System

Abstract

A system is provided.SOLUTION: A system comprising: means for allowing a user to input experience, a field of interest, and hobbies and preferences; means for transmitting the inputted information to a server; means for storing the inputted information received by the server in storage means; means for generating recommendation information by a generation AI based on the information stored in the storage means; means for transmitting the generated recommendation information to the user; and means for allowing the user to browse the transmitted recommendation information.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] In today's job-hunting process, students face the challenge of finding the right company or industry based on their experience and interests. Obtaining this information requires a lot of time and resources, and as a result, many students end up making job decisions based on insufficient information. This can lead to students finding a company or industry that is not a good fit for them, leading to early job turnover and reduced workplace satisfaction. Therefore, there is a need for support to help students find the right company or industry efficiently and accurately. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for allowing a user to input their experience, areas of interest, and hobbies and preferences, a means for transmitting the input information to a server, a means for the server to store the input information received by the server in a storage means, a means for generating recommendation information using a generation AI based on the information stored in the storage means, a means for transmitting the generated recommendation information to a user, and a means for the user to view the transmitted recommendation information. This allows students to receive recommendations for appropriate companies and industries based on their experience and interests. In particular, the generation AI analyzes the user's input information and recommends the most suitable companies and industries, enabling students to efficiently find a job that suits them.

[0006] "User" refers to an individual who uses the system to receive company and industry recommendations based on their experience and interests.

[0007] "Experience" refers to the professional or academic achievements and skills that a user has accumulated in the past.

[0008] "Areas of interest" refers to industries or technical fields in which the user is interested and in which he or she would like to work professionally in the future.

[0009] "Hobbies and tastes" refers to the user's preferences in daily life and the activities they engage in for fun.

[0010] "Means" refer to the specific methods or tools used to achieve a particular goal.

[0011] A "terminal" refers to an electronic device that allows a user to input information and communicate with a server.

[0012] "Server" refers to a computer system that receives and processes information sent by users and generates recommendation information using generation AI.

[0013] "Storage means" refers to data storage for storing user information received by the server.

[0014] "Generative AI" refers to artificial intelligence that uses algorithms to recommend appropriate companies and industries based on information provided by the user.

[0015] "Recommendation information" refers to suggestions and advice about appropriate companies and industries generated by the generative AI based on the user's experience and interests.

[0016] A "prompt" refers to an instruction or question given to the generating AI based on user input. [Brief explanation of the drawings]

[0017] [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

[0018] 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.

[0019] First, the terms used in the following description will be explained.

[0020] 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).

[0021] 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.

[0022] 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.

[0023] 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.

[0024] 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."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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."

[0038] This invention is a system that utilizes generative AI to support students in their job hunting activities. Users can input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server to obtain recommended information on companies and industries that suit them. This system includes the following means.

[0039] User input

[0040] Users enter information such as their experience, areas of interest, hobbies, etc. into a form on the device. For example, they can enter "3 years of programming experience" in the experience section, "data science" in the area of ​​interest, and "reading and traveling" in the hobbies and hobbies section.

[0041] Sending and storing information

[0042] The device sends the above input information to the server as a POST request. When the server receives this request, it stores the obtained information in variables and saves it in the UserProfile model. For example, the information is recorded as follows:

[0043] Experience: 3 years of programming experience

[0044] Area of ​​interest: Data Science

[0045] Hobbies: Reading and traveling

[0046] Generating recommendations

[0047] The server generates a prompt based on the user information stored in the storage device and sends an API request to the AI ​​generator. This prompt includes the user's experience, areas of interest, and hobbies and preferences. The AI ​​generator then uses this information to create recommendations for appropriate companies and industries. For example, the following response might be generated:

[0048] “Based on your profile, you would be interested in companies where you can work in the field of data science. Specifically, companies with a reputation for being a data analyst, machine learning engineer, or data scientist.”

[0049] Sending and displaying recommendations

[0050] The server sends the generated recommendation information to the user in JSON format, and the device displays the received recommendation information on the screen so that the user can view it.

[0051] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[0052] Specific examples

[0053] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[0054] 1. Sending input information

[0055] The user enters information into a form on the terminal and sends it to the server.

[0056] 2. Storage of Information

[0057] The server stores the received information in the UserProfile model.

[0058] 3. Requests to Generative AI

[0059] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[0060] 4. Receiving Recommendations

[0061] Receive the response from the generation AI and extract the recommendation information.

[0062] 5. Display of Recommendations

[0063] The extracted information is sent in JSON format to the user's device, and the device displays the recommended information.

[0064] This allows users to receive specific recommendations such as "companies where you can work in the field of data science" or "companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[0065] The processing flow will be explained below.

[0066] Step 1:

[0067] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into a form displayed on the terminal. For example, "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[0068] Step 2:

[0069] The terminal sends the entered information to the server. The entered information is sent in the form of a POST request. An example of the data sent is as follows:

[0070] json

[0071] {

[0072] "experience": "3 years of programming experience",

[0073] "interests": "data science",

[0074] "hobbies": "reading and traveling"

[0075] }

[0076] Step 3:

[0077] The server receives the POST request and receives the input information. Specifically, it stores the data sent by the user in a variable using the request.POST method.

[0078] Step 4:

[0079] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, and preferences in a database. An example of the storage process is as follows:

[0080] python

[0081] user_profile = UserProfile(

[0082] experience=request.POST['experience'],

[0083] interests=request.POST['interests'],

[0084] hobbies=request.POST['hobbies']

[0085] )

[0086] user_profile.save()

[0087] Step 5:

[0088] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[0089] python

[0090] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}"

[0091] Step 6:

[0092] The server sends a prompt to the Generator AI. Specifically, it sends a request to the Generator AI's API, asking for a response to recommend companies and industries suitable for the user. An example request is as follows:

[0093] python

[0094] response = openai.Completion.create(

[0095] engine="text-davinci-003",

[0096] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[0097] max_tokens=150

[0098] )

[0099] Step 7:

[0100] The server receives a response from the generative AI, which includes company and industry recommendations based on the user's input. For example, the response might include recommendations like:

[0101] "You'll be interested in companies where you can work in the data science field. For example, there are companies that are well-known for being data analysts, machine learning engineers, and data scientists."

[0102] Step 8:

[0103] The server extracts the generated AI's response as recommendation information and sends it back to the user's device in JSON format. An example of sending the extracted information as a JSON response is as follows:

[0104] python

[0105] return JsonResponse({'recommendations': recommendations})

[0106] Step 9:

[0107] The device receives the JSON response from the server, analyzes the received recommendation information, and displays it on the screen.

[0108] Step 10:

[0109] The user browses the recommendations displayed on the device screen, providing specific information to help them find the right company or industry based on their experience and interests.

[0110] These are the processing steps of this system, which allows users to proceed with their job search effectively and efficiently.

[0111] Example 1

[0112] 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."

[0113] Conventional job-hunting support systems have difficulty recommending appropriate companies and industries based on users' experiences and interests, forcing students to search through a wide variety of information to find the right fit. Furthermore, the methods for inputting information and displaying recommended information are limited, resulting in a suboptimal user experience.

[0114] 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.

[0115] In this invention, the server includes a means for allowing the user to input their experiences, areas of interest, and hobbies and preferences, a means for sending prompts to the generation AI, and a means for organizing the recommendation information received from the generation AI, thereby enabling the user to receive accurate and appropriate recommendations for companies and industries based on their own information.

[0116] "User" refers to an individual who uses the system to receive support in their job search.

[0117] "Experience" refers to the knowledge, skills, and work experience that a user has accumulated in the past.

[0118] "Areas of interest" refers to a particular industry or research area that interests a user.

[0119] "Hobbies" refers to activities and tendencies that a user personally enjoys.

[0120] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to input information.

[0121] "Server" refers to a computer system responsible for receiving, storing, and processing information sent by users.

[0122] "Storage means" refers to a database or storage system for saving user information on a server.

[0123] "Generative AI" refers to an artificial intelligence model that generates recommendation information based on user input information.

[0124] A "prompt sentence" refers to an input sentence that provides the necessary information to the generation AI.

[0125] "Recommended information" refers to information about appropriate companies and industries generated by the generating AI based on information input by the user.

[0126] This invention is a system that uses generative AI to support students in their job hunting. Users input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server, allowing them to obtain recommended information on companies and industries that suit them.

[0127] Hardware and software used

[0128] The system uses the following hardware and software:

[0129] Terminal: A device such as a computer or smartphone on which a user inputs information and views recommendations.

[0130] Server: A computer system that processes information received from the user, sends prompts to the generation AI, and sends recommendation information to the user.

[0131] Storage means: A database or storage system on the server for saving user input information

[0132] Generative AI: An artificial intelligence model that generates recommendations based on user input (e.g., GPT-3)

[0133] Data processing and calculation

[0134] User input

[0135] Users use a form on the device to enter information about their experience, areas of interest, hobbies, etc. For example, a user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[0136] Sending and storing information

[0137] The device converts the input information into JSON format and sends it to the server as a POST request. The server analyzes the received information, stores it in variables, and saves it in a storage means (database). For example, the following information is saved:

[0138] Experience: 3 years of programming experience

[0139] Area of ​​interest: Data Science

[0140] Hobbies: Reading and traveling

[0141] Generating recommendations

[0142] The server generates a prompt to send to the AI ​​based on the user information stored in the memory. This prompt has the following format:

[0143] User Information:

[0144] Experience: 3 years of programming experience

[0145] Area of ​​interest: Data Science

[0146] Hobbies: Reading and traveling

[0147] Recommend companies and industries that fit this user.

[0148] The server sends this prompt to the generation AI, which generates recommendation information for appropriate companies and industries. The generation AI generates recommendation information based on the prompt and responds to the server.

[0149] Sending and displaying recommendations

[0150] The server organizes the recommendation information received from the generation AI and sends it in JSON format to the user's device, where it is displayed for viewing by the user.

[0151] Specific examples

[0152] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[0153] 1. The user enters information into a form on the terminal and sends it to the server.

[0154] 2. The server stores the received information in a storage means.

[0155] 3. The server generates a prompt based on the stored information and sends a request to the generation AI.

[0156] 4. The generation AI generates recommendation information and responds to the server.

[0157] 5. The server organizes the recommendation information and sends it to the user's device.

[0158] 6. The device displays the recommended information and the user views it.

[0159] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] Step 1:

[0162] The user uses a device to input information about their experience, areas of interest, hobbies, and preferences. The input information may be "3 years of programming experience," "interest in data science," or "hobbies are reading and traveling." The input data is converted into JSON format.

[0163] Step 2:

[0164] The device sends the entered information to the server as a POST request in JSON format. For example, the following JSON data is sent to the server:

[0165] json

[0166] {

[0167] "experience": "3 years of programming experience",

[0168] "interest": "data science",

[0169] "hobbies": "reading and traveling"

[0170] }

[0171] Input: User-entered data

[0172] Output: POST request in JSON format

[0173] Step 3:

[0174] The server receives the POST request, analyzes its contents, and stores them in variables. The server then saves this information in a storage means (database). A database operation is performed to save the information in the storage means.

