate list based on feedback, additional criteria, and sentiment data to generate an updated candidate list.

[0825] The updated candidate list is converted into JSON format and sent to the terminal.

[0826] 5. Finalist selection and use of sentiment data

[0827] Device:

[0828] Display the updated candidate list to the user.

[0829] user:

[0830] The final job is selected from the updated candidate list. During the selection process, the emotion engine recognizes the user's emotions and collects the data.

[0831] Device:

[0832] An information form or link is displayed for the user to enter the final candidate selected by the user, and the user enters the required information.

[0833] Emotion data is also sent to the server together with the entered entry information.

[0834] 6. Entry procedure support and use of emotion data

[0835] server:

[0836] The received entry information and emotional data are analyzed, and the entry process is carried out with the relevant companies.

[0837] The necessary information will be sent to related companies to provide optimal support for application procedures based on emotional data.

[0838] Manage entry status and provide feedback to users.

[0839] Specific examples

[0840] For example, if a user enters their desired conditions as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system will take this into account when creating an initial candidate list. Upon feedback, the system will add more detailed conditions, such as "fully remote work-enabled, work that utilizes English," and re-evaluate the results using the emotion engine data to present the optimal candidate list. The system will then support a more effective application process based on the emotion data from the final selection.

[0841] ---

[0842] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, thereby realizing more personalized job suggestions and application procedures, allowing users to efficiently find the job that best suits them and conducting a highly satisfying job search.

[0843] The processing flow will be explained below.

[0844] ---

[0845] Step 1:

[0846] user:

[0847] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[0848] Device:

[0849] When a user enters their desired conditions, the emotion engine analyzes their facial expressions and voice to collect emotional data. The entered desired conditions and emotional data are converted into JSON format and sent to the server.

[0850] Step 2:

[0851] server:

[0852] The system analyzes the received JSON data of desired conditions and emotion data to extract the user's desired conditions. It uses a big database to search for company information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list based on the search results and emotion data. It converts the initial candidate list into JSON format and sends it to the device.

[0853] Step 3:

[0854] Device:

[0855] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[0856] user:

[0857] Review the displayed list of candidates and enter your feedback and additional requirements for each company. As you enter your feedback and additional requirements, the emotion engine will collect your emotional data.

[0858] Device:

[0859] User feedback, additional conditions, and emotional data are converted into JSON format and sent to the server.

[0860] Step 4:

[0861] server:

[0862] Parse the received feedback, additional conditions, and emotional data in JSON format. Use the generative AI model to re-evaluate the candidate list based on the feedback, additional conditions, and emotional data, and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[0863] Step 5:

[0864] Device:

[0865] The update candidate list received from the server is analyzed and displayed to the user.

[0866] user:

[0867] The final job is selected from the updated candidate list. At the time of the final selection, the emotion engine recognizes the user's emotions and collects the data.

[0868] Device:

[0869] It displays a form and link for the user to apply to the final candidate company of their choice. The user enters the necessary information, and the application information and emotion data are converted into JSON format and sent to the server.

[0870] Step 6:

[0871] server:

[0872] The system analyzes the received entry information and emotion data. It sends the necessary information to the relevant companies to complete the entry process. It provides optimal support for the entry process based on the emotion data, manages the entry status, and provides feedback to the user.

[0873] ---

[0874] In this way, by performing specific operations at each processing step, a system is realized that takes into account the user's emotions and provides more personalized job candidate suggestions and procedural support.

[0875] Example 2

[0876] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0877] Conventional job-hunting support systems suggested candidate companies based on the user's desired conditions, but did not consider the user's feelings when suggesting candidate companies. As a result, it was difficult for users to find the best job, and they were unable to achieve a satisfying job-hunting experience. In addition, it was difficult to effectively reflect received feedback and additional conditions, and there was also the problem of candidate lists not being updated sufficiently.

[0878] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input desired conditions, means for analyzing the user's facial expressions and voice to collect emotional data, means for transmitting the input desired conditions and emotional data to the server, means for generating an initial candidate list based on the user's desired conditions and emotional data, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the received feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, and means for supporting the application process to the finally selected company. This enables more personalized job suggestions and support that take into account not only the user's desired conditions but also their emotions.

[0879] "User's desired conditions" refers to the conditions the user desires for employment, such as salary, industry, type of business, company size, area, and working style.

[0880] "Emotional data" refers to data that indicates the user's emotional state (e.g., joy, surprise, anxiety, etc.) obtained by analyzing the user's facial expressions and voice.

[0881] "Initial candidate list" refers to a list of candidate companies presented to a user, generated based on the user's desired conditions and emotional data.

[0882] "Feedback" refers to the opinions, ratings, and additional preferences provided by the user regarding the displayed list of candidate companies.

[0883] "Re-evaluated Candidate List" refers to the list of candidate companies that have been re-evaluated and updated based on user feedback and additional criteria and sentiment data.

[0884] "Means to support the entry process" refers to functions that support the procedures required when a user applies to the company they have finally selected (such as filling out information forms and submitting required documents).

[0885] "Big database" refers to a database system (e.g., Google Cloud BigQuery, Amazon Redshift) for efficiently managing and searching large amounts of data.

[0886] "Generative AI model" refers to a model (e.g., ChatGPT) that uses artificial intelligence techniques to generate and update candidate lists.

[0887] The system of the present invention proposes optimal job opportunities based on the user's desired conditions and supports the application process. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system achieves more accurate job hunting. Specific embodiments of the present invention are described in detail below.

[0888] System Overview

[0889] The system includes means for inputting user preferences, means for collecting sentiment data, means for generating an initial candidate list, means for receiving and re-evaluating feedback, means for receiving final selections, and means for assisting the entry process.

[0890] User preference input and emotion recognition

[0891] Device:

[0892] When a user logs in, a screen for entering desired conditions appears. The user enters their desired conditions, such as salary, industry, type of business, company size, location, and working style (e.g., remote work available). At this time, the device uses its built-in webcam and microphone to send the user's facial expressions and voice to an emotion engine, which collects emotional data in real time. The emotional data is analyzed using technologies such as "Affectiva" and "Microsoft Azure Emotion API."

[0893] Generating an initial candidate list

[0894] server:

[0895] The desired conditions and emotion data sent from the device are received and analyzed. Based on the analyzed data, a big database (e.g., Google Cloud BigQuery or Amazon Redshift) is used to search for company information that matches the user's desired conditions. The search results and emotion data are input into a generative AI model (e.g., ChatGPT) to generate an initial candidate list. A prompt such as "Please select companies in the IT industry in Tokyo where the user's desired salary is 4 million yen or more. The user has shown a high interest in remote work" is used.

[0896] View candidate lists and receive feedback

[0897] Device:

[0898] The initial candidate list sent from the server is analyzed and a list of candidates is displayed to the user. The user reviews the displayed candidate list and enters feedback and additional desired conditions for each company. The device also collects emotional data during this process. The collected feedback and emotional data are then sent back to the server.

[0899] Reevaluate and update the candidate list

[0900] server:

[0901] The received feedback and sentiment data is analyzed, and the initial candidate list is re-evaluated and updated using a generative AI model, using prompts such as "Users have a strong preference for full remote work support, so please focus on this." The re-evaluated candidate list is then sent to the device.

[0902] Finalist selection and entry procedures

[0903] Device:

[0904] The updated candidate list is displayed to the user. The user then selects the final employer. Emotional data is also collected during this process. An information form and link for applying to the final selected company are displayed, and the user enters the required information. The entered application information and emotional data are then sent to the server.

[0905] server:

[0906] Analyze the received entry information and emotion data and process the entry with the relevant companies. Send the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manage the entry status and provide feedback to the user.

[0907] Specific examples

[0908] When a user enters their desired conditions, such as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system takes this into account when creating an initial candidate list. If the user provides feedback and adds more detailed conditions, such as "full remote work support, work that utilizes English," the system reevaluates the results using the emotion engine data and presents the optimal candidate list. The system then supports a more effective application process based on the emotion data from the final selection.

[0909] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, allowing for more personalized job suggestions and application procedures, enabling users to efficiently find the job that best suits them and achieving a more satisfying job search experience.

[0910] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0911] Step 1:

[0912] User: When a user logs in, a screen for entering desired conditions is displayed on the device. The user enters desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed). The input information is saved on the device.

[0913] Input: User's desired criteria (e.g. salary, industry, business type, etc.).

[0914] Output: Generate data (e.g., JSON format) based on the desired conditions.

[0915] Step 2:

[0916] Device: The user's facial expressions and voice are collected in real time on the input screen using a webcam and microphone. The collected data is analyzed using an emotion engine (e.g., "Affectiva" or "Microsoft Azure Emotion API"). Emotional data (happiness, surprise, anxiety, etc.) is generated as a result of the analysis.

[0917] Input: User facial and voice data.

[0918] Output: Generate emotion data (e.g., JSON format).

[0919] Step 3:

[0920] Device: The desired conditions and emotional data are combined into a single JSON file and sent to the server. The combined data includes the user's desired conditions and emotional state.

[0921] Input: Desired condition data, emotion data.

[0922] Output: Consolidated preference and sentiment data in JSON format.

[0923] Step 4:

[0924] Server: Analyzes the received desired conditions and sentiment data to extract the user's desired conditions. Uses a big database (e.g., Google Cloud BigQuery or Amazon Redshift) to search for company information that matches the desired conditions. Filters the company information in the database using the search query.

[0925] Input: Integrated desire criteria and emotion data.

[0926] Output: Company information as search results.

[0927] Step 5:

[0928] Server: Input the search results and sentiment data into a generative AI model (e.g., "ChatGPT") to generate an initial candidate list. Input a prompt such as "The user's desired salary is 4 million yen or more, and please select companies in the IT industry in Tokyo. The user has a high interest in remote work." Create an initial candidate list as a result and convert it to JSON format.

[0929] Input: Search results, sentiment data.

[0930] Output: Initial candidate list (JSON format).

[0931] Step 6:

[0932] Terminal: Analyzes the initial candidate list received from the server and displays a list of candidates to the user. The displayed candidate list includes information about each company (e.g., salary, industry, location, etc.).

[0933] Input: Initial candidate list (JSON format).

[0934] Output: A candidate list that can be viewed by the user.

[0935] Step 7:

[0936] User: Review the list of candidates and enter feedback and additional desired conditions for each company. When providing feedback, the device also collects the user's facial expressions and voice, which are analyzed by the emotion engine. Additional emotional data is generated.

[0937] Input: Feedback on candidate list, facial expression and speech data.

[0938] Output: Feedback, additional conditions, and additional emotion data (JSON format).

[0939] Step 8:

[0940] Terminal: Collects feedback, additional conditions, and additional emotion data, integrates them into a single JSON data, and sends it to the server.

[0941] Input: Feedback, additional conditions, additional emotion data.

[0942] Output: Consolidated feedback data in JSON format.

[0943] Step 9:

[0944] Server: Analyzes the received feedback, additional conditions, and emotional data. The generative AI model is given another prompt, such as "The user strongly desires full remote work support, so please focus on this." This prompt reevaluates the initial candidate list and generates an updated candidate list. The updated candidate list is converted to JSON format and sent to the device.

[0945] Input: Feedback, additional conditions, emotional data.

[0946] Output: The updated candidate list in JSON format.

[0947] Step 10:

[0948] On the device: Show the updated candidate list to the user.

[0949] Input: The updated candidate list (in JSON format).

[0950] Output: An updated candidate list that can be viewed by the user.

[0951] Step 11:

[0952] User: Selects a final job from the updated candidate list. Emotional data is collected and analyzed during the selection process.

[0953] Input: Updated candidate list, facial expression and speech data.

[0954] Output: Final selection data, emotion data (JSON format).

[0955] Step 12:

[0956] Terminal: Displays an information form and link for the final candidates to enter, and the user enters the required information. The entered entry information and emotion data are sent to the server.

[0957] Input: Final selection data, input information, emotion data.

[0958] Output: Consolidated entry data (JSON format).

[0959] Step 13:

[0960] Server: Analyzes the received entry information and emotion data and carries out the entry process with the relevant companies. Sends the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manages the entry status and provides feedback to the user.

[0961] Input: Entry information, emotion data.

[0962] Output: Entry information to companies, feedback to users.

[0963] (Application example 2)

[0964] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0965] Conventional content recommendation systems generate candidate lists based on a user's desired conditions, but they are unable to consider the user's emotions and moods, making it difficult to recommend the optimal content that matches the user's current mood. Furthermore, because they update lists based only on user feedback and additional conditions, they lack an understanding of actual user experiences. Therefore, there is a need for a method to recommend more personalized content that takes into account the user's emotional data.

[0966] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0967] In this invention, the server includes an emotion recognition means for recognizing a user's emotion and collecting the data, a means for adjusting a candidate list based on the emotion data and desired conditions, a means for searching for information corresponding to the user's desired conditions using a big database, and a means for generating and updating the candidate list using a generative AI model. This makes it possible to dynamically provide optimal content for the user's emotional state and improve user satisfaction.

[0968] "Desired conditions" refers to the genre, keywords, format, etc. of the content the user wants to watch.

[0969] "Initial candidate list" refers to a list of content candidates generated based on the user's desired conditions.

[0970] "Feedback" refers to the ratings and opinions that users give to the displayed list of candidates.

[0971] "Additional Terms" refers to any further detailed desired terms provided by the User along with their Feedback.

[0972] "Emotion recognition means" refers to the function of analyzing the user's facial expressions and voice and recognizing their emotional state.

[0973] "Emotion Data" refers to data regarding a user's emotions collected by an emotion recognition means.

[0974] A "big database" refers to a database for storing and searching large amounts of data, such as users' viewing history, desired conditions, and emotional data.

[0975] "Generative AI model" refers to an artificial intelligence model that generates and updates optimal content candidate lists based on user preferences and emotional data.

[0976] "Entry Procedure" refers to the various procedures to facilitate access to and viewing of the Final Selected Content.

[0977] The present invention is a content recommendation system that uses an emotion recognition engine and provides optimal content based on a user's desired conditions and emotion data. The system of the present invention is implemented as follows.

[0978] System configuration

[0979] Hardware and software used

[0980] Smartphones / Smart Glasses / Head-Mounted Displays

[0981] Device camera: Collects user facial expression data.

[0982] Device microphone: Collects user voice data.

[0983] server

[0984] Big database: Stores user viewing history, preferences, and emotional data.

[0985] Generative AI model: Generates and updates a list of optimal content candidates based on desired conditions and sentiment data.

[0986] software

[0987] OpenCV (facial expression recognition)

[0988] TensorFlow (voice emotion recognition)

[0989] Flask (Server-side API construction)

[0990] Program processing

[0991] 1. Collect user requirements

[0992] Users launch the app on their smartphone, smart glasses, or head-mounted display and enter their desired content preferences.

[0993] The device camera and microphone collect emotion data from the user's facial expressions and voice, which is then converted into JSON format and sent to the server.

[0994] 2. Initial candidate list generation and use of emotion data

[0995] The server analyzes the received desired conditions and emotional data, searches a big database, and generates an initial candidate list.

[0996] The generative AI model takes into account emotional data and desired conditions to generate an optimal list of content candidates.

[0997] 3. View candidate lists and receive feedback

[0998] An initial candidate list is sent to the device and displayed to the user, who can then provide feedback or additional criteria.

[0999] User feedback, additional conditions, and newly collected emotional data are sent to the server.

[1000] 4. Reevaluate and update the candidate list

[1001] The server analyzes the feedback, additional conditions, and emotional data, and re-evaluates and updates the candidate list using a generative AI model.

[1002] The updated list is sent to the device and displayed to the user again.

[1003] 5. Selection of Finalists and Entry Procedure

[1004] The user selects the final content, and sentiment data is collected at the time of the final selection.

[1005] The necessary information for the entry procedure is displayed, and the entry procedure is supported.

[1006] Examples of concrete examples and prompts

[1007] Specific examples

[1008] The user inputs their preference for "action movies" and the emotion recognition engine simultaneously recognizes that the user is excited. Based on this information, the server generates a list of suitable action movies and provides them to the user. Emotional data is also continuously collected during viewing and used for subsequent recommendations.

[1009] Prompt Sentence Examples

[1010] "I recognize that the user is excited. Please generate a list of action movies. The desired criteria is 'action movies.'"

[1011] As a result, the system of the present invention dynamically recommends content taking into account not only the user's desired conditions but also emotional data, thereby significantly improving user satisfaction.

[1012] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1013] Program processing steps

[1014] Step 1:

[1015] The user enters their desired conditions and emotional data is collected.

[1016] Input: User's desired conditions (e.g. genre, keywords, etc.), facial expression data, voice data

[1017] Processing: The device displays a screen for entering desired conditions, and the user enters the conditions. The device also collects facial and voice data using the camera and microphone. The collected data is converted into JSON format.

[1018] Output: JSON formatted preference and emotion data sent to the server

[1019] Step 2:

[1020] Generate an initial candidate list.

[1021] Input: JSON formatted preference and emotion data

[1022] Processing: The server analyzes the received desired conditions and emotional data. It searches a big database to collect content information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list, taking into account the emotional data.

[1023] Output: Initial candidate list sent to the terminal

[1024] Step 3:

[1025] Present an initial list of candidates to the user and receive feedback and additional criteria.

[1026] Input: Initial candidate list

[1027] Processing: The device displays an initial list of candidates. The user can then enter feedback (e.g., a rating of good or bad) or additional criteria (e.g., a more detailed genre specification) based on the displayed list, and new emotional data is collected using the device's camera and microphone. This data is then converted back into JSON format.

[1028] Output: Feedback, additional conditions, and emotion data sent to the server

[1029] Step 4:

[1030] Reassess and update the candidate list.

[1031] Input: Feedback, additional conditions, emotional data

[1032] Processing: The server analyzes the received feedback, additional criteria, and sentiment data. It uses the generative AI model to re-evaluate the initial candidate list and generate an updated list.

[1033] Output: Updated candidate list sent to the terminal

[1034] Step 5:

[1035] The updated candidate list is displayed to the user and a final selection is accepted.

[1036] Input: Updated candidate list

[1037] Processing: The device displays the updated candidate list to the user, who then selects the final viewing content, collecting emotional data at the time of selection.

[1038] Output: Final selection results and emotion data sent to the server

[1039] Step 6:

[1040] Assist with the entry process.

[1041] Input: Final selection results and emotion data

[1042] Processing: The server analyzes the final selection results and emotion data, generates the necessary entry procedure information, and assists the user in completing the necessary viewing procedures.

[1043] Output: Final viewing instructions provided to the user

[1044] Through these steps, the content recommendation system of the present invention can dynamically recommend content that perfectly matches the user's emotional state, optimizing the user's viewing experience.

[1045] 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.

[1046] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1047] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1048] [Third embodiment]

[1049] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1050] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1051] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[1052] 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.

[1053] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1054] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1055] 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.

[1056] 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.

[1057] 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 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.

[1058] 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.

[1059] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1060] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[1061] ---

[1062] The system of the present invention proposes the most suitable employment based on the user's desired conditions and efficiently supports the procedures up to application. The flow of processing of the entire system and a specific example will be explained below.

[1063] 1. Enter the user's desired conditions

[1064] Device:

[1065] When a user logs in, a screen for entering desired conditions is displayed.

[1066] Users enter their desired conditions such as salary, industry, type of business, company size, area, and employee benefits.

[1067] Example: A user enters the following requirements:

[1068] Salary: 4 million yen or more

[1069] Industry: IT industry

[1070] Area: Tokyo

[1071] Working style:Remote work available

[1072] Device:

[1073] The entered desired conditions are converted into JSON format and sent to the server.

[1074] 2. Initial candidate list generation

[1075] server:

[1076] Analyze the received JSON data and obtain the user's desired conditions.

[1077] Search for company information that matches your desired criteria from a big database.

[1078] The search results are passed as input conditions to the generative AI model to generate an initial candidate list.

[1079] The initial candidate list is converted into JSON format and sent to the terminal.

[1080] Example: The server selects 20 companies out of 100 as initial candidates and sends the list to the terminal.

[1081] 3. View candidate lists and receive feedback

[1082] Device:

[1083] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user as a list.

[1084] user:

[1085] Review the shortlist and enter your feedback and any additional preferences for each company.

[1086] example:

[1087] The user enters additional conditions such as "fully compatible with remote work, work that allows the use of English."

[1088] Device:

[1089] User feedback and additional conditions are converted into JSON format and sent to the server.

[1090] 4. Reevaluate and update the candidate list

[1091] server:

[1092] Parse the JSON data for received feedback and additional conditions.

[1093] Use generative AI models to narrow down the shortlist by re-evaluating based on feedback and additional criteria.

[1094] The updated candidate list is converted into JSON format and sent to the terminal.

[1095] Example: The server narrows down the initial candidate list from 20 companies to 10 companies and sends the re-evaluated candidate list to the terminal.

[1096] 5. Selection of finalists and assistance with application procedures

[1097] Device:

[1098] Display the updated candidate list to the user.

[1099] user:

[1100] Select the final job from the updated candidate list.

[1101] Express your intention to apply to the selected employer.

[1102] Device:

[1103] Display a form or link to collect application information for finalist companies.

[1104] The entry information entered by the user is converted into JSON format and sent to the server.

[1105] server:

[1106] The received entry information will be analyzed and the information necessary to complete the entry process will be sent to the relevant company.

[1107] Manage entry status and provide feedback to users.

[1108] example:

[1109] The user initiates an application to the company they have finally selected, the device displays the necessary form, and the server then sends the application information to the selected company.

[1110] In this way, the system of the present invention can propose optimal employment opportunities based on the user's desired conditions and provide consistent support up to the application process, allowing users to efficiently advance their job search and making it easier for them to find a job that meets their needs.

[1111] ---

[1112] The processing flow will be explained below.

[1113] ---

[1114] Step 1:

[1115] user:

[1116] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[1117] Device:

[1118] Receives the entered desired conditions, converts them into JSON format data, and sends the converted JSON format data to the server.

[1119] Step 2:

[1120] server:

[1121] The received JSON data is analyzed to extract the user's desired conditions. A big database is used to search for company information that matches the desired conditions. The search results are input into the generative AI model to generate an initial candidate list. The generated initial candidate list is converted into JSON format and sent to the terminal.

[1122] Step 3:

[1123] Device:

[1124] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[1125] user:

[1126] Review the list of candidates displayed and enter your feedback and any additional requirements for each company.

[1127] Device:

[1128] Receives feedback and additional conditions from the user, converts them into JSON format, and sends them to the server.

[1129] Step 4:

[1130] server:

[1131] Parse the JSON data of the received feedback and additional conditions. Use the generative AI model to reevaluate the initial candidate list based on the feedback and additional conditions and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[1132] Step 5:

[1133] Device:

[1134] The update candidate list received from the server is analyzed and displayed to the user.

[1135] user:

[1136] Select the final employer from the updated candidate list that is displayed. Indicate your intention to apply to the selected employer.

[1137] Device:

[1138] It displays an information form and link for the user to submit an entry for the final candidate they have selected. It receives the entry information entered by the user, converts it into JSON format, and sends it to the server.

[1139] Step 6:

[1140] server:

[1141] Analyze the received entry information. Send the necessary information to the relevant companies to process the entry. Monitor the entry status and provide feedback to the user.

[1142] ---

[1143] In this way, by performing specific actions at each step, users can efficiently find the best job based on their desired conditions and can also complete the application process smoothly.

[1144] Example 1

[1145] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1146] Previous job-hunting support systems lacked the efficiency to find companies that matched users' desired conditions, and the process for evaluating and updating candidate lists was insufficient, resulting in users spending a lot of time and effort finding the job they wanted.Furthermore, the application process lacked consistency and efficiency, placing a heavy burden on users when applying to each company.

[1147] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1148] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for analyzing the received feedback and additional conditions and re-evaluating the candidate list, means for updating the re-evaluated candidate list, means for displaying the re-evaluated candidate list and accepting a final selection from the user, and means for supporting the application procedure to the finally selected company. This enables users to efficiently and effectively find their desired job and simplifies the application procedure.

[1149] "Desired conditions" refers to the specific requirements and wishes that a user has for a job, such as salary, industry, type of business, company size, area, and employee benefits.

[1150] An "initial candidate list" refers to a list of multiple companies that is initially generated based on the user's desired conditions.

[1151] "Feedback" refers to the opinions, ratings, and additional requirements that users provide regarding the initial candidate list.

[1152] "Re-evaluated shortlist" refers to the list of companies that have been re-evaluated and filtered based on user feedback and additional criteria.

[1153] A "big database" refers to a database that stores a large amount of company information, and is used by job support systems to search for company information based on users' desired conditions.

[1154] "Generative AI model" refers to a model that uses artificial intelligence techniques to generate and update initial and reevaluated candidate lists, for example, by utilizing natural language processing or machine learning techniques.

[1155] A "prompt" is a text sentence that is input to a generative AI model to obtain a specific output, and includes the user's desired conditions and feedback.

[1156] "Application procedure support" refers to the process of supporting users to effectively apply to the company of their choice, including providing application forms and submitting required information.

[1157] MODE FOR CARRYING OUT THE INVENTION

[1158] The system of the present invention proposes suitable employment opportunities based on the user's desired employment conditions and efficiently supports the application process. This system effectively finds companies that match the user's preferences using a server, terminals, a generative AI model, and a big database.

[1159] Specific hardware and software used:

[1160] Server: A server capable of high-performance data processing and AI model execution

[1161] Device: The device used by the user, such as a PC, smartphone, or tablet

[1162] Database: A big database that stores corporate information (e.g., MongoDB or PostgreSQL)

[1163] Generative AI models: AI models capable of natural language processing and data analysis (e.g., "OpenAI GPT-4")

[1164] Program processing

[1165] 1. Enter your desired conditions:

[1166] Terminal: After the user logs in, a screen for inputting desired conditions is displayed. The user fills in the input form with desired conditions such as salary, industry, type of business, company size, area, and employee benefits. The input conditions are validated in real time, converted to JSON format, and sent to the server.

[1167] 2. Generate initial candidate list:

[1168] Server: Analyzes the received JSON data and extracts the user's desired conditions. Then, retrieves company information that matches the conditions from a big database and inputs the conditions as prompts into the generative AI model to generate an initial candidate list.