[0175] Input: User information in JSON format

[0176] Output: User information stored in the database

[0177] Step 4:

[0178] The server generates a prompt sentence to send to the generation AI based on the user information stored in the storage means. The prompt sentence is specifically constructed based on the user information. For example, the following prompt sentence is generated:

[0179] User Information:

[0180] Experience: 3 years of programming experience

[0181] Area of ​​interest: Data Science

[0182] Hobbies: Reading and traveling

[0183] Recommend companies and industries that fit this user.

[0184] Input: User information stored in the database

[0185] Output: Generated prompt statement

[0186] Step 5:

[0187] The server sends the generated prompt to the AI's API, creates an API request, and sends it to the AI ​​model (e.g., GPT-3). At this time, the server formats the prompt to fit the AI's needs.

[0188] Input: Generated prompt text

[0189] Output: API request

[0190] Step 6:

[0191] The Generator AI receives API requests from the server, processes them, and generates recommendations for companies and industries suitable for the user. The following data is returned as recommendations:

[0192] json

[0193] {

[0194] "recommendations": [

[0195] "Companies where you can thrive in the field of data science,"

[0196] "A well-known company for data analysts, machine learning engineers, and data scientists"

[0197] ]

[0198] }

[0199] Input: API request

[0200] Output: Recommendation

[0201] Step 7:

[0202] The server analyzes the recommendation information received from the AI ​​generator and sends it to the user's device in JSON format, where data may be reformatted or filtered.

[0203] Input: Recommendation information received from the generation AI

[0204] Output: Recommendations in JSON format

[0205] Step 8:

[0206] The device displays the JSON-formatted recommendation information received from the server on its screen, and the user can view the recommended companies and industry information on the device screen.

[0207] Input: Recommendation information in JSON format

[0208] Output: Recommendations displayed on screen

[0209] (Application example 1)

[0210] 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."

[0211] In today's job-hunting environment, students are faced with a vast amount of information to find the right company or industry, making it difficult to effectively select candidates. With the proliferation of online job fairs and company information sessions, students lack the means to obtain information in a virtual space and connect with companies that are right for them. This problem prevents students from finding the right company and reduces the efficiency of their job-hunting process.

[0212] 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.

[0213] In this invention, the server includes means for having the user input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information to the server, and means for storing the input information received by the server in storage means. This allows the server to view the transmitted recommendation information, means for the user to visit recommended company booths in the virtual space and participate in company information sessions and interview simulations, and means for transmitting the generated recommendation information to the user, making it possible for the generation AI to recommend industries or companies based on the user's input information.

[0214] "Users" refer to individuals who use the system, particularly students looking for jobs.

[0215] "Experience" refers to the skills and knowledge that a user has acquired through study, work, etc.

[0216] "Areas of interest" refers to academic or industrial fields in which the user is interested.

[0217] "Hobbies and preferences" refer to the activities and interests that a user likes to engage in in their daily life.

[0218] A "server" is a computer system that receives, stores, and processes information from users.

[0219] "Storage means" refers to a database or storage system for saving information input by a user.

[0220] "Generative AI" refers to artificial intelligence that generates appropriate recommendation information based on user information.

[0221] "Recommendation information" refers to information about companies and industries that is generated by the generative AI and presented to users.

[0222] The "viewing means" refers to a method by which a user can check the recommended information through a terminal or device.

[0223] "Virtual space" refers to a virtual reality environment created by computer simulation.

[0224] A "company booth" is anything other than a virtual location within a virtual space where a specific company gives a company presentation or conducts interviews.

[0225] A "company information session" is an event where a company introduces its company overview, vision, recruitment information, etc. to students.

[0226] An "interview simulation" is an interactive process that allows users to virtually experience an interview with a company.

[0227] A "prompt" is text that provides questions or instructions to the generating AI based on user information.

[0228] The present invention is a system for enabling students to more effectively conduct their job hunting activities.

[0229] The system starts when the user inputs information such as their experiences, areas of interest, hobbies, and preferences via a terminal. This terminal can be a smartphone or a head-mounted display (HMD). The input information is sent to the server and stored in the server's memory.

[0230] The server generates a prompt based on the stored information and sends an API request to the generative AI. This API uses OpenAI's generative AI model. An example of a generated prompt is, "User experience: 3 years of programming experience\nArea of ​​interest: Data science\nHobbies: Reading and travel\nBased on this, please generate recommendations for appropriate companies and industries."

[0231] Based on this, the AI ​​generates recommendations for companies and industries that are suitable for the user. The recommendation information is sent from the server in JSON format to the user's device, where it is displayed.

[0232] Furthermore, users can visit recommended company booths in the virtual space and participate in company information sessions and interview simulations. This virtual space is realized using an HMD.

[0233] Specifically, the process is as follows:

[0234] 1. The user uses a smartphone or HMD to input information such as their experiences, areas of interest, hobbies, and preferences.

[0235] 2. The terminal sends the entered information to the server.

[0236] 3. The server stores the received information in a storage means.

[0237] 4. The server generates a prompt for the AI ​​based on the stored information and sends an API request.

[0238] 5. The generation AI generates recommendation information for appropriate companies and industries and returns it to the server.

[0239] 6. The server sends the recommendation information to the user's device, which displays it.

[0240] 7. Users visit the recommended company booths in the virtual space and participate in company information sessions and interview simulations.

[0241] The specific hardware used includes smartphones and HMDs (e.g., Oculus Rift), and the servers are general cloud servers (e.g., AWS EC2).The software used includes Flask (a Python framework), OpenAI's generative AI API, and SQL.

[0242] This allows students to receive recommendations for suitable companies and industries based on their experience and interests, and conduct more effective job hunting through virtual company information sessions and interview experiences.

[0243] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0244] Step 1:

[0245] Users use a smartphone or HMD to input information such as their experience, areas of interest, and hobbies and preferences. This input information includes "3 years of programming experience" as experience, "data science" as an area of ​​interest, and "reading and traveling" as hobbies and preferences. The device then captures this input information into a form.

[0246] Step 2:

[0247] The terminal sends the information entered by the user to the server. Specifically, the input information is sent to the server as a POST request. The data format when sent is JSON, as shown below.

[0248] JSON

[0249] {

[0250] "experience": "3 years of programming experience",

[0251] "interest": "data science",

[0252] "hobby": "reading and traveling"

[0253] }

[0254] Step 3:

[0255] The server saves the received information in a storage device. The server analyzes the received JSON data and stores the information in the corresponding fields. Specifically, it is stored in the UserProfile model. The data processing here involves storing the JSON data fields in variables and inserting them into the corresponding columns in the database.

[0256] Step 4:

[0257] The server generates a prompt for the AI ​​based on the information stored in the storage means. Specifically, it generates the following prompt sentence:

[0258] "User experience: 3 years of programming experience.\nInterests: Data science.\nHobbies: Reading and travel.\nBased on this, generate recommendations for appropriate companies and industries."

[0259] Step 5:

[0260] The server sends an API request containing the generated prompt to the AI ​​generator. This uses the OpenAI AI generator API. The API request includes the prompt text. When the server sends this request, the AI ​​generator responds.

[0261] Step 6:

[0262] Based on the prompt received, the generation AI generates recommendations for companies and industries that are suitable for the user. The generation AI performs natural language processing and data analysis internally to generate appropriate recommendations. This recommendation information is returned in the form of a statement such as, "Companies where you can work in the field of data science. Specifically, companies that are well-known for data analysts, machine learning engineers, and data scientists are considered."

[0263] Step 7:

[0264] The server sends the recommendation information received from the generation AI to the user. Specifically, it converts the generated recommendation information into JSON format and sends it to the device. The JSON data sent is in the following format.

[0265] JSON

[0266] {

[0267] "recommendations": "Companies where you can work in the field of data science. Specifically, companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[0268] }

[0269] Step 8:

[0270] The device displays the received recommendation information on its screen. The user can view the information and visit company booths in the virtual space as needed. The virtual space is controlled using an HMD, allowing users to participate in company information sessions and interview simulations.

[0271] 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.

[0272] This invention is a system that utilizes generative AI and an emotion engine to support students in their job hunting. Users input their experiences, areas of interest, and hobbies and preferences into a terminal, and the emotion engine recognizes the user's emotions at the time of input, generating more precisely customized recommendation information. We will explain the specific system flow and the operation of each element.

[0273] User input

[0274] Users enter their experience, areas of interest, and hobbies into a form on their device. For example, they can enter "3 years of programming experience," "Interested in data science," or "My hobbies are reading and traveling."

[0275] Information transmission and emotion recognition

[0276] When the device sends the above input information to the server as a POST request, the emotion engine recognizes the emotion of the user when they input the information. The emotion engine analyzes the user's voice and facial expressions to evaluate their emotional state. For example, if the input is made with a happy expression, it is recognized as "positive," and if it is made with a confused expression, it is recognized as "negative."

[0277] Information storage

[0278] The server receives the POST request and stores the input information and the evaluation results of the emotion engine in a storage device. For example, the following information is recorded:

[0279] Experience: 3 years of programming experience

[0280] Area of ​​interest: Data Science

[0281] Hobbies: Reading and traveling

[0282] Emotional state: Positive

[0283] Generating recommendations

[0284] The server creates a prompt for the generation AI based on the information stored in the memory and sends an API request. This prompt includes the user's experience, areas of interest, hobbies, and preferences, as well as the emotional state evaluated by the emotion engine. The generation AI uses this information to create recommendations for appropriate companies and industries. If the emotional state is positive, the system will make recommendations in a positive tone, and if it is negative, the system will use more detailed and reassuring language than usual.

[0285] Sending and displaying recommendations

[0286] The server sends the generated recommendation information in JSON format to the user's device, which then displays the received recommendation information on the screen for the user to view.

[0287] Specific examples

[0288] As a concrete example, if a user inputs "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and a positive emotional state is recognized, the following processing will occur:

[0289] 1. Information input and emotion recognition

[0290] The user enters information into a form on the device, and the emotion engine recognizes positive emotional states.

[0291] 2. Transmission and storage of information

[0292] The terminal transmits the information and the recognized emotional state to a server, which stores it in a storage means.

[0293] 3. Requests and Responses to Generative AI

[0294] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[0295] The generative AI responds and creates recommendations with a positive tone.

[0296] For example: "You'd be well-suited to a company where you can grow in data science. Consider a career as a data analyst or machine learning engineer."

[0297] 4. Display of recommendation information

[0298] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[0299] The system allows users to receive relevant and customized recommendations for companies and industries based on their experience, interests, and emotional state, making their job search more effective.

[0300] The processing flow will be explained below.

[0301] Step 1:

[0302] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into the form displayed on the terminal. For example, the user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[0303] Step 2:

[0304] The device activates an emotion engine to recognize the user's emotions when they input. The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice to determine their emotional state. For example, it classifies emotional states as positive, negative, or neutral.