[1169] Example prompt: "Generate a list of companies that meet the following criteria: salary over ¥4 million, industry IT, location Tokyo, work style remote work available."

[1170] The generated initial candidate list is also converted into JSON format and sent to the terminal.

[1171] 3. View candidate list and receive feedback:

[1172] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted back to JSON format and sent to the server.

[1173] 4. Reevaluate and update the candidate list:

[1174] Server: Analyzes the received feedback and additional conditions, re-evaluates and narrows down the candidate list using the generative AI model, converts the re-evaluated candidate list into JSON format, and sends it to the device.

[1175] Example prompt: "Please reassess your shortlist based on the following feedback and additional criteria: Fully remote-friendly, English-speaking roles."

[1176] 5. Finalist selection and entry process assistance:

[1177] Terminal: The re-evaluated candidate list is displayed to the user. The user selects a final job and enters information to indicate their intention to apply. The application information is converted to JSON format and sent to the server.

[1178] Server: Analyzes entry information, sends it to related companies to assist with entry procedures, manages entry status, and provides feedback to users.

[1179] As a result, this system helps users efficiently apply to companies that meet their desired criteria. As a specific example, when the above prompt sentence is passed to the generative AI model, the generated list of companies can be used to smoothly advance the user's job search.

[1180] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1181] Step 1:

[1182] Input of user's desired conditions

[1183] Terminal: When the user logs in, a screen for inputting desired conditions is displayed. The user enters desired conditions such as salary, industry, type of business, company size, area, and employee benefits in the displayed form. The input is validated in real time, and an error message is displayed immediately if there are any omissions or errors.

[1184] input:

[1185] The desired conditions entered by the user in the form (e.g. salary, industry, area, etc.)

[1186] output:

[1187] Desired conditions data converted to JSON format

[1188] Specific behavior:

[1189] When the user completes the input, the submit button is activated. When the user presses the submit button, the input data is converted to JSON format and sent to the server as an HTTP request.

[1190] Step 2:

[1191] Initial candidate list generation

[1192] Server: Parses the received JSON-formatted desired conditions data and extracts them as key-value pairs. Next, it queries the big database to search for company information that matches the desired conditions. The search results are input as prompts to the generative AI model, and an initial candidate list is generated.

[1193] input:

[1194] JSON data containing the user's preferences

[1195] output:

[1196] Initial candidate list in JSON format

[1197] Specific behavior:

[1198] The server uses a parsing library to parse the JSON data. It then issues an SQL or NoSQL query to retrieve company information that matches the desired criteria from the database. The retrieved data is input to the generative AI model in the form of a prompt statement, which generates an initial candidate list. The generated list is then converted to JSON format and sent back to the device.

[1199] Step 3:

[1200] View candidate lists and receive feedback

[1201] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted into JSON format and sent to the server.

[1202] input:

[1203] Initial candidate list received from the server

[1204] User-entered feedback and additional requirements

[1205] output:

[1206] Feedback data in JSON format

[1207] Specific behavior:

[1208] The device parses the initial candidate list received from the server and displays it in the user interface. Once the user has entered their feedback and additional preferences, the device converts this into JSON format and sends it to the server.

[1209] Step 4:

[1210] Reevaluate and update the candidate list

[1211] Server: Analyzes the received feedback and JSON data for additional conditions, and re-evaluates it using the generative AI model. Passes a new prompt to the generative AI model to narrow down the candidate list. Converts the re-evaluated candidate list into JSON format and sends it to the device.

[1212] input:

[1213] JSON data of feedback received from users and additional conditions

[1214] output:

[1215] Re-evaluated candidate list in JSON format

[1216] Specific behavior:

[1217] The server analyzes the feedback and additional conditions and generates a new prompt. Example prompt: "Please reevaluate the candidate list based on the following feedback and additional conditions: fully compatible with remote work, work that utilizes English." This prompt is input into the generative AI model, which generates a reevaluated candidate list. The reevaluated list is converted into JSON format and sent back to the device.

[1218] Step 5:

[1219] Selection of finalists and assistance with application procedures

[1220] Terminal: Parses the re-evaluated candidate list received from the server and displays it to the user. The user selects the final job and enters application information. The application information is converted to JSON format and sent to the server.

[1221] input:

[1222] Re-evaluated candidate list received from the server

[1223] Entry information entered by the user

[1224] output:

[1225] Entry information in JSON format

[1226] Specific behavior:

[1227] The device parses the re-evaluated candidate list and displays it in a user-friendly format. Once the user makes their final selection and enters their entry information, the information is converted to JSON format and sent to the server.

[1228] Step 6:

[1229] Entry status management and feedback

[1230] Server: Analyzes the received entry information and sends it to the relevant companies. Manages the entry process and provides feedback to users on the status.

[1231] input:

[1232] JSON data of the entry information received from the user

[1233] output:

[1234] Feedback information regarding the status of the entry process

[1235] Specific behavior:

[1236] The server analyzes the entry information and sends the necessary data to the relevant companies via API, email, etc. The progress of the entry is monitored in real time and feedback is sent to the user's device. This feedback includes whether the entry was accepted and instructions for the next step.

[1237] (Application example 1)

[1238] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1239] In conventional job-hunting systems, even if users input their desired conditions, it can be difficult to efficiently find suitable employers based on those conditions. Furthermore, the time and effort required to gather company information and complete application procedures can make job hunting a burden for users. In particular, with the introduction of remote work and the growing need for virtual interviews, traditional methods present challenges that cannot be fully addressed. To address these challenges, the present invention provides a system that quickly and efficiently suggests optimal employers based on users' desired conditions and also supports interviews and browsing of company information in a virtual space.

[1240] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1241] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, means for supporting the application process to the finally selected company, and means for viewing company information in a virtual space and virtually experiencing interviews and job hunting. This enables users to efficiently find jobs that meet their desired conditions and smoothly conduct their job search by viewing company information and conducting interviews in a virtual space.

[1242] The "means for inputting desired conditions" is an interface that allows users to input their desired employment conditions, such as salary, industry, work location, and work style.

[1243] The "means for generating an initial candidate list" is a function for generating a list of suitable candidate companies at an early stage based on the desired conditions entered by the user.

[1244] The "means for displaying the initial candidate list and receiving feedback and additional conditions from the user" is a mechanism for displaying the generated initial candidate list to the user and accepting opinions and input of additional items from the user.

[1245] "Means to reevaluate and update candidate list" refers to the functionality to reevaluate the initial candidate list based on feedback received from users and additional criteria, and update the list as needed to reflect new information.

[1246] The "means for displaying the re-evaluated candidate list and accepting a final selection from the user" refers to an interface for presenting the updated candidate list to the user again and accepting the user's final selection of the company.

[1247] "Means to support the application process to the final selected company" refers to a support function that helps the user smoothly go through the application process to the company they have selected, and supports them in entering the necessary information and submitting documents, etc.

[1248] "A means of viewing company information in a virtual space and virtually experiencing interviews and job interviews" is a function that allows users to use smart glasses or a head-mounted display to check company information in a virtual environment and virtually experience interviews and job interviews.

[1249] The system of the present invention is designed to enable users to efficiently conduct job hunting, and to achieve this, it uses smart glasses and a head-mounted display to provide an experience in a virtual space.

[1250] 1. System Configuration

[1251] The system consists of the following main components:

[1252] Terminal: A device that provides an interface for users to input their desired conditions, view company information, and conduct interviews and job interviews in a virtual space. Examples of this include smart glasses and head-mounted displays.

[1253] Server: A central control unit that analyzes preferences, generates and updates candidate lists, processes feedback, and assists with the entry process.

[1254] Generative AI model: An algorithm that uses OpenAI's API to suggest suitable companies based on the user's desired criteria.

[1255] 2. Program Overview

[1256] Below is an overview of the system's main functions: company proposals based on the user's desired conditions and virtual interview functions.

[1257] Input and analysis of desired conditions

[1258] The user enters their desired job search conditions from their device, including salary, industry, work location, and work style. The entered information is converted into JSON format and sent to the server.

[1259] Generate and display candidate lists

[1260] The server analyzes the received requirements and searches for relevant company information in a big database. It then uses a generative AI model to create an initial candidate list and sends it to the device. The device then displays it to the user and accepts feedback and additional requirements.

[1261] Reevaluate and update the candidate list

[1262] After receiving user feedback, the server re-evaluates and updates the candidate list using the generative AI model, which is then sent back to the device and displayed to the user.

[1263] Viewing company information and conducting interviews in a virtual space

[1264] Users can enter the virtual space by wearing smart glasses or a head-mounted display and check detailed information about companies. Interviews and job interviews can also be conducted in the virtual space. This allows users to conduct job hunting remotely without having to visit a company in person.

[1265] 3. Examples and prompts

[1266] As a specific use case, the following shows how a user inputs their desired conditions in a virtual space and the generative AI model suggests suitable companies.

[1267] Example prompt sentence:

[1268] Use a generative AI model to generate a list of companies that meet the following criteria:

[1269] Salary: 4 million yen or more

[1270] Industry: IT industry

[1271] Area: Tokyo

[1272] Working style:Remote work available

[1273] By sending this prompt to the system, a list of companies that match the user's desired criteria is automatically generated, allowing the user to proceed with their job search efficiently and effectively.

[1274] The above is an embodiment of the present invention.

[1275] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1276] Step 1:

[1277] Enter your desired criteria and submit:

[1278] Users log in to the virtual space using smart glasses or a head-mounted display. A desired conditions input screen is displayed, and the user inputs conditions such as desired salary, industry, work location, and working style. The input information is converted to JSON format on the device and sent to the server.

[1279] Input: User's desired conditions (e.g. salary, industry, work location, work style)

[1280] Output: JSON format desired conditions data

[1281] Step 2:

[1282] Generate the initial candidate list:

[1283] The server analyzes the received JSON data and obtains the user's desired conditions. It then searches the big database to extract company information that matches the desired conditions. The search results are passed as input conditions to the generative AI model, which generates an initial candidate list. The generated initial candidate list is converted to JSON format and sent to the device.

[1284] Input: JSON format desired conditions data

[1285] Data calculation: Big database search, initial candidate list generation using generative AI models

[1286] Output: Initial candidate list in JSON format

[1287] Step 3:

[1288] View initial candidate list and receive feedback:

[1289] The device parses the JSON data received from the server and displays an initial candidate list to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted to JSON format on the device and sent to the server.

[1290] Input: Initial candidate list in JSON format

[1291] Output: User feedback and additional conditions (JSON format)

[1292] Step 4:

[1293] Reevaluate and update the candidate list:

[1294] The server parses the received feedback and additional conditions in JSON data and re-evaluates them using the generative AI model. The re-evaluated candidate list is converted into JSON format and sent to the device. The device then displays the updated candidate list to the user.

[1295] Input: Feedback and additional conditions data in JSON format

[1296] Data Computing: Reevaluating and Updating Candidate Lists with Generative AI Models

[1297] Output: Updated candidate list in JSON format

[1298] Step 5:

[1299] Finalist selection and entry assistance:

[1300] The user selects a final employer from the updated candidate list and indicates their intention to apply. The device displays a form and links for collecting application information for the final candidate companies. The application information entered by the user is converted to JSON format on the device and sent to the server. The server analyzes the application information and sends the necessary information to the relevant companies to complete the application process.

[1301] Input: Updated candidate list in JSON format

[1302] Output: User entry information (JSON format)

[1303] Step 6:

[1304] Virtual company information viewing and interviews:

[1305] Users wear smart glasses or a head-mounted display and can view company information in a virtual space. They can also access company booths, view presentation videos and detailed company information, and virtually experience interviews and job interviews in the virtual space.

[1306] Input: Company information in virtual space

[1307] Output: Company information browsing results and interview experience

[1308] The above are the specific processing steps of the system that realizes this application example. This processing flow allows users to consistently conduct their job search efficiently and effectively.

[1309] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1310] ---

[1311] The system of the present invention not only proposes optimal employment opportunities based on the user's desired conditions and supports the application process, but also realizes more accurate job hunting by combining it with an emotion engine that recognizes the user's emotions. The following explains the overall processing flow of the system and a specific example.

[1312] 1. User preference input and emotion recognition

[1313] Device:

[1314] When a user logs in, a screen for entering desired conditions is displayed.

[1315] Users enter their desired conditions, such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[1316] user:

[1317] When users input their desired conditions, the device's emotion engine analyzes their facial expressions and voice to collect emotional data.

[1318] Device:

[1319] The emotion data along with the entered desired conditions is converted into JSON format and sent to the server.

[1320] 2. Initial candidate list generation and use of emotion data

[1321] server:

[1322] The received JSON data of desired conditions and emotional data is analyzed to extract the user's desired conditions.

[1323] Use a big database to search for company information that matches your desired criteria.

[1324] Search results are fed into a generative AI model, which takes sentiment data into account when generating an initial candidate list.

[1325] The initial candidate list is converted into JSON format and sent to the terminal.

[1326] 3. View candidate lists and receive feedback

[1327] Device:

[1328] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user.

[1329] user:

[1330] While reviewing the displayed list of candidates, users can enter their feedback and any additional requirements for each company. The emotion engine also collects their emotions when providing feedback.

[1331] Device:

[1332] User feedback, additional conditions, and collected emotional data are converted into JSON format and sent to the server.

[1333] 4. Reevaluate and update the candidate list

[1334] server:

[1335] Parse the JSON data for received feedback, additional conditions, and sentiment data.

[1336] A generative AI model is used to re-evaluate the initial candidate list based on feedback, additional criteria, and sentiment data to generate an updated candidate list.

[1337] The updated candidate list is converted into JSON format and sent to the terminal.

[1338] 5. Finalist selection and use of sentiment data

[1339] Device:

[1340] Display the updated candidate list to the user.

[1341] user:

[1342] The final job is selected from the updated candidate list. During the selection process, the emotion engine recognizes the user's emotions and collects the data.

[1343] Device:

[1344] An information form or link is displayed for the user to enter the final candidate selected by the user, and the user enters the required information.

[1345] Emotion data is also sent to the server together with the entered entry information.

[1346] 6. Entry procedure support and use of emotion data

[1347] server:

[1348] The received entry information and emotional data are analyzed, and the entry process is carried out with the relevant companies.

[1349] The necessary information will be sent to related companies to provide optimal support for application procedures based on emotional data.

[1350] Manage entry status and provide feedback to users.

[1351] Specific examples

[1352] For example, if a user enters their desired conditions as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system will take this into account when creating an initial candidate list. Upon feedback, the system will add more detailed conditions, such as "fully remote work-enabled, work that utilizes English," and re-evaluate the results using the emotion engine data to present the optimal candidate list. The system will then support a more effective application process based on the emotion data from the final selection.

[1353] ---

[1354] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, thereby realizing more personalized job suggestions and application procedures, allowing users to efficiently find the job that best suits them and conducting a highly satisfying job search.

[1355] The processing flow will be explained below.

[1356] ---

[1357] Step 1:

[1358] user:

[1359] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[1360] Device:

[1361] When a user enters their desired conditions, the emotion engine analyzes their facial expressions and voice to collect emotional data. The entered desired conditions and emotional data are converted into JSON format and sent to the server.

[1362] Step 2:

[1363] server:

[1364] The system analyzes the received JSON data of desired conditions and emotion data to extract the user's desired conditions. It uses a big database to search for company information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list based on the search results and emotion data. It converts the initial candidate list into JSON format and sends it to the device.

[1365] Step 3:

[1366] Device:

[1367] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[1368] user:

[1369] Review the displayed list of candidates and enter your feedback and additional requirements for each company. As you enter your feedback and additional requirements, the emotion engine will collect your emotional data.

[1370] Device:

[1371] User feedback, additional conditions, and emotional data are converted into JSON format and sent to the server.

[1372] Step 4:

[1373] server:

[1374] Parse the received feedback, additional conditions, and emotional data in JSON format. Use the generative AI model to re-evaluate the candidate list based on the feedback, additional conditions, and emotional data, and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[1375] Step 5:

[1376] Device:

[1377] The update candidate list received from the server is analyzed and displayed to the user.

[1378] user:

[1379] The final job is selected from the updated candidate list. At the time of the final selection, the emotion engine recognizes the user's emotions and collects the data.

[1380] Device:

[1381] It displays a form and link for the user to apply to the final candidate company of their choice. The user enters the necessary information, and the application information and emotion data are converted into JSON format and sent to the server.

[1382] Step 6:

[1383] server:

[1384] The system analyzes the received entry information and emotion data. It sends the necessary information to the relevant companies to complete the entry process. It provides optimal support for the entry process based on the emotion data, manages the entry status, and provides feedback to the user.

[1385] ---

[1386] In this way, by performing specific operations at each processing step, a system is realized that takes into account the user's emotions and provides more personalized job candidate suggestions and procedural support.

[1387] Example 2

[1388] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1389] Conventional job-hunting support systems suggested candidate companies based on the user's desired conditions, but did not consider the user's feelings when suggesting candidate companies. As a result, it was difficult for users to find the best job, and they were unable to achieve a satisfying job-hunting experience. In addition, it was difficult to effectively reflect received feedback and additional conditions, and there was also the problem of candidate lists not being updated sufficiently.

[1390] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input desired conditions, means for analyzing the user's facial expressions and voice to collect emotional data, means for transmitting the input desired conditions and emotional data to the server, means for generating an initial candidate list based on the user's desired conditions and emotional data, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the received feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, and means for supporting the application process to the finally selected company. This enables more personalized job suggestions and support that take into account not only the user's desired conditions but also their emotions.

[1391] "User's desired conditions" refers to the conditions the user desires for employment, such as salary, industry, type of business, company size, area, and working style.

[1392] "Emotional data" refers to data that indicates the user's emotional state (e.g., joy, surprise, anxiety, etc.) obtained by analyzing the user's facial expressions and voice.

[1393] "Initial candidate list" refers to a list of candidate companies presented to a user, generated based on the user's desired conditions and emotional data.

[1394] "Feedback" refers to the opinions, ratings, and additional preferences provided by the user regarding the displayed list of candidate companies.

[1395] "Re-evaluated Candidate List" refers to the list of candidate companies that have been re-evaluated and updated based on user feedback and additional criteria and sentiment data.

[1396] "Means to support the entry process" refers to functions that support the procedures required when a user applies to the company they have finally selected (such as filling out information forms and submitting required documents).

[1397] "Big database" refers to a database system (e.g., Google Cloud BigQuery, Amazon Redshift) for efficiently managing and searching large amounts of data.

[1398] "Generative AI model" refers to a model (e.g., ChatGPT) that uses artificial intelligence techniques to generate and update candidate lists.

[1399] The system of the present invention proposes optimal job opportunities based on the user's desired conditions and supports the application process. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system achieves more accurate job hunting. Specific embodiments of the present invention are described in detail below.

[1400] System Overview

[1401] The system includes means for inputting user preferences, means for collecting sentiment data, means for generating an initial candidate list, means for receiving and re-evaluating feedback, means for receiving final selections, and means for assisting the entry process.

[1402] User preference input and emotion recognition

[1403] Device:

[1404] When a user logs in, a screen for entering desired conditions appears. The user enters their desired conditions, such as salary, industry, type of business, company size, location, and working style (e.g., remote work available). At this time, the device uses its built-in webcam and microphone to send the user's facial expressions and voice to an emotion engine, which collects emotional data in real time. The emotional data is analyzed using technologies such as "Affectiva" and "Microsoft Azure Emotion API."

[1405] Generating an initial candidate list

[1406] server:

[1407] The desired conditions and emotion data sent from the device are received and analyzed. Based on the analyzed data, a big database (e.g., Google Cloud BigQuery or Amazon Redshift) is used to search for company information that matches the user's desired conditions. The search results and emotion data are input into a generative AI model (e.g., ChatGPT) to generate an initial candidate list. A prompt such as "Please select companies in the IT industry in Tokyo where the user's desired salary is 4 million yen or more. The user has shown a high interest in remote work" is used.

[1408] View candidate lists and receive feedback

[1409] Device:

[1410] The initial candidate list sent from the server is analyzed and a list of candidates is displayed to the user. The user reviews the displayed candidate list and enters feedback and additional desired conditions for each company. The device also collects emotional data during this process. The collected feedback and emotional data are then sent back to the server.

[1411] Reevaluate and update the candidate list

[1412] server:

[1413] The received feedback and sentiment data is analyzed, and the initial candidate list is re-evaluated and updated using a generative AI model, using prompts such as "Users have a strong preference for full remote work support, so please focus on this." The re-evaluated candidate list is then sent to the device.

[1414] Finalist selection and entry procedures

[1415] Device:

[1416] The updated candidate list is displayed to the user. The user then selects the final employer. Emotional data is also collected during this process. An information form and link for applying to the final selected company are displayed, and the user enters the required information. The entered application information and emotional data are then sent to the server.

[1417] server:

[1418] Analyze the received entry information and emotion data and process the entry with the relevant companies. Send the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manage the entry status and provide feedback to the user.

[1419] Specific examples

[1420] When a user enters their desired conditions, such as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system takes this into account when creating an initial candidate list. If the user provides feedback and adds more detailed conditions, such as "full remote work support, work that utilizes English," the system reevaluates the results using the emotion engine data and presents the optimal candidate list. The system then supports a more effective application process based on the emotion data from the final selection.

[1421] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, allowing for more personalized job suggestions and application procedures, enabling users to efficiently find the job that best suits them and achieving a more satisfying job search experience.

[1422] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1423] Step 1:

[1424] User: When a user logs in, a screen for entering desired conditions is displayed on the device. The user enters desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed). The input information is saved on the device.

[1425] Input: User's desired criteria (e.g. salary, industry, business type, etc.).

[1426] Output: Generate data (e.g., JSON format) based on the desired conditions.

[1427] Step 2:

[1428] Device: The user's facial expressions and voice are collected in real time on the input screen using a webcam and microphone. The collected data is analyzed using an emotion engine (e.g., "Affectiva" or "Microsoft Azure Emotion API"). Emotional data (happiness, surprise, anxiety, etc.) is generated as a result of the analysis.

[1429] Input: User facial and voice data.

[1430] Output: Generate emotion data (e.g., JSON format).

[1431] Step 3:

[1432] Device: The desired conditions and emotional data are combined into a single JSON file and sent to the server. The combined data includes the user's desired conditions and emotional state.

[1433] Input: Desired condition data, emotion data.

[1434] Output: Consolidated preference and sentiment data in JSON format.

[1435] Step 4:

[1436] Server: Analyzes the received desired conditions and sentiment data to extract the user's desired conditions. Uses a big database (e.g., Google Cloud BigQuery or Amazon Redshift) to search for company information that matches the desired conditions. Filters the company information in the database using the search query.

[1437] Input: Integrated desire criteria and emotion data.

[1438] Output: Company information as search results.

[1439] Step 5:

[1440] Server: Input the search results and sentiment data into a generative AI model (e.g., "ChatGPT") to generate an initial candidate list. Input a prompt such as "The user's desired salary is 4 million yen or more, and please select companies in the IT industry in Tokyo. The user has a high interest in remote work." Create an initial candidate list as a result and convert it to JSON format.

[1441] Input: Search results, sentiment data.

[1442] Output: Initial candidate list (JSON format).

[1443] Step 6:

[1444] Terminal: Analyzes the initial candidate list received from the server and displays a list of candidates to the user. The displayed candidate list includes information about each company (e.g., salary, industry, location, etc.).

[1445] Input: Initial candidate list (JSON format).

[1446] Output: A candidate list that can be viewed by the user.

[1447] Step 7:

[1448] User: Review the list of candidates and enter feedback and additional desired conditions for each company. When providing feedback, the device also collects the user's facial expressions and voice, which are analyzed by the emotion engine. Additional emotional data is generated.

[1449] Input: Feedback on candidate list, facial expression and speech data.

[1450] Output: Feedback, additional conditions, and additional emotion data (JSON format).

[1451] Step 8:

[1452] Terminal: Collects feedback, additional conditions, and additional emotion data, integrates them into a single JSON data, and sends it to the server.

[1453] Input: Feedback, additional conditions, additional emotion data.

[1454] Output: Consolidated feedback data in JSON format.

[1455] Step 9:

[1456] Server: Analyzes the received feedback, additional conditions, and emotional data. The generative AI model is given another prompt, such as "The user strongly desires full remote work support, so please focus on this." This prompt reevaluates the initial candidate list and generates an updated candidate list. The updated candidate list is converted to JSON format and sent to the device.

[1457] Input: Feedback, additional conditions, emotional data.

[1458] Output: The updated candidate list in JSON format.

[1459] Step 10:

[1460] On the device: Show the updated candidate list to the user.

[1461] Input: The updated candidate list (in JSON format).

[1462] Output: An updated candidate list that can be viewed by the user.

[1463] Step 11:

[1464] User: Selects a final job from the updated candidate list. Emotional data is collected and analyzed during the selection process.

[1465] Input: Updated candidate list, facial expression and speech data.

[1466] Output: Final selection data, emotion data (JSON format).

[1467] Step 12:

[1468] Terminal: Displays an information form and link for the final candidates to enter, and the user enters the required information. The entered entry information and emotion data are sent to the server.

[1469] Input: Final selection data, input information, emotion data.

[1470] Output: Consolidated entry data (JSON format).

[1471] Step 13:

[1472] Server: Analyzes the received entry information and emotion data and carries out the entry process with the relevant companies. Sends the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manages the entry status and provides feedback to the user.

[1473] Input: Entry information, emotion data.

[1474] Output: Entry information to companies, feedback to users.

[1475] (Application example 2)

[1476] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1477] Conventional content recommendation systems generate candidate lists based on a user's desired conditions, but they are unable to consider the user's emotions and moods, making it difficult to recommend the optimal content that matches the user's current mood. Furthermore, because they update lists based only on user feedback and additional conditions, they lack an understanding of actual user experiences. Therefore, there is a need for a method to recommend more personalized content that takes into account the user's emotional data.