[0305] Step 3:

[0306] The device sends the input information and the recognized emotional state to the server. The information is sent to the server as a POST request, with example data as follows:

[0307] json

[0308] {

[0309] "experience": "3 years of programming experience",

[0310] "interests": "data science",

[0311] "hobbies": "reading and traveling",

[0312] "emotion": "positive"

[0313] }

[0314] Step 4:

[0315] The server receives the POST request and stores the input information and emotional state in variables. For example, it processes the data as follows:

[0316] python

[0317] experience = request.POST['experience']

[0318] interests = request.POST['interests']

[0319] hobbies = request.POST['hobbies']

[0320] emotion = request.POST['emotion']

[0321] Step 5:

[0322] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, preferences, and emotional state in a database. An example of the storage process is as follows:

[0323] python

[0324] user_profile = UserProfile(

[0325] experience=experience,

[0326] interests=interests,

[0327] hobbies=hobbies,

[0328] emotion=emotion

[0329] )

[0330] user_profile.save()

[0331] Step 6:

[0332] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[0333] python

[0334] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}, Emotion: {user_profile.emotion}"

[0335] Step 7:

[0336] The server sends a prompt to the Generator AI, which makes a request to the Generator AI's API for recommendations of suitable companies and industries. An example request is as follows:

[0337] python

[0338] response = openai.Completion.create(

[0339] engine="text-davinci-003",

[0340] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[0341] max_tokens=150

[0342] )

[0343] Step 8:

[0344] The server receives the response from the AI ​​generator and extracts the recommendation information. For example, the following recommendation may be generated:

[0345] “Based on your profile, you may be interested in companies that offer jobs in the data science field. You may also consider a career as a data analyst or machine learning engineer.”

[0346] Step 9:

[0347] The server sends the generated recommendation information to the user's device. It also returns the information in JSON format to the device. Example:

[0348] python

[0349] return JsonResponse({'recommendations': recommendations})

[0350] Step 10:

[0351] The device receives the JSON response from the server and displays the recommended information on the screen. The user can then check the recommended information displayed on the device screen.

[0352] Step 11:

[0353] The user browses the recommendation information, which allows the user to obtain recommended information on companies and industries based on their own experiences, interests, and emotional state.

[0354] These are the processing steps of this system, which allows users to receive detailed support tailored to their emotional state while effectively and efficiently pursuing their job search.

[0355] Example 2

[0356] 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."

[0357] Conventional job-hunting support systems can only provide simple recommendations based on user input, and have the problem of being unable to provide customized support that takes into account the user's emotional state. This limits the ability of job seekers to find companies and industries that are more suitable for them.

[0358] 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 allowing a user to input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information and the user's emotional state to the server, means for storing the input information and the emotional state received by the server in a storage means, means for generating recommendation information by a generation AI based on the information and the emotional state stored in the storage means, means for transmitting the generated recommendation information to the user, and means for the user to view the transmitted recommendation information. This makes it possible to provide more sophisticated and customized recommendation information that takes into account the user's emotional state.

[0359] "User" refers to an individual who uses the system to input their experiences, areas of interest, and hobbies and preferences and receive recommendation information.

[0360] "Experience" refers to information indicating knowledge and skills related to work, learning, projects, etc. that a user has accumulated in the past.

[0361] "Areas of interest" refers to the job areas or research topics in which the user is interested.

[0362] "Hobbies and preferences" refers to information that indicates the activities that a user enjoys on a daily basis and the things that the user likes.

[0363] "Emotional state" refers to the psychological and emotional state of the user when inputting information, and is classified as positive, negative, or the like.

[0364] "Device" refers to the electronic device used by a user to input information and receive recommendation information, such as a PC, smartphone, or tablet.

[0365] "Server" refers to a computer system that receives and stores information from users, creates recommendation information based on the generation AI, and sends it to users.

[0366] "Storage means" refers to a database or storage device used by the server to store the user's input information and emotional state.

[0367] "Generative AI" refers to an artificial intelligence module that creates appropriate recommendations based on the user's input information and emotional state.

[0368] A "prompt" refers to an instruction or request sent to the generating AI, including the user's input information and emotional state.

[0369] "Recommendation information" refers to information about companies and industries recommended to users that is created by the generative AI based on the user's input information and emotional state.

[0370] This invention is a system that uses a generative AI and an emotion engine to help users conduct job hunting more effectively. Specific embodiments of this system are described below.

[0371] User input

[0372] Users use their own devices (PC, smartphone, tablet, etc.) to enter their experiences, areas of interest, and hobbies and preferences. This input is done using an HTML form, and data is collected through UI elements such as text boxes and drop-down lists. For example, users can enter "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[0373] Information transmission and emotion recognition

[0374] Once the user has finished entering the information, the device sends this information to the server as a POST request. During this transmission process, the device's built-in emotion recognition software recognizes the user's emotional state. Emotion recognition is performed using the device's built-in camera and microphone to capture the user's facial expression and voice data, and then uses an emotion recognition algorithm (such as OpenCV or Microsoft Azure's Emotion API). The emotional state is evaluated as "positive" or "negative."

[0375] Information storage

[0376] The server receives the information and emotional state sent by the user and stores them in a database (e.g., PostgreSQL). The stored information includes:

[0377] Experience: 3 years of programming experience

[0378] Area of ​​interest: Data Science

[0379] Hobbies: Reading and traveling

[0380] Emotional state: Positive

[0381] Generating recommendations

[0382] The server creates and sends prompts to the AI ​​based on the information stored in the memory. These prompts include the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the prompt text might look like this:

[0383] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[0384] The server sends this prompt to a generative AI (e.g., OpenAI's GPT-3 model), which then generates recommendations for appropriate companies and industries.

[0385] Sending and displaying recommendations

[0386] The server sends the recommendation information received from the generation AI in JSON format to the user's device. The device analyzes the received recommendation information and displays it on the screen. The display uses JavaScript to dynamically update the UI, allowing the user to view information about recommended companies and industries.

[0387] Specific examples

[0388] For example, if a user enters "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and the emotional state is recognized as positive, the system will act as follows:

[0389] 1. Information input and emotion recognition

[0390] The user enters information into a form on the device, and emotion recognition software recognizes positive emotional states.

[0391] 2. Transmission and storage of information

[0392] The device sends the information and the perceived emotional state to a server, which stores it in a database.

[0393] 3. Requests and Responses to Generative AI

[0394] The server creates a prompt and sends an API request to the generating AI.

[0395] The generative AI creates recommendations in a positive tone, such as, "You'd be well suited to a company where you can grow in the field of data science. You might also want to consider a career as a data analyst or machine learning engineer."

[0396] 4. Sending and Displaying Recommendations

[0397] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[0398] The system allows users to receive customized company and industry recommendations based on their experience, interests, and emotional state, enabling them to conduct a more effective job search.

[0399] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0400] Step 1: Enter your information

[0401] Users enter their experiences, areas of interest, and hobbies and preferences into a form on their device (PC, smartphone, tablet, etc.). This form is set up in HTML format, and data is collected through UI elements such as text boxes and drop-down lists. For example, a user might enter "3 years of programming experience," "Interested in data science," and "My hobbies are reading and traveling." The entered information is temporarily saved in the device's browser.

[0402] input:

[0403] User experience, areas of interest, hobbies and preferences

[0404] output:

[0405] Data stored on the device as user-entered information

[0406] Step 2: Information transmission and emotion recognition

[0407] The device sends the information entered by the user to the server as a POST request. At the same time, the device's built-in camera and microphone capture the user's facial expression and voice data, which are then sent to emotion recognition software (such as OpenCV or Microsoft Azure's Emotion API). This emotion recognition algorithm analyzes the user's emotional state at the time of input and classifies it as positive, negative, etc.

[0408] input:

[0409] User experience, areas of interest, hobbies and preferences

[0410] User's facial expression data, voice data

[0411] output:

[0412] User data and emotional state sent to the server as a POST request

[0413] Step 3: Save your information

[0414] The server receives POST requests from the device and processes the input information and emotional state. This information is then stored in a database such as PostgreSQL. The data stored includes the user's experience, areas of interest, hobbies, and emotional state.

[0415] input:

[0416] User input information, emotional state

[0417] output:

[0418] Information stored in a database

[0419] Step 4: Generate a prompt statement

[0420] The server creates a prompt sentence to be sent to the generation AI based on the information stored in the storage means. This prompt sentence includes the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the following prompt sentence is generated:

[0421] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[0422] input:

[0423] User information and emotional state stored in the database

[0424] output:

[0425] Prompt to send to the generation AI

[0426] Step 5: Generate recommendations

[0427] The server sends a prompt to a generative AI (e.g., OpenAI's GPT-3 model), which generates recommendations for companies and industries suitable for the user based on the prompt. The generated recommendations contain positive tones and specific suggestions.

[0428] input:

[0429] Prompt statement

[0430] output:

[0431] Generated recommendations

[0432] Step 6: Submit and view your recommendations

[0433] The server receives the recommendation information returned by the generation AI, converts it to JSON format, and sends it to the user's device. The device then analyzes the received recommendation information and generates HTML elements to display on the screen. Dynamic UI updates are performed using JavaScript, allowing the user to view information on recommended companies and industries.

[0434] input:

[0435] Generated recommendations

[0436] output:

[0437] Recommendation information displayed on the user's device

[0438] Through the above processing steps, users can receive customized recommendation information based on their experiences, interests, hobbies, preferences, and emotional state, allowing them to conduct a more effective job search.

[0439] (Application example 2)

[0440] 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."

[0441] Conventional job-hunting support systems can provide recommended information based on a user's experience, areas of interest, and hobbies and preferences, but they cannot provide customized recommended information that takes into account the user's emotional state. This makes it difficult for users to obtain recommended information that is truly interesting and psychologically appropriate.

[0442] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for allowing a user to input their experiences, areas of interest, and hobbies and preferences; means for transmitting the input information to the server; means for storing the input information received by the server in a storage means; means for generating recommendation information using a generation AI based on the information stored in the storage means; means for transmitting the generated recommendation information to the user; means for the user to view the sent recommendation information; means for recognizing the user's emotional state from voice and facial expressions using an emotion engine; and means for generating recommendation information taking the emotional state into consideration. This enables the user to obtain customized recommendation information based not only on their own experiences and interests but also on their current emotional state.

[0443] A "user" is an entity that uses the system to input their experiences, areas of interest, hobbies, and preferences.

[0444] "Experience" is information indicating the activities and skills that the user has engaged in in the past.

[0445] "Areas of interest" is information that indicates areas of expertise or topics that interest a user.

[0446] "Hobbies and preferences" is information that indicates the activities and preferences that a user enjoys on a daily basis.

[0447] A "server" is a central device that receives, stores, and processes information sent by users.

[0448] "Storage means" refers to data storage for saving input information received by the server.

[0449] "Generation AI" is artificial intelligence that generates recommendation information based on information stored in a storage device.

[0450] "Recommended information" is information on appropriate content, industries, companies, etc. provided by the generation AI based on user input information.

[0451] An "emotion engine" is an algorithm or system that analyzes a user's voice and facial expressions to assess their emotional state.

[0452] A "prompt" is data containing information such as a user's experience and emotional state that is used as input to a generative AI.

[0453] "Content" refers to information such as movies, books, podcasts, etc. that is provided as recommended information.

[0454] This invention is a system that provides recommended content based on a user's experience, areas of interest, hobbies, preferences, and current emotional state. This system collects user input information, sends it to a server, and generates customized recommendation information using a generative AI and an emotion engine.

[0455] The server performs processing using the following hardware and software. For hardware, the server uses a cloud server equipped with high-performance data storage and processors. For software, a web framework is built using Flask, emotion recognition is performed using EmotionEngine, and recommendation processing is performed using an AIRecommender generative AI model. A database is also used as storage.