[1478] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1479] In this invention, the server includes an emotion recognition means for recognizing a user's emotion and collecting the data, a means for adjusting a candidate list based on the emotion data and desired conditions, a means for searching for information corresponding to the user's desired conditions using a big database, and a means for generating and updating the candidate list using a generative AI model. This makes it possible to dynamically provide optimal content for the user's emotional state and improve user satisfaction.

[1480] "Desired conditions" refers to the genre, keywords, format, etc. of the content the user wants to watch.

[1481] "Initial candidate list" refers to a list of content candidates generated based on the user's desired conditions.

[1482] "Feedback" refers to the ratings and opinions that users give to the displayed list of candidates.

[1483] "Additional Terms" refers to any further detailed desired terms provided by the User along with their Feedback.

[1484] "Emotion recognition means" refers to the function of analyzing the user's facial expressions and voice and recognizing their emotional state.

[1485] "Emotion Data" refers to data regarding a user's emotions collected by an emotion recognition means.

[1486] A "big database" refers to a database for storing and searching large amounts of data, such as users' viewing history, desired conditions, and emotional data.

[1487] "Generative AI model" refers to an artificial intelligence model that generates and updates optimal content candidate lists based on user preferences and emotional data.

[1488] "Entry Procedure" refers to the various procedures to facilitate access to and viewing of the Final Selected Content.

[1489] The present invention is a content recommendation system that uses an emotion recognition engine and provides optimal content based on a user's desired conditions and emotion data. The system of the present invention is implemented as follows.

[1490] System configuration

[1491] Hardware and software used

[1492] Smartphones / Smart Glasses / Head-Mounted Displays

[1493] Device camera: Collects user facial expression data.

[1494] Device microphone: Collects user voice data.

[1495] server

[1496] Big database: Stores user viewing history, preferences, and emotional data.

[1497] Generative AI model: Generates and updates a list of optimal content candidates based on desired conditions and sentiment data.

[1498] software

[1499] OpenCV (facial expression recognition)

[1500] TensorFlow (voice emotion recognition)

[1501] Flask (Server-side API construction)

[1502] Program processing

[1503] 1. Collect user requirements

[1504] Users launch the app on their smartphone, smart glasses, or head-mounted display and enter their desired content preferences.

[1505] The device camera and microphone collect emotion data from the user's facial expressions and voice, which is then converted into JSON format and sent to the server.

[1506] 2. Initial candidate list generation and use of emotion data

[1507] The server analyzes the received desired conditions and emotional data, searches a big database, and generates an initial candidate list.

[1508] The generative AI model takes into account emotional data and desired conditions to generate an optimal list of content candidates.

[1509] 3. View candidate lists and receive feedback

[1510] An initial candidate list is sent to the device and displayed to the user, who can then provide feedback or additional criteria.

[1511] User feedback, additional conditions, and newly collected emotional data are sent to the server.

[1512] 4. Reevaluate and update the candidate list

[1513] The server analyzes the feedback, additional conditions, and emotional data, and re-evaluates and updates the candidate list using a generative AI model.

[1514] The updated list is sent to the device and displayed to the user again.

[1515] 5. Selection of Finalists and Entry Procedure

[1516] The user selects the final content, and sentiment data is collected at the time of the final selection.

[1517] The necessary information for the entry procedure is displayed, and the entry procedure is supported.

[1518] Examples of concrete examples and prompts

[1519] Specific examples

[1520] The user inputs their preference for "action movies" and the emotion recognition engine simultaneously recognizes that the user is excited. Based on this information, the server generates a list of suitable action movies and provides them to the user. Emotional data is also continuously collected during viewing and used for subsequent recommendations.

[1521] Prompt Sentence Examples

[1522] "I recognize that the user is excited. Please generate a list of action movies. The desired criteria is 'action movies.'"

[1523] As a result, the system of the present invention dynamically recommends content taking into account not only the user's desired conditions but also emotional data, thereby significantly improving user satisfaction.

[1524] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1525] Program processing steps

[1526] Step 1:

[1527] The user enters their desired conditions and emotional data is collected.

[1528] Input: User's desired conditions (e.g. genre, keywords, etc.), facial expression data, voice data

[1529] Processing: The device displays a screen for entering desired conditions, and the user enters the conditions. The device also collects facial and voice data using the camera and microphone. The collected data is converted into JSON format.

[1530] Output: JSON formatted preference and emotion data sent to the server

[1531] Step 2:

[1532] Generate an initial candidate list.

[1533] Input: JSON formatted preference and emotion data

[1534] Processing: The server analyzes the received desired conditions and emotional data. It searches a big database to collect content information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list, taking into account the emotional data.

[1535] Output: Initial candidate list sent to the terminal

[1536] Step 3:

[1537] Present an initial list of candidates to the user and receive feedback and additional criteria.

[1538] Input: Initial candidate list

[1539] Processing: The device displays an initial list of candidates. The user can then enter feedback (e.g., a rating of good or bad) or additional criteria (e.g., a more detailed genre specification) based on the displayed list, and new emotional data is collected using the device's camera and microphone. This data is then converted back into JSON format.

[1540] Output: Feedback, additional conditions, and emotion data sent to the server

[1541] Step 4:

[1542] Reassess and update the candidate list.

[1543] Input: Feedback, additional conditions, emotional data

[1544] Processing: The server analyzes the received feedback, additional criteria, and sentiment data. It uses the generative AI model to re-evaluate the initial candidate list and generate an updated list.

[1545] Output: Updated candidate list sent to the terminal

[1546] Step 5:

[1547] The updated candidate list is displayed to the user and a final selection is accepted.

[1548] Input: Updated candidate list

[1549] Processing: The device displays the updated candidate list to the user, who then selects the final viewing content, collecting emotional data at the time of selection.

[1550] Output: Final selection results and emotion data sent to the server

[1551] Step 6:

[1552] Assist with the entry process.

[1553] Input: Final selection results and emotion data

[1554] Processing: The server analyzes the final selection results and emotion data, generates the necessary entry procedure information, and assists the user in completing the necessary viewing procedures.

[1555] Output: Final viewing instructions provided to the user

[1556] Through these steps, the content recommendation system of the present invention can dynamically recommend content that perfectly matches the user's emotional state, optimizing the user's viewing experience.

[1557] 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.

[1558] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1559] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1560] [Fourth embodiment]

[1561] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1562] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1563] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[1564] 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.

[1565] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1566] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1567] 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.

[1568] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1569] 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.

[1570] 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 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.

[1571] 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.

[1572] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1573] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1574] ---

[1575] The system of the present invention proposes the most suitable employment based on the user's desired conditions and efficiently supports the procedures up to application. The flow of processing of the entire system and a specific example will be explained below.

[1576] 1. Enter the user's desired conditions

[1577] Device:

[1578] When a user logs in, a screen for entering desired conditions is displayed.

[1579] Users enter their desired conditions such as salary, industry, type of business, company size, area, and employee benefits.

[1580] Example: A user enters the following requirements:

[1581] Salary: 4 million yen or more

[1582] Industry: IT industry

[1583] Area: Tokyo

[1584] Working style:Remote work available

[1585] Device:

[1586] The entered desired conditions are converted into JSON format and sent to the server.

[1587] 2. Initial candidate list generation

[1588] server:

[1589] Analyze the received JSON data and obtain the user's desired conditions.

[1590] Search for company information that matches your desired criteria from a big database.

[1591] The search results are passed as input conditions to the generative AI model to generate an initial candidate list.

[1592] The initial candidate list is converted into JSON format and sent to the terminal.

[1593] Example: The server selects 20 companies out of 100 as initial candidates and sends the list to the terminal.

[1594] 3. View candidate lists and receive feedback

[1595] Device:

[1596] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user as a list.

[1597] user:

[1598] Review the shortlist and enter your feedback and any additional preferences for each company.

[1599] example:

[1600] The user enters additional conditions such as "fully compatible with remote work, work that allows the use of English."

[1601] Device:

[1602] User feedback and additional conditions are converted into JSON format and sent to the server.

[1603] 4. Reevaluate and update the candidate list

[1604] server:

[1605] Parse the JSON data for received feedback and additional conditions.

[1606] Use generative AI models to narrow down the shortlist by re-evaluating based on feedback and additional criteria.

[1607] The updated candidate list is converted into JSON format and sent to the terminal.

[1608] Example: The server narrows down the initial candidate list from 20 companies to 10 companies and sends the re-evaluated candidate list to the terminal.

[1609] 5. Selection of finalists and assistance with application procedures

[1610] Device:

[1611] Display the updated candidate list to the user.

[1612] user:

[1613] Select the final job from the updated candidate list.

[1614] Express your intention to apply to the selected employer.

[1615] Device:

[1616] Display a form or link to collect application information for finalist companies.

[1617] The entry information entered by the user is converted into JSON format and sent to the server.

[1618] server:

[1619] The received entry information will be analyzed and the information necessary to complete the entry process will be sent to the relevant company.

[1620] Manage entry status and provide feedback to users.

[1621] example:

[1622] The user initiates an application to the company they have finally selected, the device displays the necessary form, and the server then sends the application information to the selected company.

[1623] In this way, the system of the present invention can propose optimal employment opportunities based on the user's desired conditions and provide consistent support up to the application process, allowing users to efficiently advance their job search and making it easier for them to find a job that meets their needs.

[1624] ---

[1625] The processing flow will be explained below.

[1626] ---

[1627] Step 1:

[1628] user:

[1629] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[1630] Device:

[1631] Receives the entered desired conditions, converts them into JSON format data, and sends the converted JSON format data to the server.

[1632] Step 2:

[1633] server:

[1634] The received JSON data is analyzed to extract the user's desired conditions. A big database is used to search for company information that matches the desired conditions. The search results are input into the generative AI model to generate an initial candidate list. The generated initial candidate list is converted into JSON format and sent to the terminal.

[1635] Step 3:

[1636] Device:

[1637] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[1638] user:

[1639] Review the list of candidates displayed and enter your feedback and any additional requirements for each company.

[1640] Device:

[1641] Receives feedback and additional conditions from the user, converts them into JSON format, and sends them to the server.

[1642] Step 4:

[1643] server:

[1644] Parse the JSON data of the received feedback and additional conditions. Use the generative AI model to reevaluate the initial candidate list based on the feedback and additional conditions and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[1645] Step 5:

[1646] Device:

[1647] The update candidate list received from the server is analyzed and displayed to the user.

[1648] user:

[1649] Select the final employer from the updated candidate list that is displayed. Indicate your intention to apply to the selected employer.

[1650] Device:

[1651] It displays an information form and link for the user to submit an entry for the final candidate they have selected. It receives the entry information entered by the user, converts it into JSON format, and sends it to the server.

[1652] Step 6:

[1653] server:

[1654] Analyze the received entry information. Send the necessary information to the relevant companies to process the entry. Monitor the entry status and provide feedback to the user.

[1655] ---

[1656] In this way, by performing specific actions at each step, users can efficiently find the best job based on their desired conditions and can also complete the application process smoothly.

[1657] Example 1

[1658] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1659] Previous job-hunting support systems lacked the efficiency to find companies that matched users' desired conditions, and the process for evaluating and updating candidate lists was insufficient, resulting in users spending a lot of time and effort finding the job they wanted.Furthermore, the application process lacked consistency and efficiency, placing a heavy burden on users when applying to each company.

[1660] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1661] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for analyzing the received feedback and additional conditions and re-evaluating the candidate list, means for updating the re-evaluated candidate list, means for displaying the re-evaluated candidate list and accepting a final selection from the user, and means for supporting the application procedure to the finally selected company. This enables users to efficiently and effectively find their desired job and simplifies the application procedure.

[1662] "Desired conditions" refers to the specific requirements and wishes that a user has for a job, such as salary, industry, type of business, company size, area, and employee benefits.

[1663] An "initial candidate list" refers to a list of multiple companies that is initially generated based on the user's desired conditions.

[1664] "Feedback" refers to the opinions, ratings, and additional requirements that users provide regarding the initial candidate list.

[1665] "Re-evaluated shortlist" refers to the list of companies that have been re-evaluated and filtered based on user feedback and additional criteria.

[1666] A "big database" refers to a database that stores a large amount of company information, and is used by job support systems to search for company information based on users' desired conditions.

[1667] "Generative AI model" refers to a model that uses artificial intelligence techniques to generate and update initial and reevaluated candidate lists, for example, by utilizing natural language processing or machine learning techniques.

[1668] A "prompt" is a text sentence that is input to a generative AI model to obtain a specific output, and includes the user's desired conditions and feedback.

[1669] "Application procedure support" refers to the process of supporting users to effectively apply to the company of their choice, including providing application forms and submitting required information.

[1670] MODE FOR CARRYING OUT THE INVENTION

[1671] The system of the present invention proposes suitable employment opportunities based on the user's desired employment conditions and efficiently supports the application process. This system effectively finds companies that match the user's preferences using a server, terminals, a generative AI model, and a big database.

[1672] Specific hardware and software used:

[1673] Server: A server capable of high-performance data processing and AI model execution

[1674] Device: The device used by the user, such as a PC, smartphone, or tablet

[1675] Database: A big database that stores corporate information (e.g., MongoDB or PostgreSQL)

[1676] Generative AI models: AI models capable of natural language processing and data analysis (e.g., "OpenAI GPT-4")

[1677] Program processing

[1678] 1. Enter your desired conditions:

[1679] Terminal: After the user logs in, a screen for inputting desired conditions is displayed. The user fills in the input form with desired conditions such as salary, industry, type of business, company size, area, and employee benefits. The input conditions are validated in real time, converted to JSON format, and sent to the server.