[0456] First, a user uses a smartphone or desktop device to enter information about their experiences, areas of interest, and hobbies and preferences. Specifically, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." At the same time, the user's current emotional state is also captured using voice input or facial recognition.

[0457] The device sends the information entered by the user and the collected emotional data to the server. Upon receiving this information, the server analyzes the emotional state using the Emotion Engine and stores all information along with the analysis results in a database. The server then generates a prompt based on the storage means and sends the prompt to the generation AI. Based on this prompt, the generation AI generates recommended content that is optimal for the user.

[0458] The generated recommendation content is sent from the server to the user's device and displayed on the device screen. For example, if the user expresses positive emotions, the server will display recommended content with a positive tone, such as "recommended action movies," "fantasy web novels," and "related podcasts."

[0459] For example, the following prompt is generated and sent to the generator AI:

[0460] User Information:

[0461] Experience: I watch a lot of action movies

[0462] Areas of interest: Fantasy

[0463] Hobbies and interests: Reading

[0464] Emotional state: Positive

[0465] Using this prompt, the AI ​​generates recommendations for movies, books, podcasts, and other content that are best suited to the user, and sends them to the user's device, allowing the user to obtain customized recommendations based on their interests and emotional state.

[0466] The invention is characterized by the fact that a recommendation system using generative AI provides customized information that takes into account the user's emotions, making it easier for users to efficiently discover content that will provide them with greater satisfaction.

[0467] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0468] Step 1:

[0469] Users use their smartphones or desktop devices to enter information about their experiences, areas of interest, and hobbies. For example, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." Input is done using pull-down menus and free text format.

[0470] Input: User experience, areas of interest, hobbies and preferences

[0471] Output: User input information

[0472] Step 2:

[0473] After the user completes the input, the Emotion Engine recognizes the user's emotional state at that time using voice input or facial recognition. The Emotion Engine analyzes voice tone and facial expression data to classify the emotional state as positive, negative, neutral, etc.

[0474] Input: User voice or facial recognition data

[0475] Output: User's emotional state

[0476] Step 3:

[0477] The device sends the user-entered information and the recognized emotional state to the server, structured as a POST request via the API.

[0478] Input: User input information, user emotional state

[0479] Output: API request to the server

[0480] Step 4:

[0481] The server stores the received inputs and emotional states in a database, which organizes them for each user and later uses them to send prompts to the generative AI model.

[0482] Input: API request data (user input information, emotional state)

[0483] Output: User information stored in the database

[0484] Step 5:

[0485] The server creates prompts based on the information stored in the database and sends API requests to the generative AI model (AIRecommender). The prompts include the user's experience, areas of interest, hobbies, and emotional state.

[0486] Input: Database user information

[0487] Output: prompts to the generative AI model

[0488] Step 6:

[0489] The generative AI model receives the prompts and generates optimal recommended content based on the user's information and emotional state, which is returned in JSON format and sent to the server.

[0490] Input: prompt to generative AI model

[0491] Output: Recommended content (JSON format)

[0492] Step 7:

[0493] The server then sends the generated recommended content to the device, which then displays it to the user, who can then browse the recommended information for movies, books, podcasts, etc. on the screen.

[0494] Input: Recommended content (JSON format)

[0495] Output: Recommendation information displayed on the user's device

[0496] Through the above processing steps, users can receive content recommendations that are customized according to their interests and emotional state. This system allows users to efficiently discover content that will provide them with greater satisfaction.

[0497] 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.

[0498] 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.

[0499] 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.

[0500] [Second embodiment]

[0501] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0502] 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.

[0503] 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).

[0504] 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.

[0505] 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.

[0506] 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).

[0507] 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.

[0508] 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.

[0509] 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.

[0510] 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.

[0511] 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.

[0512] 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."

[0513] This invention is a system that utilizes generative AI to support students in their job hunting activities. Users can input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server to obtain recommended information on companies and industries that suit them. This system includes the following means.

[0514] User input

[0515] Users enter information such as their experience, areas of interest, hobbies, etc. into a form on the device. For example, they can enter "3 years of programming experience" in the experience section, "data science" in the area of ​​interest, and "reading and traveling" in the hobbies and hobbies section.

[0516] Sending and storing information

[0517] The device sends the above input information to the server as a POST request. When the server receives this request, it stores the obtained information in variables and saves it in the UserProfile model. For example, the information is recorded as follows:

[0518] Experience: 3 years of programming experience

[0519] Area of ​​interest: Data Science

[0520] Hobbies: Reading and traveling

[0521] Generating recommendations

[0522] The server generates a prompt based on the user information stored in the storage device and sends an API request to the AI ​​generator. This prompt includes the user's experience, areas of interest, and hobbies and preferences. The AI ​​generator then uses this information to create recommendations for appropriate companies and industries. For example, the following response might be generated:

[0523] “Based on your profile, you would be interested in companies where you can work in the field of data science. Specifically, companies with a reputation for being a data analyst, machine learning engineer, or data scientist.”

[0524] Sending and displaying recommendations

[0525] The server sends the generated recommendation information to the user in JSON format, and the device displays the received recommendation information on the screen so that the user can view it.

[0526] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[0527] Specific examples

[0528] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[0529] 1. Sending input information

[0530] The user enters information into a form on the terminal and sends it to the server.

[0531] 2. Storage of Information

[0532] The server stores the received information in the UserProfile model.

[0533] 3. Requests to Generative AI

[0534] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[0535] 4. Receiving Recommendations

[0536] Receive the response from the generation AI and extract the recommendation information.

[0537] 5. Display of Recommendations

[0538] The extracted information is sent in JSON format to the user's device, and the device displays the recommended information.

[0539] This allows users to receive specific recommendations such as "companies where you can work in the field of data science" or "companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[0540] The processing flow will be explained below.

[0541] Step 1:

[0542] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into a form displayed on the terminal. For example, "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[0543] Step 2:

[0544] The terminal sends the entered information to the server. The entered information is sent in the form of a POST request. An example of the data sent is as follows:

[0545] json

[0546] {

[0547] "experience": "3 years of programming experience",

[0548] "interests": "data science",

[0549] "hobbies": "reading and traveling"

[0550] }

[0551] Step 3:

[0552] The server receives the POST request and receives the input information. Specifically, it stores the data sent by the user in a variable using the request.POST method.

[0553] Step 4:

[0554] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, and preferences in a database. An example of the storage process is as follows:

[0555] python

[0556] user_profile = UserProfile(

[0557] experience=request.POST['experience'],

[0558] interests=request.POST['interests'],

[0559] hobbies=request.POST['hobbies']

[0560] )

[0561] user_profile.save()

[0562] Step 5:

[0563] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[0564] python

[0565] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}"

[0566] Step 6:

[0567] The server sends a prompt to the Generator AI. Specifically, it sends a request to the Generator AI's API, asking for a response to recommend companies and industries suitable for the user. An example request is as follows:

[0568] python

[0569] response = openai.Completion.create(

[0570] engine="text-davinci-003",

[0571] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[0572] max_tokens=150

[0573] )

[0574] Step 7:

[0575] The server receives a response from the generative AI, which includes company and industry recommendations based on the user's input. For example, the response might include recommendations like:

[0576] "You'll be interested in companies where you can work in the data science field. For example, there are companies that are well-known for being data analysts, machine learning engineers, and data scientists."

[0577] Step 8:

[0578] The server extracts the generated AI's response as recommendation information and sends it back to the user's device in JSON format. An example of sending the extracted information as a JSON response is as follows:

[0579] python

[0580] return JsonResponse({'recommendations': recommendations})

[0581] Step 9:

[0582] The device receives the JSON response from the server, analyzes the received recommendation information, and displays it on the screen.

[0583] Step 10:

[0584] The user browses the recommendations displayed on the device screen, providing specific information to help them find the right company or industry based on their experience and interests.

[0585] These are the processing steps of this system, which allows users to proceed with their job search effectively and efficiently.

[0586] Example 1

[0587] 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."

[0588] Conventional job-hunting support systems have difficulty recommending appropriate companies and industries based on users' experiences and interests, forcing students to search through a wide variety of information to find the right fit. Furthermore, the methods for inputting information and displaying recommended information are limited, resulting in a suboptimal user experience.

[0589] 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.

[0590] In this invention, the server includes a means for allowing the user to input their experiences, areas of interest, and hobbies and preferences, a means for sending prompts to the generation AI, and a means for organizing the recommendation information received from the generation AI, thereby enabling the user to receive accurate and appropriate recommendations for companies and industries based on their own information.

[0591] "User" refers to an individual who uses the system to receive support in their job search.

[0592] "Experience" refers to the knowledge, skills, and work experience that a user has accumulated in the past.

[0593] "Areas of interest" refers to a particular industry or research area that interests a user.

[0594] "Hobbies" refers to activities and tendencies that a user personally enjoys.

[0595] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to input information.

[0596] "Server" refers to a computer system responsible for receiving, storing, and processing information sent by users.

[0597] "Storage means" refers to a database or storage system for saving user information on a server.

[0598] "Generative AI" refers to an artificial intelligence model that generates recommendation information based on user input information.

[0599] A "prompt sentence" refers to an input sentence that provides the necessary information to the generation AI.

[0600] "Recommended information" refers to information about appropriate companies and industries generated by the generating AI based on information input by the user.

[0601] This invention is a system that uses generative AI to support students in their job hunting. Users input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server, allowing them to obtain recommended information on companies and industries that suit them.

[0602] Hardware and software used

[0603] The system uses the following hardware and software:

[0604] Terminal: A device such as a computer or smartphone on which a user inputs information and views recommendations.

[0605] Server: A computer system that processes information received from the user, sends prompts to the generation AI, and sends recommendation information to the user.

[0606] Storage means: A database or storage system on the server for saving user input information

[0607] Generative AI: An artificial intelligence model that generates recommendations based on user input (e.g., GPT-3)

[0608] Data processing and calculation

[0609] User input

[0610] Users use a form on the device to enter information about their experience, areas of interest, hobbies, etc. For example, a user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[0611] Sending and storing information

[0612] The device converts the input information into JSON format and sends it to the server as a POST request. The server analyzes the received information, stores it in variables, and saves it in a storage means (database). For example, the following information is saved:

[0613] Experience: 3 years of programming experience

[0614] Area of ​​interest: Data Science

[0615] Hobbies: Reading and traveling

[0616] Generating recommendations

[0617] The server generates a prompt to send to the AI ​​based on the user information stored in the memory. This prompt has the following format:

[0618] User Information:

[0619] Experience: 3 years of programming experience

[0620] Area of ​​interest: Data Science

[0621] Hobbies: Reading and traveling

[0622] Recommend companies and industries that fit this user.

[0623] The server sends this prompt to the generation AI, which generates recommendation information for appropriate companies and industries. The generation AI generates recommendation information based on the prompt and responds to the server.

[0624] Sending and displaying recommendations

[0625] The server organizes the recommendation information received from the generation AI and sends it in JSON format to the user's device, where it is displayed for viewing by the user.

[0626] Specific examples

[0627] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[0628] 1. The user enters information into a form on the terminal and sends it to the server.

[0629] 2. The server stores the received information in a storage means.

[0630] 3. The server generates a prompt based on the stored information and sends a request to the generation AI.

[0631] 4. The generation AI generates recommendation information and responds to the server.

[0632] 5. The server organizes the recommendation information and sends it to the user's device.