[1680] 2. Generate initial candidate list:

[1681] Server: Analyzes the received JSON data and extracts the user's desired conditions. Then, retrieves company information that matches the conditions from a big database and inputs the conditions as prompts into the generative AI model to generate an initial candidate list.

[1682] Example prompt: "Generate a list of companies that meet the following criteria: salary over ¥4 million, industry IT, location Tokyo, work style remote work available."

[1683] The generated initial candidate list is also converted into JSON format and sent to the terminal.

[1684] 3. View candidate list and receive feedback:

[1685] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted back to JSON format and sent to the server.

[1686] 4. Reevaluate and update the candidate list:

[1687] Server: Analyzes the received feedback and additional conditions, re-evaluates and narrows down the candidate list using the generative AI model, converts the re-evaluated candidate list into JSON format, and sends it to the device.

[1688] Example prompt: "Please reassess your shortlist based on the following feedback and additional criteria: Fully remote-friendly, English-speaking roles."

[1689] 5. Finalist selection and entry process assistance:

[1690] Terminal: The re-evaluated candidate list is displayed to the user. The user selects a final job and enters information to indicate their intention to apply. The application information is converted to JSON format and sent to the server.

[1691] Server: Analyzes entry information, sends it to related companies to assist with entry procedures, manages entry status, and provides feedback to users.

[1692] As a result, this system helps users efficiently apply to companies that meet their desired criteria. As a specific example, when the above prompt sentence is passed to the generative AI model, the generated list of companies can be used to smoothly advance the user's job search.

[1693] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1694] Step 1:

[1695] Input of user's desired conditions

[1696] Terminal: When the user logs in, a screen for inputting desired conditions is displayed. The user enters desired conditions such as salary, industry, type of business, company size, area, and employee benefits in the displayed form. The input is validated in real time, and an error message is displayed immediately if there are any omissions or errors.

[1697] input:

[1698] The desired conditions entered by the user in the form (e.g. salary, industry, area, etc.)

[1699] output:

[1700] Desired conditions data converted to JSON format

[1701] Specific behavior:

[1702] When the user completes the input, the submit button is activated. When the user presses the submit button, the input data is converted to JSON format and sent to the server as an HTTP request.

[1703] Step 2:

[1704] Initial candidate list generation

[1705] Server: Parses the received JSON-formatted desired conditions data and extracts them as key-value pairs. Next, it queries the big database to search for company information that matches the desired conditions. The search results are input as prompts to the generative AI model, and an initial candidate list is generated.

[1706] input:

[1707] JSON data containing the user's preferences

[1708] output:

[1709] Initial candidate list in JSON format

[1710] Specific behavior:

[1711] The server uses a parsing library to parse the JSON data. It then issues an SQL or NoSQL query to retrieve company information that matches the desired criteria from the database. The retrieved data is input to the generative AI model in the form of a prompt statement, which generates an initial candidate list. The generated list is then converted to JSON format and sent back to the device.

[1712] Step 3:

[1713] View candidate lists and receive feedback

[1714] Terminal: Analyzes the received initial candidate list and displays it to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted into JSON format and sent to the server.

[1715] input:

[1716] Initial candidate list received from the server

[1717] User-entered feedback and additional requirements

[1718] output:

[1719] Feedback data in JSON format

[1720] Specific behavior:

[1721] The device parses the initial candidate list received from the server and displays it in the user interface. Once the user has entered their feedback and additional preferences, the device converts this into JSON format and sends it to the server.

[1722] Step 4:

[1723] Reevaluate and update the candidate list

[1724] Server: Analyzes the received feedback and JSON data for additional conditions, and re-evaluates it using the generative AI model. Passes a new prompt to the generative AI model to narrow down the candidate list. Converts the re-evaluated candidate list into JSON format and sends it to the device.

[1725] input:

[1726] JSON data of feedback received from users and additional conditions

[1727] output:

[1728] Re-evaluated candidate list in JSON format

[1729] Specific behavior:

[1730] The server analyzes the feedback and additional conditions and generates a new prompt. Example prompt: "Please reevaluate the candidate list based on the following feedback and additional conditions: fully compatible with remote work, work that utilizes English." This prompt is input into the generative AI model, which generates a reevaluated candidate list. The reevaluated list is converted into JSON format and sent back to the device.

[1731] Step 5:

[1732] Selection of finalists and assistance with application procedures

[1733] Terminal: Parses the re-evaluated candidate list received from the server and displays it to the user. The user selects the final job and enters application information. The application information is converted to JSON format and sent to the server.

[1734] input:

[1735] Re-evaluated candidate list received from the server

[1736] Entry information entered by the user

[1737] output:

[1738] Entry information in JSON format

[1739] Specific behavior:

[1740] The device parses the re-evaluated candidate list and displays it in a user-friendly format. Once the user makes their final selection and enters their entry information, the information is converted to JSON format and sent to the server.

[1741] Step 6:

[1742] Entry status management and feedback

[1743] Server: Analyzes the received entry information and sends it to the relevant companies. Manages the entry process and provides feedback to users on the status.

[1744] input:

[1745] JSON data of the entry information received from the user

[1746] output:

[1747] Feedback information regarding the status of the entry process

[1748] Specific behavior:

[1749] The server analyzes the entry information and sends the necessary data to the relevant companies via API, email, etc. The progress of the entry is monitored in real time and feedback is sent to the user's device. This feedback includes whether the entry was accepted and instructions for the next step.

[1750] (Application example 1)

[1751] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1752] In conventional job-hunting systems, even if users input their desired conditions, it can be difficult to efficiently find suitable employers based on those conditions. Furthermore, the time and effort required to gather company information and complete application procedures can make job hunting a burden for users. In particular, with the introduction of remote work and the growing need for virtual interviews, traditional methods present challenges that cannot be fully addressed. To address these challenges, the present invention provides a system that quickly and efficiently suggests optimal employers based on users' desired conditions and also supports interviews and browsing of company information in a virtual space.

[1753] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1754] In this invention, the server includes means for inputting desired conditions, means for generating an initial candidate list based on the user's desired conditions, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, means for supporting the application process to the finally selected company, and means for viewing company information in a virtual space and virtually experiencing interviews and job hunting. This enables users to efficiently find jobs that meet their desired conditions and smoothly conduct their job search by viewing company information and conducting interviews in a virtual space.

[1755] The "means for inputting desired conditions" is an interface that allows users to input their desired employment conditions, such as salary, industry, work location, and work style.

[1756] The "means for generating an initial candidate list" is a function for generating a list of suitable candidate companies at an early stage based on the desired conditions entered by the user.

[1757] The "means for displaying the initial candidate list and receiving feedback and additional conditions from the user" is a mechanism for displaying the generated initial candidate list to the user and accepting opinions and input of additional items from the user.

[1758] "Means to reevaluate and update candidate list" refers to the functionality to reevaluate the initial candidate list based on feedback received from users and additional criteria, and update the list as needed to reflect new information.

[1759] The "means for displaying the re-evaluated candidate list and accepting a final selection from the user" refers to an interface for presenting the updated candidate list to the user again and accepting the user's final selection of the company.

[1760] "Means to support the application process to the final selected company" refers to a support function that helps the user smoothly go through the application process to the company they have selected, and supports them in entering the necessary information and submitting documents, etc.

[1761] "A means of viewing company information in a virtual space and virtually experiencing interviews and job interviews" is a function that allows users to use smart glasses or a head-mounted display to check company information in a virtual environment and virtually experience interviews and job interviews.

[1762] The system of the present invention is designed to enable users to efficiently conduct job hunting, and to achieve this, it uses smart glasses and a head-mounted display to provide an experience in a virtual space.

[1763] 1. System Configuration

[1764] The system consists of the following main components:

[1765] Terminal: A device that provides an interface for users to input their desired conditions, view company information, and conduct interviews and job interviews in a virtual space. Examples of this include smart glasses and head-mounted displays.

[1766] Server: A central control unit that analyzes preferences, generates and updates candidate lists, processes feedback, and assists with the entry process.

[1767] Generative AI model: An algorithm that uses OpenAI's API to suggest suitable companies based on the user's desired criteria.

[1768] 2. Program Overview

[1769] Below is an overview of the system's main functions: company proposals based on the user's desired conditions and virtual interview functions.

[1770] Input and analysis of desired conditions

[1771] The user enters their desired job search conditions from their device, including salary, industry, work location, and work style. The entered information is converted into JSON format and sent to the server.

[1772] Generate and display candidate lists

[1773] The server analyzes the received requirements and searches for relevant company information in a big database. It then uses a generative AI model to create an initial candidate list and sends it to the device. The device then displays it to the user and accepts feedback and additional requirements.

[1774] Reevaluate and update the candidate list

[1775] After receiving user feedback, the server re-evaluates and updates the candidate list using the generative AI model, which is then sent back to the device and displayed to the user.

[1776] Viewing company information and conducting interviews in a virtual space

[1777] Users can enter the virtual space by wearing smart glasses or a head-mounted display and check detailed information about companies. Interviews and job interviews can also be conducted in the virtual space. This allows users to conduct job hunting remotely without having to visit a company in person.

[1778] 3. Examples and prompts

[1779] As a specific use case, the following shows how a user inputs their desired conditions in a virtual space and the generative AI model suggests suitable companies.

[1780] Example prompt sentence:

[1781] Use a generative AI model to generate a list of companies that meet the following criteria:

[1782] Salary: 4 million yen or more

[1783] Industry: IT industry

[1784] Area: Tokyo

[1785] Working style:Remote work available

[1786] By sending this prompt to the system, a list of companies that match the user's desired criteria is automatically generated, allowing the user to proceed with their job search efficiently and effectively.

[1787] The above is an embodiment of the present invention.

[1788] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1789] Step 1:

[1790] Enter your desired criteria and submit:

[1791] Users log in to the virtual space using smart glasses or a head-mounted display. A desired conditions input screen is displayed, and the user inputs conditions such as desired salary, industry, work location, and working style. The input information is converted to JSON format on the device and sent to the server.

[1792] Input: User's desired conditions (e.g. salary, industry, work location, work style)

[1793] Output: JSON format desired conditions data

[1794] Step 2:

[1795] Generate the initial candidate list:

[1796] The server analyzes the received JSON data and obtains the user's desired conditions. It then searches the big database to extract company information that matches the desired conditions. The search results are passed as input conditions to the generative AI model, which generates an initial candidate list. The generated initial candidate list is converted to JSON format and sent to the device.

[1797] Input: JSON format desired conditions data

[1798] Data calculation: Big database search, initial candidate list generation using generative AI models

[1799] Output: Initial candidate list in JSON format

[1800] Step 3:

[1801] View initial candidate list and receive feedback:

[1802] The device parses the JSON data received from the server and displays an initial candidate list to the user. The user reviews the candidate list and enters feedback and additional desired conditions for each company. The entered feedback and additional conditions are converted to JSON format on the device and sent to the server.

[1803] Input: Initial candidate list in JSON format

[1804] Output: User feedback and additional conditions (JSON format)

[1805] Step 4:

[1806] Reevaluate and update the candidate list:

[1807] The server parses the received feedback and additional conditions in JSON data and re-evaluates them using the generative AI model. The re-evaluated candidate list is converted into JSON format and sent to the device. The device then displays the updated candidate list to the user.

[1808] Input: Feedback and additional conditions data in JSON format

[1809] Data Computing: Reevaluating and Updating Candidate Lists with Generative AI Models

[1810] Output: Updated candidate list in JSON format

[1811] Step 5:

[1812] Finalist selection and entry assistance:

[1813] The user selects a final employer from the updated candidate list and indicates their intention to apply. The device displays a form and links for collecting application information for the final candidate companies. The application information entered by the user is converted to JSON format on the device and sent to the server. The server analyzes the application information and sends the necessary information to the relevant companies to complete the application process.

[1814] Input: Updated candidate list in JSON format

[1815] Output: User entry information (JSON format)

[1816] Step 6:

[1817] Virtual company information viewing and interviews:

[1818] Users wear smart glasses or a head-mounted display and can view company information in a virtual space. They can also access company booths, view presentation videos and detailed company information, and virtually experience interviews and job interviews in the virtual space.

[1819] Input: Company information in virtual space

[1820] Output: Company information browsing results and interview experience

[1821] The above are the specific processing steps of the system that realizes this application example. This processing flow allows users to consistently conduct their job search efficiently and effectively.

[1822] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1823] ---

[1824] The system of the present invention not only proposes optimal employment opportunities based on the user's desired conditions and supports the application process, but also realizes more accurate job hunting by combining it with an emotion engine that recognizes the user's emotions. The following explains the overall processing flow of the system and a specific example.

[1825] 1. User preference input and emotion recognition

[1826] Device:

[1827] When a user logs in, a screen for entering desired conditions is displayed.

[1828] Users enter their desired conditions, such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[1829] user:

[1830] When users input their desired conditions, the device's emotion engine analyzes their facial expressions and voice to collect emotional data.