[0633] 6. The device displays the recommended information and the user views it.

[0634] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[0635] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0636] Step 1:

[0637] The user uses a device to input information about their experience, areas of interest, hobbies, and preferences. The input information may be "3 years of programming experience," "interest in data science," or "hobbies are reading and traveling." The input data is converted into JSON format.

[0638] Step 2:

[0639] The device sends the entered information to the server as a POST request in JSON format. For example, the following JSON data is sent to the server:

[0640] json

[0641] {

[0642] "experience": "3 years of programming experience",

[0643] "interest": "data science",

[0644] "hobbies": "reading and traveling"

[0645] }

[0646] Input: User-entered data

[0647] Output: POST request in JSON format

[0648] Step 3:

[0649] The server receives the POST request, analyzes its contents, and stores them in variables. The server then saves this information in a storage means (database). A database operation is performed to save the information in the storage means.

[0650] Input: User information in JSON format

[0651] Output: User information stored in the database

[0652] Step 4:

[0653] The server generates a prompt sentence to send to the generation AI based on the user information stored in the storage means. The prompt sentence is specifically constructed based on the user information. For example, the following prompt sentence is generated:

[0654] User Information:

[0655] Experience: 3 years of programming experience

[0656] Area of ​​interest: Data Science

[0657] Hobbies: Reading and traveling

[0658] Recommend companies and industries that fit this user.

[0659] Input: User information stored in the database

[0660] Output: Generated prompt statement

[0661] Step 5:

[0662] The server sends the generated prompt to the AI's API, creates an API request, and sends it to the AI ​​model (e.g., GPT-3). At this time, the server formats the prompt to fit the AI's needs.

[0663] Input: Generated prompt text

[0664] Output: API request

[0665] Step 6:

[0666] The Generator AI receives API requests from the server, processes them, and generates recommendations for companies and industries suitable for the user. The following data is returned as recommendations:

[0667] json

[0668] {

[0669] "recommendations": [

[0670] "Companies where you can thrive in the field of data science,"

[0671] "A well-known company for data analysts, machine learning engineers, and data scientists"

[0672] ]

[0673] }

[0674] Input: API request

[0675] Output: Recommendation

[0676] Step 7:

[0677] The server analyzes the recommendation information received from the AI ​​generator and sends it to the user's device in JSON format, where data may be reformatted or filtered.

[0678] Input: Recommendation information received from the generation AI

[0679] Output: Recommendations in JSON format

[0680] Step 8:

[0681] The device displays the JSON-formatted recommendation information received from the server on its screen, and the user can view the recommended companies and industry information on the device screen.

[0682] Input: Recommendation information in JSON format

[0683] Output: Recommendations displayed on screen

[0684] (Application example 1)

[0685] 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."

[0686] In today's job-hunting environment, students are faced with a vast amount of information to find the right company or industry, making it difficult to effectively select candidates. With the proliferation of online job fairs and company information sessions, students lack the means to obtain information in a virtual space and connect with companies that are right for them. This problem prevents students from finding the right company and reduces the efficiency of their job-hunting process.

[0687] 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.

[0688] In this invention, the server includes means for having the user input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information to the server, and means for storing the input information received by the server in storage means. This allows the server to view the transmitted recommendation information, means for the user to visit recommended company booths in the virtual space and participate in company information sessions and interview simulations, and means for transmitting the generated recommendation information to the user, making it possible for the generation AI to recommend industries or companies based on the user's input information.

[0689] "Users" refer to individuals who use the system, particularly students looking for jobs.

[0690] "Experience" refers to the skills and knowledge that a user has acquired through study, work, etc.

[0691] "Areas of interest" refers to academic or industrial fields in which the user is interested.

[0692] "Hobbies and preferences" refer to the activities and interests that a user likes to engage in in their daily life.

[0693] A "server" is a computer system that receives, stores, and processes information from users.

[0694] "Storage means" refers to a database or storage system for saving information input by a user.

[0695] "Generative AI" refers to artificial intelligence that generates appropriate recommendation information based on user information.

[0696] "Recommendation information" refers to information about companies and industries that is generated by the generative AI and presented to users.

[0697] The "viewing means" refers to a method by which a user can check the recommended information through a terminal or device.

[0698] "Virtual space" refers to a virtual reality environment created by computer simulation.

[0699] A "company booth" is anything other than a virtual location within a virtual space where a specific company gives a company presentation or conducts interviews.

[0700] A "company information session" is an event where a company introduces its company overview, vision, recruitment information, etc. to students.

[0701] An "interview simulation" is an interactive process that allows users to virtually experience an interview with a company.

[0702] A "prompt" is text that provides questions or instructions to the generating AI based on user information.

[0703] The present invention is a system for enabling students to more effectively conduct their job hunting activities.

[0704] The system starts when the user inputs information such as their experiences, areas of interest, hobbies, and preferences via a terminal. This terminal can be a smartphone or a head-mounted display (HMD). The input information is sent to the server and stored in the server's memory.

[0705] The server generates a prompt based on the stored information and sends an API request to the generative AI. This API uses OpenAI's generative AI model. An example of a generated prompt is, "User experience: 3 years of programming experience\nArea of ​​interest: Data science\nHobbies: Reading and travel\nBased on this, please generate recommendations for appropriate companies and industries."

[0706] Based on this, the AI ​​generates recommendations for companies and industries that are suitable for the user. The recommendation information is sent from the server in JSON format to the user's device, where it is displayed.

[0707] Furthermore, users can visit recommended company booths in the virtual space and participate in company information sessions and interview simulations. This virtual space is realized using an HMD.

[0708] Specifically, the process is as follows:

[0709] 1. The user uses a smartphone or HMD to input information such as their experiences, areas of interest, hobbies, and preferences.

[0710] 2. The terminal sends the entered information to the server.

[0711] 3. The server stores the received information in a storage means.

[0712] 4. The server generates a prompt for the AI ​​based on the stored information and sends an API request.

[0713] 5. The generation AI generates recommendation information for appropriate companies and industries and returns it to the server.

[0714] 6. The server sends the recommendation information to the user's device, which displays it.

[0715] 7. Users visit the recommended company booths in the virtual space and participate in company information sessions and interview simulations.

[0716] The specific hardware used includes smartphones and HMDs (e.g., Oculus Rift), and the servers are general cloud servers (e.g., AWS EC2).The software used includes Flask (a Python framework), OpenAI's generative AI API, and SQL.

[0717] This allows students to receive recommendations for suitable companies and industries based on their experience and interests, and conduct more effective job hunting through virtual company information sessions and interview experiences.

[0718] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0719] Step 1:

[0720] Users use a smartphone or HMD to input information such as their experience, areas of interest, and hobbies and preferences. This input information includes "3 years of programming experience" as experience, "data science" as an area of ​​interest, and "reading and traveling" as hobbies and preferences. The device then captures this input information into a form.

[0721] Step 2:

[0722] The terminal sends the information entered by the user to the server. Specifically, the input information is sent to the server as a POST request. The data format when sent is JSON, as shown below.

[0723] JSON

[0724] {

[0725] "experience": "3 years of programming experience",

[0726] "interest": "data science",

[0727] "hobby": "reading and traveling"

[0728] }

[0729] Step 3:

[0730] The server saves the received information in a storage device. The server analyzes the received JSON data and stores the information in the corresponding fields. Specifically, it is stored in the UserProfile model. The data processing here involves storing the JSON data fields in variables and inserting them into the corresponding columns in the database.

[0731] Step 4:

[0732] The server generates a prompt for the AI ​​based on the information stored in the storage means. Specifically, it generates the following prompt sentence:

[0733] "User experience: 3 years of programming experience.\nInterests: Data science.\nHobbies: Reading and travel.\nBased on this, generate recommendations for appropriate companies and industries."

[0734] Step 5:

[0735] The server sends an API request containing the generated prompt to the AI ​​generator. This uses the OpenAI AI generator API. The API request includes the prompt text. When the server sends this request, the AI ​​generator responds.

[0736] Step 6:

[0737] Based on the prompt received, the generation AI generates recommendations for companies and industries that are suitable for the user. The generation AI performs natural language processing and data analysis internally to generate appropriate recommendations. This recommendation information is returned in the form of a statement such as, "Companies where you can work in the field of data science. Specifically, companies that are well-known for data analysts, machine learning engineers, and data scientists are considered."

[0738] Step 7:

[0739] The server sends the recommendation information received from the generation AI to the user. Specifically, it converts the generated recommendation information into JSON format and sends it to the device. The JSON data sent is in the following format.

[0740] JSON

[0741] {

[0742] "recommendations": "Companies where you can work in the field of data science. Specifically, companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[0743] }

[0744] Step 8:

[0745] The device displays the received recommendation information on its screen. The user can view the information and visit company booths in the virtual space as needed. The virtual space is controlled using an HMD, allowing users to participate in company information sessions and interview simulations.

[0746] 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.

[0747] This invention is a system that utilizes generative AI and an emotion engine to support students in their job hunting. Users input their experiences, areas of interest, and hobbies and preferences into a terminal, and the emotion engine recognizes the user's emotions at the time of input, generating more precisely customized recommendation information. We will explain the specific system flow and the operation of each element.

[0748] User input

[0749] Users enter their experience, areas of interest, and hobbies into a form on their device. For example, they can enter "3 years of programming experience," "Interested in data science," or "My hobbies are reading and traveling."

[0750] Information transmission and emotion recognition

[0751] When the device sends the above input information to the server as a POST request, the emotion engine recognizes the emotion of the user when they input the information. The emotion engine analyzes the user's voice and facial expressions to evaluate their emotional state. For example, if the input is made with a happy expression, it is recognized as "positive," and if it is made with a confused expression, it is recognized as "negative."

[0752] Information storage

[0753] The server receives the POST request and stores the input information and the evaluation results of the emotion engine in a storage device. For example, the following information is recorded:

[0754] Experience: 3 years of programming experience

[0755] Area of ​​interest: Data Science

[0756] Hobbies: Reading and traveling

[0757] Emotional state: Positive

[0758] Generating recommendations

[0759] The server creates a prompt for the generation AI based on the information stored in the memory and sends an API request. This prompt includes the user's experience, areas of interest, hobbies, and preferences, as well as the emotional state evaluated by the emotion engine. The generation AI uses this information to create recommendations for appropriate companies and industries. If the emotional state is positive, the system will make recommendations in a positive tone, and if it is negative, the system will use more detailed and reassuring language than usual.

[0760] Sending and displaying recommendations

[0761] The server sends the generated recommendation information in JSON format to the user's device, which then displays the received recommendation information on the screen for the user to view.

[0762] Specific examples

[0763] As a concrete example, if a user inputs "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and a positive emotional state is recognized, the following processing will occur:

[0764] 1. Information input and emotion recognition

[0765] The user enters information into a form on the device, and the emotion engine recognizes positive emotional states.

[0766] 2. Transmission and storage of information

[0767] The terminal transmits the information and the recognized emotional state to a server, which stores it in a storage means.

[0768] 3. Requests and Responses to Generative AI

[0769] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[0770] The generative AI responds and creates recommendations with a positive tone.

[0771] For example: "You'd be well-suited to a company where you can grow in data science. Consider a career as a data analyst or machine learning engineer."

[0772] 4. Display of recommendation information

[0773] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[0774] The system allows users to receive relevant and customized recommendations for companies and industries based on their experience, interests, and emotional state, making their job search more effective.

[0775] The processing flow will be explained below.

[0776] Step 1:

[0777] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into the form displayed on the terminal. For example, the user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[0778] Step 2:

[0779] The device activates an emotion engine to recognize the user's emotions when they input. The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice to determine their emotional state. For example, it classifies emotional states as positive, negative, or neutral.

[0780] Step 3:

[0781] The device sends the input information and the recognized emotional state to the server. The information is sent to the server as a POST request, with example data as follows:

[0782] json

[0783] {

[0784] "experience": "3 years of programming experience",

[0785] "interests": "data science",

[0786] "hobbies": "reading and traveling",

[0787] "emotion": "positive"

[0788] }

[0789] Step 4:

[0790] The server receives the POST request and stores the input information and emotional state in variables. For example, it processes the data as follows:

[0791] python

[0792] experience = request.POST['experience']

[0793] interests = request.POST['interests']

[0794] hobbies = request.POST['hobbies']

[0795] emotion = request.POST['emotion']

[0796] Step 5:

[0797] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, preferences, and emotional state in a database. An example of the storage process is as follows:

[0798] python

[0799] user_profile = UserProfile(

[0800] experience=experience,

[0801] interests=interests,

[0802] hobbies=hobbies,

[0803] emotion=emotion

[0804] )

[0805] user_profile.save()

[0806] Step 6:

[0807] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[0808] python

[0809] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}, Emotion: {user_profile.emotion}"

[0810] Step 7:

[0811] The server sends a prompt to the Generator AI, which makes a request to the Generator AI's API for recommendations of suitable companies and industries. An example request is as follows:

[0812] python

[0813] response = openai.Completion.create(

[0814] engine="text-davinci-003",

[0815] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[0816] max_tokens=150

[0817] )

[0818] Step 8:

[0819] The server receives the response from the AI ​​generator and extracts the recommendation information. For example, the following recommendation may be generated:

[0820] “Based on your profile, you may be interested in companies that offer jobs in the data science field. You may also consider a career as a data analyst or machine learning engineer.”

[0821] Step 9:

[0822] The server sends the generated recommendation information to the user's device. It also returns the information in JSON format to the device. Example:

[0823] python

[0824] return JsonResponse({'recommendations': recommendations})

[0825] Step 10:

[0826] The device receives the JSON response from the server and displays the recommended information on the screen. The user can then check the recommended information displayed on the device screen.

[0827] Step 11:

[0828] The user browses the recommendation information, which allows the user to obtain recommended information on companies and industries based on their own experiences, interests, and emotional state.

[0829] These are the processing steps of this system, which allows users to receive detailed support tailored to their emotional state while effectively and efficiently pursuing their job search.

[0830] Example 2

[0831] 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."

[0832] Conventional job-hunting support systems can only provide simple recommendations based on user input, and have the problem of being unable to provide customized support that takes into account the user's emotional state. This limits the ability of job seekers to find companies and industries that are more suitable for them.

[0833] 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 allowing a user to input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information and the user's emotional state to the server, means for storing the input information and the emotional state received by the server in a storage means, means for generating recommendation information by a generation AI based on the information and the emotional state stored in the storage means, means for transmitting the generated recommendation information to the user, and means for the user to view the transmitted recommendation information. This makes it possible to provide more sophisticated and customized recommendation information that takes into account the user's emotional state.

[0834] "User" refers to an individual who uses the system to input their experiences, areas of interest, and hobbies and preferences and receive recommendation information.

[0835] "Experience" refers to information indicating knowledge and skills related to work, learning, projects, etc. that a user has accumulated in the past.

[0836] "Areas of interest" refers to the job areas or research topics in which the user is interested.

[0837] "Hobbies and preferences" refers to information that indicates the activities that a user enjoys on a daily basis and the things that the user likes.

[0838] "Emotional state" refers to the psychological and emotional state of the user when inputting information, and is classified as positive, negative, or the like.

[0839] "Device" refers to the electronic device used by a user to input information and receive recommendation information, such as a PC, smartphone, or tablet.

[0840] "Server" refers to a computer system that receives and stores information from users, creates recommendation information based on the generation AI, and sends it to users.

[0841] "Storage means" refers to a database or storage device used by the server to store the user's input information and emotional state.

[0842] "Generative AI" refers to an artificial intelligence module that creates appropriate recommendations based on the user's input information and emotional state.

[0843] A "prompt" refers to an instruction or request sent to the generating AI, including the user's input information and emotional state.

[0844] "Recommendation information" refers to information about companies and industries recommended to users that is created by the generative AI based on the user's input information and emotional state.

[0845] This invention is a system that uses a generative AI and an emotion engine to help users conduct job hunting more effectively. Specific embodiments of this system are described below.

[0846] User input

[0847] Users use their own devices (PC, smartphone, tablet, etc.) to enter their experiences, areas of interest, and hobbies and preferences. This input is done using an HTML form, and data is collected through UI elements such as text boxes and drop-down lists. For example, users can enter "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[0848] Information transmission and emotion recognition

[0849] Once the user has finished entering the information, the device sends this information to the server as a POST request. During this transmission process, the device's built-in emotion recognition software recognizes the user's emotional state. Emotion recognition is performed using the device's built-in camera and microphone to capture the user's facial expression and voice data, and then uses an emotion recognition algorithm (such as OpenCV or Microsoft Azure's Emotion API). The emotional state is evaluated as "positive" or "negative."

[0850] Information storage

[0851] The server receives the information and emotional state sent by the user and stores them in a database (e.g., PostgreSQL). The stored information includes:

[0852] Experience: 3 years of programming experience

[0853] Area of ​​interest: Data Science

[0854] Hobbies: Reading and traveling

[0855] Emotional state: Positive

[0856] Generating recommendations

[0857] The server creates and sends prompts to the AI ​​based on the information stored in the memory. These prompts include the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the prompt text might look like this:

[0858] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[0859] The server sends this prompt to a generative AI (e.g., OpenAI's GPT-3 model), which then generates recommendations for appropriate companies and industries.

[0860] Sending and displaying recommendations

[0861] The server sends the recommendation information received from the generation AI in JSON format to the user's device. The device analyzes the received recommendation information and displays it on the screen. The display uses JavaScript to dynamically update the UI, allowing the user to view information about recommended companies and industries.

[0862] Specific examples

[0863] For example, if a user enters "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and the emotional state is recognized as positive, the system will act as follows:

[0864] 1. Information input and emotion recognition

[0865] The user enters information into a form on the device, and emotion recognition software recognizes positive emotional states.

[0866] 2. Transmission and storage of information

[0867] The device sends the information and the perceived emotional state to a server, which stores it in a database.

[0868] 3. Requests and Responses to Generative AI

[0869] The server creates a prompt and sends an API request to the generating AI.

[0870] The generative AI creates recommendations in a positive tone, such as, "You'd be well suited to a company where you can grow in the field of data science. You might also want to consider a career as a data analyst or machine learning engineer."

[0871] 4. Sending and Displaying Recommendations

[0872] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[0873] The system allows users to receive customized company and industry recommendations based on their experience, interests, and emotional state, enabling them to conduct a more effective job search.

[0874] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0875] Step 1: Enter your information

[0876] Users enter their experiences, areas of interest, and hobbies and preferences into a form on their device (PC, smartphone, tablet, etc.). This form is set up in HTML format, and data is collected through UI elements such as text boxes and drop-down lists. For example, a user might enter "3 years of programming experience," "Interested in data science," and "My hobbies are reading and traveling." The entered information is temporarily saved in the device's browser.

[0877] input:

[0878] User experience, areas of interest, hobbies and preferences

[0879] output:

[0880] Data stored on the device as user-entered information

[0881] Step 2: Information transmission and emotion recognition

[0882] The device sends the information entered by the user to the server as a POST request. At the same time, the device's built-in camera and microphone capture the user's facial expression and voice data, which are then sent to emotion recognition software (such as OpenCV or Microsoft Azure's Emotion API). This emotion recognition algorithm analyzes the user's emotional state at the time of input and classifies it as positive, negative, etc.

[0883] input:

[0884] User experience, areas of interest, hobbies and preferences

[0885] User's facial expression data, voice data

[0886] output:

[0887] User data and emotional state sent to the server as a POST request

[0888] Step 3: Save your information

[0889] The server receives POST requests from the device and processes the input information and emotional state. This information is then stored in a database such as PostgreSQL. The data stored includes the user's experience, areas of interest, hobbies, and emotional state.

[0890] input:

[0891] User input information, emotional state

[0892] output:

[0893] Information stored in a database

[0894] Step 4: Generate a prompt statement

[0895] The server creates a prompt sentence to be sent to the generation AI based on the information stored in the storage means. This prompt sentence includes the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the following prompt sentence is generated:

[0896] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[0897] input:

[0898] User information and emotional state stored in the database

[0899] output:

[0900] Prompt to send to the generation AI

[0901] Step 5: Generate recommendations

[0902] The server sends a prompt to a generative AI (e.g., OpenAI's GPT-3 model), which generates recommendations for companies and industries suitable for the user based on the prompt. The generated recommendations contain positive tones and specific suggestions.

[0903] input:

[0904] Prompt statement

[0905] output:

[0906] Generated recommendations

[0907] Step 6: Submit and view your recommendations

[0908] The server receives the recommendation information returned by the generation AI, converts it to JSON format, and sends it to the user's device. The device then analyzes the received recommendation information and generates HTML elements to display on the screen. Dynamic UI updates are performed using JavaScript, allowing the user to view information on recommended companies and industries.

[0909] input:

[0910] Generated recommendations

[0911] output:

[0912] Recommendation information displayed on the user's device

[0913] Through the above processing steps, users can receive customized recommendation information based on their experiences, interests, hobbies, preferences, and emotional state, allowing them to conduct a more effective job search.

[0914] (Application example 2)

[0915] 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."

[0916] Conventional job-hunting support systems can provide recommended information based on a user's experience, areas of interest, and hobbies and preferences, but they cannot provide customized recommended information that takes into account the user's emotional state. This makes it difficult for users to obtain recommended information that is truly interesting and psychologically appropriate.

[0917] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for allowing a user to input their experiences, areas of interest, and hobbies and preferences; means for transmitting the input information to the server; means for storing the input information received by the server in a storage means; means for generating recommendation information using a generation AI based on the information stored in the storage means; means for transmitting the generated recommendation information to the user; means for the user to view the sent recommendation information; means for recognizing the user's emotional state from voice and facial expressions using an emotion engine; and means for generating recommendation information taking the emotional state into consideration. This enables the user to obtain customized recommendation information based not only on their own experiences and interests but also on their current emotional state.

[0918] A "user" is an entity that uses the system to input their experiences, areas of interest, hobbies, and preferences.

[0919] "Experience" is information indicating the activities and skills that the user has engaged in in the past.

[0920] "Areas of interest" is information that indicates areas of expertise or topics that interest a user.

[0921] "Hobbies and preferences" is information that indicates the activities and preferences that a user enjoys on a daily basis.

[0922] A "server" is a central device that receives, stores, and processes information sent by users.

[0923] "Storage means" refers to data storage for saving input information received by the server.