[1831] Device:

[1832] The emotion data along with the entered desired conditions is converted into JSON format and sent to the server.

[1833] 2. Initial candidate list generation and use of emotion data

[1834] server:

[1835] The received JSON data of desired conditions and emotional data is analyzed to extract the user's desired conditions.

[1836] Use a big database to search for company information that matches your desired criteria.

[1837] Search results are fed into a generative AI model, which takes sentiment data into account when generating an initial candidate list.

[1838] The initial candidate list is converted into JSON format and sent to the terminal.

[1839] 3. View candidate lists and receive feedback

[1840] Device:

[1841] The initial candidate list received from the server is analyzed and the candidate list is displayed to the user.

[1842] user:

[1843] While reviewing the displayed list of candidates, users can enter their feedback and any additional requirements for each company. The emotion engine also collects their emotions when providing feedback.

[1844] Device:

[1845] User feedback, additional conditions, and collected emotional data are converted into JSON format and sent to the server.

[1846] 4. Reevaluate and update the candidate list

[1847] server:

[1848] Parse the JSON data for received feedback, additional conditions, and sentiment data.

[1849] A generative AI model is used to re-evaluate the initial candidate list based on feedback, additional criteria, and sentiment data to generate an updated candidate list.

[1850] The updated candidate list is converted into JSON format and sent to the terminal.

[1851] 5. Finalist selection and use of sentiment data

[1852] Device:

[1853] Display the updated candidate list to the user.

[1854] user:

[1855] The final job is selected from the updated candidate list. During the selection process, the emotion engine recognizes the user's emotions and collects the data.

[1856] Device:

[1857] An information form or link is displayed for the user to enter the final candidate selected by the user, and the user enters the required information.

[1858] Emotion data is also sent to the server together with the entered entry information.

[1859] 6. Entry procedure support and use of emotion data

[1860] server:

[1861] The received entry information and emotional data are analyzed, and the entry process is carried out with the relevant companies.

[1862] The necessary information will be sent to related companies to provide optimal support for application procedures based on emotional data.

[1863] Manage entry status and provide feedback to users.

[1864] Specific examples

[1865] For example, if a user enters their desired conditions as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system will take this into account when creating an initial candidate list. Upon feedback, the system will add more detailed conditions, such as "fully remote work-enabled, work that utilizes English," and re-evaluate the results using the emotion engine data to present the optimal candidate list. The system will then support a more effective application process based on the emotion data from the final selection.

[1866] ---

[1867] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, thereby realizing more personalized job suggestions and application procedures, allowing users to efficiently find the job that best suits them and conducting a highly satisfying job search.

[1868] The processing flow will be explained below.

[1869] ---

[1870] Step 1:

[1871] user:

[1872] Log in and access the desired conditions input screen. Enter your desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed).

[1873] Device:

[1874] When a user enters their desired conditions, the emotion engine analyzes their facial expressions and voice to collect emotional data. The entered desired conditions and emotional data are converted into JSON format and sent to the server.

[1875] Step 2:

[1876] server:

[1877] The system analyzes the received JSON data of desired conditions and emotion data to extract the user's desired conditions. It uses a big database to search for company information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list based on the search results and emotion data. It converts the initial candidate list into JSON format and sends it to the device.

[1878] Step 3:

[1879] Device:

[1880] Parse the JSON data of the initial candidate list received from the server and display the candidate list to the user.

[1881] user:

[1882] Review the displayed list of candidates and enter your feedback and additional requirements for each company. As you enter your feedback and additional requirements, the emotion engine will collect your emotional data.

[1883] Device:

[1884] User feedback, additional conditions, and emotional data are converted into JSON format and sent to the server.

[1885] Step 4:

[1886] server:

[1887] Parse the received feedback, additional conditions, and emotional data in JSON format. Use the generative AI model to re-evaluate the candidate list based on the feedback, additional conditions, and emotional data, and generate an updated candidate list. Convert the updated candidate list into JSON format and send it to the device.

[1888] Step 5:

[1889] Device:

[1890] The update candidate list received from the server is analyzed and displayed to the user.

[1891] user:

[1892] The final job is selected from the updated candidate list. At the time of the final selection, the emotion engine recognizes the user's emotions and collects the data.

[1893] Device:

[1894] It displays a form and link for the user to apply to the final candidate company of their choice. The user enters the necessary information, and the application information and emotion data are converted into JSON format and sent to the server.

[1895] Step 6:

[1896] server:

[1897] The system analyzes the received entry information and emotion data. It sends the necessary information to the relevant companies to complete the entry process. It provides optimal support for the entry process based on the emotion data, manages the entry status, and provides feedback to the user.

[1898] ---

[1899] In this way, by performing specific operations at each processing step, a system is realized that takes into account the user's emotions and provides more personalized job candidate suggestions and procedural support.

[1900] Example 2

[1901] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1902] Conventional job-hunting support systems suggested candidate companies based on the user's desired conditions, but did not consider the user's feelings when suggesting candidate companies. As a result, it was difficult for users to find the best job, and they were unable to achieve a satisfying job-hunting experience. In addition, it was difficult to effectively reflect received feedback and additional conditions, and there was also the problem of candidate lists not being updated sufficiently.

[1903] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for the user to input desired conditions, means for analyzing the user's facial expressions and voice to collect emotional data, means for transmitting the input desired conditions and emotional data to the server, means for generating an initial candidate list based on the user's desired conditions and emotional data, means for displaying the initial candidate list and receiving feedback and additional conditions from the user, means for reevaluating and updating the candidate list based on the received feedback and additional conditions, means for displaying the reevaluated candidate list and accepting a final selection from the user, and means for supporting the application process to the finally selected company. This enables more personalized job suggestions and support that take into account not only the user's desired conditions but also their emotions.

[1904] "User's desired conditions" refers to the conditions the user desires for employment, such as salary, industry, type of business, company size, area, and working style.

[1905] "Emotional data" refers to data that indicates the user's emotional state (e.g., joy, surprise, anxiety, etc.) obtained by analyzing the user's facial expressions and voice.

[1906] "Initial candidate list" refers to a list of candidate companies presented to a user, generated based on the user's desired conditions and emotional data.

[1907] "Feedback" refers to the opinions, ratings, and additional preferences provided by the user regarding the displayed list of candidate companies.

[1908] "Re-evaluated Candidate List" refers to the list of candidate companies that have been re-evaluated and updated based on user feedback and additional criteria and sentiment data.

[1909] "Means to support the entry process" refers to functions that support the procedures required when a user applies to the company they have finally selected (such as filling out information forms and submitting required documents).

[1910] "Big database" refers to a database system (e.g., Google Cloud BigQuery, Amazon Redshift) for efficiently managing and searching large amounts of data.

[1911] "Generative AI model" refers to a model (e.g., ChatGPT) that uses artificial intelligence techniques to generate and update candidate lists.

[1912] The system of the present invention proposes optimal job opportunities based on the user's desired conditions and supports the application process. Furthermore, by combining this system with an emotion engine that recognizes the user's emotions, the system achieves more accurate job hunting. Specific embodiments of the present invention are described in detail below.

[1913] System Overview

[1914] The system includes means for inputting user preferences, means for collecting sentiment data, means for generating an initial candidate list, means for receiving and re-evaluating feedback, means for receiving final selections, and means for assisting the entry process.

[1915] User preference input and emotion recognition

[1916] Device:

[1917] When a user logs in, a screen for entering desired conditions appears. The user enters their desired conditions, such as salary, industry, type of business, company size, location, and working style (e.g., remote work available). At this time, the device uses its built-in webcam and microphone to send the user's facial expressions and voice to an emotion engine, which collects emotional data in real time. The emotional data is analyzed using technologies such as "Affectiva" and "Microsoft Azure Emotion API."

[1918] Generating an initial candidate list

[1919] server:

[1920] The desired conditions and emotion data sent from the device are received and analyzed. Based on the analyzed data, a big database (e.g., Google Cloud BigQuery or Amazon Redshift) is used to search for company information that matches the user's desired conditions. The search results and emotion data are input into a generative AI model (e.g., ChatGPT) to generate an initial candidate list. A prompt such as "Please select companies in the IT industry in Tokyo where the user's desired salary is 4 million yen or more. The user has shown a high interest in remote work" is used.

[1921] View candidate lists and receive feedback

[1922] Device:

[1923] The initial candidate list sent from the server is analyzed and a list of candidates is displayed to the user. The user reviews the displayed candidate list and enters feedback and additional desired conditions for each company. The device also collects emotional data during this process. The collected feedback and emotional data are then sent back to the server.

[1924] Reevaluate and update the candidate list

[1925] server:

[1926] The received feedback and sentiment data is analyzed, and the initial candidate list is re-evaluated and updated using a generative AI model, using prompts such as "Users have a strong preference for full remote work support, so please focus on this." The re-evaluated candidate list is then sent to the device.

[1927] Finalist selection and entry procedures

[1928] Device:

[1929] The updated candidate list is displayed to the user. The user then selects the final employer. Emotional data is also collected during this process. An information form and link for applying to the final selected company are displayed, and the user enters the required information. The entered application information and emotional data are then sent to the server.

[1930] server:

[1931] Analyze the received entry information and emotion data and process the entry with the relevant companies. Send the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manage the entry status and provide feedback to the user.

[1932] Specific examples

[1933] When a user enters their desired conditions, such as "annual salary of 4 million yen or more, IT industry, Tokyo, remote work available," and the emotion engine recognizes the user's high level of excitement and interest, the system takes this into account when creating an initial candidate list. If the user provides feedback and adds more detailed conditions, such as "full remote work support, work that utilizes English," the system reevaluates the results using the emotion engine data and presents the optimal candidate list. The system then supports a more effective application process based on the emotion data from the final selection.

[1934] In this way, the system of the present invention takes into account not only the user's desired conditions but also their emotions, allowing for more personalized job suggestions and application procedures, enabling users to efficiently find the job that best suits them and achieving a more satisfying job search experience.

[1935] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1936] Step 1:

[1937] User: When a user logs in, a screen for entering desired conditions is displayed on the device. The user enters desired conditions such as salary, industry, type of business, company size, area, and working style (e.g., remote work allowed). The input information is saved on the device.

[1938] Input: User's desired criteria (e.g. salary, industry, business type, etc.).

[1939] Output: Generate data (e.g., JSON format) based on the desired conditions.

[1940] Step 2:

[1941] Device: The user's facial expressions and voice are collected in real time on the input screen using a webcam and microphone. The collected data is analyzed using an emotion engine (e.g., "Affectiva" or "Microsoft Azure Emotion API"). Emotional data (happiness, surprise, anxiety, etc.) is generated as a result of the analysis.

[1942] Input: User facial and voice data.

[1943] Output: Generate emotion data (e.g., JSON format).

[1944] Step 3:

[1945] Device: The desired conditions and emotional data are combined into a single JSON file and sent to the server. The combined data includes the user's desired conditions and emotional state.

[1946] Input: Desired condition data, emotion data.

[1947] Output: Consolidated preference and sentiment data in JSON format.

[1948] Step 4:

[1949] Server: Analyzes the received desired conditions and sentiment data to extract the user's desired conditions. Uses a big database (e.g., Google Cloud BigQuery or Amazon Redshift) to search for company information that matches the desired conditions. Filters the company information in the database using the search query.

[1950] Input: Integrated desire criteria and emotion data.

[1951] Output: Company information as search results.

[1952] Step 5:

[1953] Server: Input the search results and sentiment data into a generative AI model (e.g., "ChatGPT") to generate an initial candidate list. Input a prompt such as "The user's desired salary is 4 million yen or more, and please select companies in the IT industry in Tokyo. The user has a high interest in remote work." Create an initial candidate list as a result and convert it to JSON format.

[1954] Input: Search results, sentiment data.

[1955] Output: Initial candidate list (JSON format).

[1956] Step 6:

[1957] Terminal: Analyzes the initial candidate list received from the server and displays a list of candidates to the user. The displayed candidate list includes information about each company (e.g., salary, industry, location, etc.).

[1958] Input: Initial candidate list (JSON format).

[1959] Output: A candidate list that can be viewed by the user.

[1960] Step 7:

[1961] User: Review the list of candidates and enter feedback and additional desired conditions for each company. When providing feedback, the device also collects the user's facial expressions and voice, which are analyzed by the emotion engine. Additional emotional data is generated.

[1962] Input: Feedback on candidate list, facial expression and speech data.

[1963] Output: Feedback, additional conditions, and additional emotion data (JSON format).

[1964] Step 8:

[1965] Terminal: Collects feedback, additional conditions, and additional emotion data, integrates them into a single JSON data, and sends it to the server.

[1966] Input: Feedback, additional conditions, additional emotion data.

[1967] Output: Consolidated feedback data in JSON format.

[1968] Step 9:

[1969] Server: Analyzes the received feedback, additional conditions, and emotional data. The generative AI model is given another prompt, such as "The user strongly desires full remote work support, so please focus on this." This prompt reevaluates the initial candidate list and generates an updated candidate list. The updated candidate list is converted to JSON format and sent to the device.

[1970] Input: Feedback, additional conditions, emotional data.