[0924] "Generation AI" is artificial intelligence that generates recommendation information based on information stored in a storage device.

[0925] "Recommended information" is information on appropriate content, industries, companies, etc. provided by the generation AI based on user input information.

[0926] An "emotion engine" is an algorithm or system that analyzes a user's voice and facial expressions to assess their emotional state.

[0927] A "prompt" is data containing information such as a user's experience and emotional state that is used as input to a generative AI.

[0928] "Content" refers to information such as movies, books, podcasts, etc. that is provided as recommended information.

[0929] This invention is a system that provides recommended content based on a user's experience, areas of interest, hobbies, preferences, and current emotional state. This system collects user input information, sends it to a server, and generates customized recommendation information using a generative AI and an emotion engine.

[0930] The server performs processing using the following hardware and software. For hardware, the server uses a cloud server equipped with high-performance data storage and processors. For software, a web framework is built using Flask, emotion recognition is performed using EmotionEngine, and recommendation processing is performed using an AIRecommender generative AI model. A database is also used as storage.

[0931] First, a user uses a smartphone or desktop device to enter information about their experiences, areas of interest, and hobbies and preferences. Specifically, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." At the same time, the user's current emotional state is also captured using voice input or facial recognition.

[0932] The device sends the information entered by the user and the collected emotional data to the server. Upon receiving this information, the server analyzes the emotional state using the Emotion Engine and stores all information along with the analysis results in a database. The server then generates a prompt based on the storage means and sends the prompt to the generation AI. Based on this prompt, the generation AI generates recommended content that is optimal for the user.

[0933] The generated recommendation content is sent from the server to the user's device and displayed on the device screen. For example, if the user expresses positive emotions, the server will display recommended content with a positive tone, such as "recommended action movies," "fantasy web novels," and "related podcasts."

[0934] For example, the following prompt is generated and sent to the generator AI:

[0935] User Information:

[0936] Experience: I watch a lot of action movies

[0937] Areas of interest: Fantasy

[0938] Hobbies and interests: Reading

[0939] Emotional state: Positive

[0940] Using this prompt, the AI ​​generates recommendations for movies, books, podcasts, and other content that are best suited to the user, and sends them to the user's device, allowing the user to obtain customized recommendations based on their interests and emotional state.

[0941] The invention is characterized by the fact that a recommendation system using generative AI provides customized information that takes into account the user's emotions, making it easier for users to efficiently discover content that will provide them with greater satisfaction.

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] Users use their smartphones or desktop devices to enter information about their experiences, areas of interest, and hobbies. For example, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." Input is done using pull-down menus and free text format.

[0945] Input: User experience, areas of interest, hobbies and preferences

[0946] Output: User input information

[0947] Step 2:

[0948] After the user completes the input, the Emotion Engine recognizes the user's emotional state at that time using voice input or facial recognition. The Emotion Engine analyzes voice tone and facial expression data to classify the emotional state as positive, negative, neutral, etc.

[0949] Input: User voice or facial recognition data

[0950] Output: User's emotional state

[0951] Step 3:

[0952] The device sends the user-entered information and the recognized emotional state to the server, structured as a POST request via the API.

[0953] Input: User input information, user emotional state

[0954] Output: API request to the server

[0955] Step 4:

[0956] The server stores the received inputs and emotional states in a database, which organizes them for each user and later uses them to send prompts to the generative AI model.

[0957] Input: API request data (user input information, emotional state)

[0958] Output: User information stored in the database

[0959] Step 5:

[0960] The server creates prompts based on the information stored in the database and sends API requests to the generative AI model (AIRecommender). The prompts include the user's experience, areas of interest, hobbies, and emotional state.

[0961] Input: Database user information

[0962] Output: prompts to the generative AI model

[0963] Step 6:

[0964] The generative AI model receives the prompts and generates optimal recommended content based on the user's information and emotional state, which is returned in JSON format and sent to the server.

[0965] Input: prompt to generative AI model

[0966] Output: Recommended content (JSON format)

[0967] Step 7:

[0968] The server then sends the generated recommended content to the device, which then displays it to the user, who can then browse the recommended information for movies, books, podcasts, etc. on the screen.

[0969] Input: Recommended content (JSON format)

[0970] Output: Recommendation information displayed on the user's device

[0971] Through the above processing steps, users can receive content recommendations that are customized according to their interests and emotional state. This system allows users to efficiently discover content that will provide them with greater satisfaction.

[0972] 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.

[0973] 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.

[0974] 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.

[0975] [Third embodiment]

[0976] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0977] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0978] 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).

[0979] 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.

[0980] 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.

[0981] 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).

[0982] 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.

[0983] 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.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] 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."

[0988] This invention is a system that utilizes generative AI to support students in their job hunting activities. Users can input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server to obtain recommended information on companies and industries that suit them. This system includes the following means.

[0989] User input

[0990] Users enter information such as their experience, areas of interest, hobbies, etc. into a form on the device. For example, they can enter "3 years of programming experience" in the experience section, "data science" in the area of ​​interest, and "reading and traveling" in the hobbies and hobbies section.

[0991] Sending and storing information

[0992] The device sends the above input information to the server as a POST request. When the server receives this request, it stores the obtained information in variables and saves it in the UserProfile model. For example, the information is recorded as follows:

[0993] Experience: 3 years of programming experience

[0994] Area of ​​interest: Data Science

[0995] Hobbies: Reading and traveling

[0996] Generating recommendations

[0997] The server generates a prompt based on the user information stored in the storage device and sends an API request to the AI ​​generator. This prompt includes the user's experience, areas of interest, and hobbies and preferences. The AI ​​generator then uses this information to create recommendations for appropriate companies and industries. For example, the following response might be generated:

[0998] “Based on your profile, you would be interested in companies where you can work in the field of data science. Specifically, companies with a reputation for being a data analyst, machine learning engineer, or data scientist.”

[0999] Sending and displaying recommendations

[1000] The server sends the generated recommendation information to the user in JSON format, and the device displays the received recommendation information on the screen so that the user can view it.

[1001] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[1002] Specific examples

[1003] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[1004] 1. Sending input information

[1005] The user enters information into a form on the terminal and sends it to the server.

[1006] 2. Storage of Information

[1007] The server stores the received information in the UserProfile model.

[1008] 3. Requests to Generative AI

[1009] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[1010] 4. Receiving Recommendations

[1011] Receive the response from the generation AI and extract the recommendation information.

[1012] 5. Display of Recommendations

[1013] The extracted information is sent in JSON format to the user's device, and the device displays the recommended information.

[1014] This allows users to receive specific recommendations such as "companies where you can work in the field of data science" or "companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[1015] The processing flow will be explained below.

[1016] Step 1:

[1017] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into a form displayed on the terminal. For example, "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[1018] Step 2:

[1019] The terminal sends the entered information to the server. The entered information is sent in the form of a POST request. An example of the data sent is as follows:

[1020] json

[1021] {

[1022] "experience": "3 years of programming experience",

[1023] "interests": "data science",

[1024] "hobbies": "reading and traveling"

[1025] }

[1026] Step 3:

[1027] The server receives the POST request and receives the input information. Specifically, it stores the data sent by the user in a variable using the request.POST method.

[1028] Step 4:

[1029] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, and preferences in a database. An example of the storage process is as follows:

[1030] python

[1031] user_profile = UserProfile(

[1032] experience=request.POST['experience'],

[1033] interests=request.POST['interests'],

[1034] hobbies=request.POST['hobbies']

[1035] )

[1036] user_profile.save()

[1037] Step 5:

[1038] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[1039] python

[1040] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}"

[1041] Step 6:

[1042] The server sends a prompt to the Generator AI. Specifically, it sends a request to the Generator AI's API, asking for a response to recommend companies and industries suitable for the user. An example request is as follows:

[1043] python

[1044] response = openai.Completion.create(

[1045] engine="text-davinci-003",

[1046] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[1047] max_tokens=150

[1048] )

[1049] Step 7:

[1050] The server receives a response from the generative AI, which includes company and industry recommendations based on the user's input. For example, the response might include recommendations like:

[1051] "You'll be interested in companies where you can work in the data science field. For example, there are companies that are well-known for being data analysts, machine learning engineers, and data scientists."

[1052] Step 8:

[1053] The server extracts the generated AI's response as recommendation information and sends it back to the user's device in JSON format. An example of sending the extracted information as a JSON response is as follows:

[1054] python

[1055] return JsonResponse({'recommendations': recommendations})

[1056] Step 9:

[1057] The device receives the JSON response from the server, analyzes the received recommendation information, and displays it on the screen.

[1058] Step 10:

[1059] The user browses the recommendations displayed on the device screen, providing specific information to help them find the right company or industry based on their experience and interests.

[1060] These are the processing steps of this system, which allows users to proceed with their job search effectively and efficiently.

[1061] Example 1

[1062] 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."

[1063] Conventional job-hunting support systems have difficulty recommending appropriate companies and industries based on users' experiences and interests, forcing students to search through a wide variety of information to find the right fit. Furthermore, the methods for inputting information and displaying recommended information are limited, resulting in a suboptimal user experience.

[1064] 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.

[1065] In this invention, the server includes a means for allowing the user to input their experiences, areas of interest, and hobbies and preferences, a means for sending prompts to the generation AI, and a means for organizing the recommendation information received from the generation AI, thereby enabling the user to receive accurate and appropriate recommendations for companies and industries based on their own information.

[1066] "User" refers to an individual who uses the system to receive support in their job search.

[1067] "Experience" refers to the knowledge, skills, and work experience that a user has accumulated in the past.

[1068] "Areas of interest" refers to a particular industry or research area that interests a user.

[1069] "Hobbies" refers to activities and tendencies that a user personally enjoys.

[1070] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to input information.

[1071] "Server" refers to a computer system responsible for receiving, storing, and processing information sent by users.

[1072] "Storage means" refers to a database or storage system for saving user information on a server.

[1073] "Generative AI" refers to an artificial intelligence model that generates recommendation information based on user input information.

[1074] A "prompt sentence" refers to an input sentence that provides the necessary information to the generation AI.

[1075] "Recommended information" refers to information about appropriate companies and industries generated by the generating AI based on information input by the user.

[1076] This invention is a system that uses generative AI to support students in their job hunting. Users input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server, allowing them to obtain recommended information on companies and industries that suit them.

[1077] Hardware and software used

[1078] The system uses the following hardware and software:

[1079] Terminal: A device such as a computer or smartphone on which a user inputs information and views recommendations.

[1080] Server: A computer system that processes information received from the user, sends prompts to the generation AI, and sends recommendation information to the user.

[1081] Storage means: A database or storage system on the server for saving user input information

[1082] Generative AI: An artificial intelligence model that generates recommendations based on user input (e.g., GPT-3)

[1083] Data processing and calculation

[1084] User input

[1085] Users use a form on the device to enter information about their experience, areas of interest, hobbies, etc. For example, a user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[1086] Sending and storing information

[1087] The device converts the input information into JSON format and sends it to the server as a POST request. The server analyzes the received information, stores it in variables, and saves it in a storage means (database). For example, the following information is saved:

[1088] Experience: 3 years of programming experience

[1089] Area of ​​interest: Data Science

[1090] Hobbies: Reading and traveling

[1091] Generating recommendations

[1092] The server generates a prompt to send to the AI ​​based on the user information stored in the memory. This prompt has the following format:

[1093] User Information:

[1094] Experience: 3 years of programming experience

[1095] Area of ​​interest: Data Science

[1096] Hobbies: Reading and traveling

[1097] Recommend companies and industries that fit this user.