[1971] Output: The updated candidate list in JSON format.

[1972] Step 10:

[1973] On the device: Show the updated candidate list to the user.

[1974] Input: The updated candidate list (in JSON format).

[1975] Output: An updated candidate list that can be viewed by the user.

[1976] Step 11:

[1977] User: Selects a final job from the updated candidate list. Emotional data is collected and analyzed during the selection process.

[1978] Input: Updated candidate list, facial expression and speech data.

[1979] Output: Final selection data, emotion data (JSON format).

[1980] Step 12:

[1981] Terminal: Displays an information form and link for the final candidates to enter, and the user enters the required information. The entered entry information and emotion data are sent to the server.

[1982] Input: Final selection data, input information, emotion data.

[1983] Output: Consolidated entry data (JSON format).

[1984] Step 13:

[1985] Server: Analyzes the received entry information and emotion data and carries out the entry process with the relevant companies. Sends the necessary information to the relevant companies to provide optimal entry support based on the emotion data. Manages the entry status and provides feedback to the user.

[1986] Input: Entry information, emotion data.

[1987] Output: Entry information to companies, feedback to users.

[1988] (Application example 2)

[1989] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1990] Conventional content recommendation systems generate candidate lists based on a user's desired conditions, but they are unable to consider the user's emotions and moods, making it difficult to recommend the optimal content that matches the user's current mood. Furthermore, because they update lists based only on user feedback and additional conditions, they lack an understanding of actual user experiences. Therefore, there is a need for a method to recommend more personalized content that takes into account the user's emotional data.

[1991] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1992] In this invention, the server includes an emotion recognition means for recognizing a user's emotion and collecting the data, a means for adjusting a candidate list based on the emotion data and desired conditions, a means for searching for information corresponding to the user's desired conditions using a big database, and a means for generating and updating the candidate list using a generative AI model. This makes it possible to dynamically provide optimal content for the user's emotional state and improve user satisfaction.

[1993] "Desired conditions" refers to the genre, keywords, format, etc. of the content the user wants to watch.

[1994] "Initial candidate list" refers to a list of content candidates generated based on the user's desired conditions.

[1995] "Feedback" refers to the ratings and opinions that users give to the displayed list of candidates.

[1996] "Additional Terms" refers to any further detailed desired terms provided by the User along with their Feedback.

[1997] "Emotion recognition means" refers to the function of analyzing the user's facial expressions and voice and recognizing their emotional state.

[1998] "Emotion Data" refers to data regarding a user's emotions collected by an emotion recognition means.

[1999] A "big database" refers to a database for storing and searching large amounts of data, such as users' viewing history, desired conditions, and emotional data.

[2000] "Generative AI model" refers to an artificial intelligence model that generates and updates optimal content candidate lists based on user preferences and emotional data.

[2001] "Entry Procedure" refers to the various procedures to facilitate access to and viewing of the Final Selected Content.

[2002] The present invention is a content recommendation system that uses an emotion recognition engine and provides optimal content based on a user's desired conditions and emotion data. The system of the present invention is implemented as follows.

[2003] System configuration

[2004] Hardware and software used

[2005] Smartphones / Smart Glasses / Head-Mounted Displays

[2006] Device camera: Collects user facial expression data.

[2007] Device microphone: Collects user voice data.

[2008] server

[2009] Big database: Stores user viewing history, preferences, and emotional data.

[2010] Generative AI model: Generates and updates a list of optimal content candidates based on desired conditions and sentiment data.

[2011] software

[2012] OpenCV (facial expression recognition)

[2013] TensorFlow (voice emotion recognition)

[2014] Flask (Server-side API construction)

[2015] Program processing

[2016] 1. Collect user requirements

[2017] Users launch the app on their smartphone, smart glasses, or head-mounted display and enter their desired content preferences.

[2018] The device camera and microphone collect emotion data from the user's facial expressions and voice, which is then converted into JSON format and sent to the server.

[2019] 2. Initial candidate list generation and use of emotion data

[2020] The server analyzes the received desired conditions and emotional data, searches a big database, and generates an initial candidate list.

[2021] The generative AI model takes into account emotional data and desired conditions to generate an optimal list of content candidates.

[2022] 3. View candidate lists and receive feedback

[2023] An initial candidate list is sent to the device and displayed to the user, who can then provide feedback or additional criteria.

[2024] User feedback, additional conditions, and newly collected emotional data are sent to the server.

[2025] 4. Reevaluate and update the candidate list

[2026] The server analyzes the feedback, additional conditions, and emotional data, and re-evaluates and updates the candidate list using a generative AI model.

[2027] The updated list is sent to the device and displayed to the user again.

[2028] 5. Selection of Finalists and Entry Procedure

[2029] The user selects the final content, and sentiment data is collected at the time of the final selection.

[2030] The necessary information for the entry procedure is displayed, and the entry procedure is supported.

[2031] Examples of concrete examples and prompts

[2032] Specific examples

[2033] The user inputs their preference for "action movies" and the emotion recognition engine simultaneously recognizes that the user is excited. Based on this information, the server generates a list of suitable action movies and provides them to the user. Emotional data is also continuously collected during viewing and used for subsequent recommendations.

[2034] Prompt Sentence Examples

[2035] "I recognize that the user is excited. Please generate a list of action movies. The desired criteria is 'action movies.'"

[2036] As a result, the system of the present invention dynamically recommends content taking into account not only the user's desired conditions but also emotional data, thereby significantly improving user satisfaction.

[2037] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2038] Program processing steps

[2039] Step 1:

[2040] The user enters their desired conditions and emotional data is collected.

[2041] Input: User's desired conditions (e.g. genre, keywords, etc.), facial expression data, voice data

[2042] Processing: The device displays a screen for entering desired conditions, and the user enters the conditions. The device also collects facial and voice data using the camera and microphone. The collected data is converted into JSON format.

[2043] Output: JSON formatted preference and emotion data sent to the server

[2044] Step 2:

[2045] Generate an initial candidate list.

[2046] Input: JSON formatted preference and emotion data

[2047] Processing: The server analyzes the received desired conditions and emotional data. It searches a big database to collect content information that matches the desired conditions. It uses a generative AI model to generate an initial candidate list, taking into account the emotional data.

[2048] Output: Initial candidate list sent to the terminal

[2049] Step 3:

[2050] Present an initial list of candidates to the user and receive feedback and additional criteria.

[2051] Input: Initial candidate list

[2052] Processing: The device displays an initial list of candidates. The user can then enter feedback (e.g., a rating of good or bad) or additional criteria (e.g., a more detailed genre specification) based on the displayed list, and new emotional data is collected using the device's camera and microphone. This data is then converted back into JSON format.

[2053] Output: Feedback, additional conditions, and emotion data sent to the server

[2054] Step 4:

[2055] Reassess and update the candidate list.

[2056] Input: Feedback, additional conditions, emotional data

[2057] Processing: The server analyzes the received feedback, additional criteria, and sentiment data. It uses the generative AI model to re-evaluate the initial candidate list and generate an updated list.

[2058] Output: Updated candidate list sent to the terminal

[2059] Step 5:

[2060] The updated candidate list is displayed to the user and a final selection is accepted.

[2061] Input: Updated candidate list

[2062] Processing: The device displays the updated candidate list to the user, who then selects the final viewing content, collecting emotional data at the time of selection.

[2063] Output: Final selection results and emotion data sent to the server

[2064] Step 6:

[2065] Assist with the entry process.

[2066] Input: Final selection results and emotion data

[2067] Processing: The server analyzes the final selection results and emotion data, generates the necessary entry procedure information, and assists the user in completing the necessary viewing procedures.

[2068] Output: Final viewing instructions provided to the user

[2069] Through these steps, the content recommendation system of the present invention can dynamically recommend content that perfectly matches the user's emotional state, optimizing the user's viewing experience.

[2070] 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.

[2071] 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> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[2072] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2073] 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.

[2074] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[2075] 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.

[2076] 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).

[2077] 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 indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2078] 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."

[2079] 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.

[2080] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2081] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2082] 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.

[2083] 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.

[2084] 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.

[2085] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[2086] The hardware resource that executes the specific processing 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 processing may be a single processor.

[2087] 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.

[2088] 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.

[2089] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2090] 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.

[2091] The following is further disclosed regarding the above embodiment.

[2092] (Claim 1)

[2093] A means for inputting desired conditions;

[2094] A means for generating an initial candidate list based on user preferences;

[2095] a means for displaying the initial candidate list and receiving user feedback and additional requirements;

[2096] A means to reassess and update the shortlist based on feedback and additional criteria;

[2097] a means for displaying the re-evaluated candidate list and accepting a final selection from the user;

[2098] A means of assisting the application process for the final selected companies;

[2099] A system including:

[2100] (Claim 2)

[2101] The system according to claim 1, further comprising means for searching for company information corresponding to the user's desired conditions using a big database.

[2102] (Claim 3)

[2103] 10. The system of claim 1, further comprising means for generating and updating the candidate list using a generative AI model.

[2104] Based on the above claims, the specific technical features of this system are clearly indicated, and the scope of the patent is appropriately limited.

[2105] "Example 1"

[2106] (Claim 1)

[2107] A means for inputting desired conditions;

[2108] A means for generating an initial candidate list based on user preferences;

[2109] a means for displaying the initial candidate list and receiving user feedback and additional requirements;

[2110] A means of analyzing received feedback and additional criteria and re-evaluating the candidate list;

[2111] a means for updating the re-evaluated candidate list;

[2112] a means for displaying the re-evaluated candidate list and accepting a final selection from the user;

[2113] A means of assisting the application process for the final selected companies;

[2114] A system including:

[2115] (Claim 2)

[2116] The system according to claim 1, further comprising a means for searching for company information corresponding to the user's desired conditions using a big database.

[2117] (Claim 3)

[2118] 10. The system of claim 1, further comprising means for generating and updating the initial candidate list and the reevaluated candidate list using a generative AI model.

[2119] "Application Example 1"

[2120] (Claim 1)

[2121] A means for inputting desired conditions;

[2122] A means for generating an initial candidate list based on user preferences;

[2123] a means for displaying the initial candidate list and receiving user feedback and additional requirements;

[2124] A means to reassess and update the shortlist based on feedback and additional criteria;

[2125] a means for displaying the re-evaluated candidate list and accepting a final selection from the user;

[2126] A means of assisting the application process for the final selected companies;

[2127] A means to view company information in a virtual space and virtually experience interviews and job interviews, etc.

[2128] A system including:

[2129] (Claim 2)

[2130] The system according to claim 1, further comprising means for searching for company information corresponding to the user's desired conditions using a big database.

[2131] (Claim 3)

[2132] 10. The system of claim 1, further comprising means for generating and updating the candidate list using a generative AI model.

[2133] "Example 2: Combining Emotion Engines"

[2134] (Claim 1)

[2135] A means for users to input their desired conditions;

[2136] A means of collecting emotional data by analyzing the user's facial expressions and voice,

[2137] means for transmitting the input desired conditions and emotion data to a server;

[2138] A means for generating an initial candidate list based on user's desired conditions and emotion data;

[2139] a means for displaying the initial candidate list and receiving user feedback and additional requirements;

[2140] a means for re-evaluating and updating the candidate list based on received feedback and additional criteria;

[2141] a means for displaying the re-evaluated candidate list and accepting a final selection from the user;

[2142] A means of assisting the application process for the final selected companies;

[2143] A system including:

[2144] (Claim 2)

[2145] The system according to claim 1, further comprising means for searching for company information corresponding to the user's desired conditions and emotion data using a big database.

[2146] (Claim 3)

[2147] 10. The system of claim 1, further comprising means for generating and updating the candidate list using a generative AI model.

[2148] "Application example 2 when combining emotion engines"

[2149] New invention claims

[2150] (Claim 1)

[2151] A means for inputting desired conditions;

[2152] A means for generating an initial candidate list based on user preferences;

[2153] a means for displaying the initial candidate list and receiving user feedback and additional requirements;

[2154] A means to reassess and update the shortlist based on feedback and additional criteria;

[2155] a means for displaying the re-evaluated candidate list and accepting a final selection from the user;

[2156] A means to assist the entry procedure for the final selected subjects;

[2157] an emotion recognition means for recognizing a user's emotion and collecting data thereof;

[2158] a means for adjusting the candidate list based on the emotional data and the desired criteria;

[2159] A system including:

[2160] (Claim 2)

[2161] The system according to claim 1, further comprising means for searching for information corresponding to the user's desired conditions using a big database.

[2162] (Claim 3)

[2163] 10. The system of claim 1, further comprising means for generating and updating the candidate list using a generative AI model. [Explanation of symbols]

[2164] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for inputting desired conditions; A means for generating an initial candidate list based on user preferences; a means for displaying the initial candidate list and receiving user feedback and additional requirements; A means to reassess and update the shortlist based on feedback and additional criteria; a means for displaying the re-evaluated candidate list and accepting a final selection from the user; A means of assisting the application process for the final selected companies; A system including:

2. The system according to claim 1, further comprising means for searching for company information corresponding to the user's desired conditions using a big database.

3. 10. The system of claim 1, further comprising means for generating and updating the candidate list using a generative AI model.

Images