[1098] The server sends this prompt to the generation AI, which generates recommendation information for appropriate companies and industries. The generation AI generates recommendation information based on the prompt and responds to the server.

[1099] Sending and displaying recommendations

[1100] The server organizes the recommendation information received from the generation AI and sends it in JSON format to the user's device, where it is displayed for viewing by the user.

[1101] Specific examples

[1102] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[1103] 1. The user enters information into a form on the terminal and sends it to the server.

[1104] 2. The server stores the received information in a storage means.

[1105] 3. The server generates a prompt based on the stored information and sends a request to the generation AI.

[1106] 4. The generation AI generates recommendation information and responds to the server.

[1107] 5. The server organizes the recommendation information and sends it to the user's device.

[1108] 6. The device displays the recommended information and the user views it.

[1109] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[1110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1111] Step 1:

[1112] The user uses a device to input information about their experience, areas of interest, hobbies, and preferences. The input information may be "3 years of programming experience," "interest in data science," or "hobbies are reading and traveling." The input data is converted into JSON format.

[1113] Step 2:

[1114] The device sends the entered information to the server as a POST request in JSON format. For example, the following JSON data is sent to the server:

[1115] json

[1116] {

[1117] "experience": "3 years of programming experience",

[1118] "interest": "data science",

[1119] "hobbies": "reading and traveling"

[1120] }

[1121] Input: User-entered data

[1122] Output: POST request in JSON format

[1123] Step 3:

[1124] The server receives the POST request, analyzes its contents, and stores them in variables. The server then saves this information in a storage means (database). A database operation is performed to save the information in the storage means.

[1125] Input: User information in JSON format

[1126] Output: User information stored in the database

[1127] Step 4:

[1128] The server generates a prompt sentence to send to the generation AI based on the user information stored in the storage means. The prompt sentence is specifically constructed based on the user information. For example, the following prompt sentence is generated:

[1129] User Information:

[1130] Experience: 3 years of programming experience

[1131] Area of ​​interest: Data Science

[1132] Hobbies: Reading and traveling

[1133] Recommend companies and industries that fit this user.

[1134] Input: User information stored in the database

[1135] Output: Generated prompt statement

[1136] Step 5:

[1137] The server sends the generated prompt to the AI's API, creates an API request, and sends it to the AI ​​model (e.g., GPT-3). At this time, the server formats the prompt to fit the AI's needs.

[1138] Input: Generated prompt text

[1139] Output: API request

[1140] Step 6:

[1141] The Generator AI receives API requests from the server, processes them, and generates recommendations for companies and industries suitable for the user. The following data is returned as recommendations:

[1142] json

[1143] {

[1144] "recommendations": [

[1145] "Companies where you can thrive in the field of data science,"

[1146] "A well-known company for data analysts, machine learning engineers, and data scientists"

[1147] ]

[1148] }

[1149] Input: API request

[1150] Output: Recommendation

[1151] Step 7:

[1152] The server analyzes the recommendation information received from the AI ​​generator and sends it to the user's device in JSON format, where data may be reformatted or filtered.

[1153] Input: Recommendation information received from the generation AI

[1154] Output: Recommendations in JSON format

[1155] Step 8:

[1156] The device displays the JSON-formatted recommendation information received from the server on its screen, and the user can view the recommended companies and industry information on the device screen.

[1157] Input: Recommendation information in JSON format

[1158] Output: Recommendations displayed on screen

[1159] (Application example 1)

[1160] 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."

[1161] In today's job-hunting environment, students are faced with a vast amount of information to find the right company or industry, making it difficult to effectively select candidates. With the proliferation of online job fairs and company information sessions, students lack the means to obtain information in a virtual space and connect with companies that are right for them. This problem prevents students from finding the right company and reduces the efficiency of their job-hunting process.

[1162] 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.

[1163] In this invention, the server includes means for having the user input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information to the server, and means for storing the input information received by the server in storage means. This allows the server to view the transmitted recommendation information, means for the user to visit recommended company booths in the virtual space and participate in company information sessions and interview simulations, and means for transmitting the generated recommendation information to the user, making it possible for the generation AI to recommend industries or companies based on the user's input information.

[1164] "Users" refer to individuals who use the system, particularly students looking for jobs.

[1165] "Experience" refers to the skills and knowledge that a user has acquired through study, work, etc.

[1166] "Areas of interest" refers to academic or industrial fields in which the user is interested.

[1167] "Hobbies and preferences" refer to the activities and interests that a user likes to engage in in their daily life.

[1168] A "server" is a computer system that receives, stores, and processes information from users.

[1169] "Storage means" refers to a database or storage system for saving information input by a user.

[1170] "Generative AI" refers to artificial intelligence that generates appropriate recommendation information based on user information.

[1171] "Recommendation information" refers to information about companies and industries that is generated by the generative AI and presented to users.

[1172] The "viewing means" refers to a method by which a user can check the recommended information through a terminal or device.

[1173] "Virtual space" refers to a virtual reality environment created by computer simulation.

[1174] A "company booth" is anything other than a virtual location within a virtual space where a specific company gives a company presentation or conducts interviews.

[1175] A "company information session" is an event where a company introduces its company overview, vision, recruitment information, etc. to students.

[1176] An "interview simulation" is an interactive process that allows users to virtually experience an interview with a company.

[1177] A "prompt" is text that provides questions or instructions to the generating AI based on user information.

[1178] The present invention is a system for enabling students to more effectively conduct their job hunting activities.

[1179] The system starts when the user inputs information such as their experiences, areas of interest, hobbies, and preferences via a terminal. This terminal can be a smartphone or a head-mounted display (HMD). The input information is sent to the server and stored in the server's memory.

[1180] The server generates a prompt based on the stored information and sends an API request to the generative AI. This API uses OpenAI's generative AI model. An example of a generated prompt is, "User experience: 3 years of programming experience\nArea of ​​interest: Data science\nHobbies: Reading and travel\nBased on this, please generate recommendations for appropriate companies and industries."

[1181] Based on this, the AI ​​generates recommendations for companies and industries that are suitable for the user. The recommendation information is sent from the server in JSON format to the user's device, where it is displayed.

[1182] Furthermore, users can visit recommended company booths in the virtual space and participate in company information sessions and interview simulations. This virtual space is realized using an HMD.

[1183] Specifically, the process is as follows:

[1184] 1. The user uses a smartphone or HMD to input information such as their experiences, areas of interest, hobbies, and preferences.

[1185] 2. The terminal sends the entered information to the server.

[1186] 3. The server stores the received information in a storage means.

[1187] 4. The server generates a prompt for the AI ​​based on the stored information and sends an API request.

[1188] 5. The generation AI generates recommendation information for appropriate companies and industries and returns it to the server.

[1189] 6. The server sends the recommendation information to the user's device, which displays it.

[1190] 7. Users visit the recommended company booths in the virtual space and participate in company information sessions and interview simulations.

[1191] The specific hardware used includes smartphones and HMDs (e.g., Oculus Rift), and the servers are general cloud servers (e.g., AWS EC2).The software used includes Flask (a Python framework), OpenAI's generative AI API, and SQL.

[1192] This allows students to receive recommendations for suitable companies and industries based on their experience and interests, and conduct more effective job hunting through virtual company information sessions and interview experiences.

[1193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1194] Step 1:

[1195] Users use a smartphone or HMD to input information such as their experience, areas of interest, and hobbies and preferences. This input information includes "3 years of programming experience" as experience, "data science" as an area of ​​interest, and "reading and traveling" as hobbies and preferences. The device then captures this input information into a form.

[1196] Step 2:

[1197] The terminal sends the information entered by the user to the server. Specifically, the input information is sent to the server as a POST request. The data format when sent is JSON, as shown below.

[1198] JSON

[1199] {

[1200] "experience": "3 years of programming experience",

[1201] "interest": "data science",

[1202] "hobby": "reading and traveling"

[1203] }

[1204] Step 3:

[1205] The server saves the received information in a storage device. The server analyzes the received JSON data and stores the information in the corresponding fields. Specifically, it is stored in the UserProfile model. The data processing here involves storing the JSON data fields in variables and inserting them into the corresponding columns in the database.

[1206] Step 4:

[1207] The server generates a prompt for the AI ​​based on the information stored in the storage means. Specifically, it generates the following prompt sentence:

[1208] "User experience: 3 years of programming experience.\nInterests: Data science.\nHobbies: Reading and travel.\nBased on this, generate recommendations for appropriate companies and industries."

[1209] Step 5:

[1210] The server sends an API request containing the generated prompt to the AI ​​generator. This uses the OpenAI AI generator API. The API request includes the prompt text. When the server sends this request, the AI ​​generator responds.

[1211] Step 6:

[1212] Based on the prompt received, the generation AI generates recommendations for companies and industries that are suitable for the user. The generation AI performs natural language processing and data analysis internally to generate appropriate recommendations. This recommendation information is returned in the form of a statement such as, "Companies where you can work in the field of data science. Specifically, companies that are well-known for data analysts, machine learning engineers, and data scientists are considered."

[1213] Step 7:

[1214] The server sends the recommendation information received from the generation AI to the user. Specifically, it converts the generated recommendation information into JSON format and sends it to the device. The JSON data sent is in the following format.

[1215] JSON

[1216] {

[1217] "recommendations": "Companies where you can work in the field of data science. Specifically, companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[1218] }

[1219] Step 8:

[1220] The device displays the received recommendation information on its screen. The user can view the information and visit company booths in the virtual space as needed. The virtual space is controlled using an HMD, allowing users to participate in company information sessions and interview simulations.

[1221] 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.

[1222] This invention is a system that utilizes generative AI and an emotion engine to support students in their job hunting. Users input their experiences, areas of interest, and hobbies and preferences into a terminal, and the emotion engine recognizes the user's emotions at the time of input, generating more precisely customized recommendation information. We will explain the specific system flow and the operation of each element.

[1223] User input

[1224] Users enter their experience, areas of interest, and hobbies into a form on their device. For example, they can enter "3 years of programming experience," "Interested in data science," or "My hobbies are reading and traveling."

[1225] Information transmission and emotion recognition

[1226] When the device sends the above input information to the server as a POST request, the emotion engine recognizes the emotion of the user when they input the information. The emotion engine analyzes the user's voice and facial expressions to evaluate their emotional state. For example, if the input is made with a happy expression, it is recognized as "positive," and if it is made with a confused expression, it is recognized as "negative."

[1227] Information storage

[1228] The server receives the POST request and stores the input information and the evaluation results of the emotion engine in a storage device. For example, the following information is recorded:

[1229] Experience: 3 years of programming experience

[1230] Area of ​​interest: Data Science

[1231] Hobbies: Reading and traveling

[1232] Emotional state: Positive

[1233] Generating recommendations

[1234] The server creates a prompt for the generation AI based on the information stored in the memory and sends an API request. This prompt includes the user's experience, areas of interest, hobbies, and preferences, as well as the emotional state evaluated by the emotion engine. The generation AI uses this information to create recommendations for appropriate companies and industries. If the emotional state is positive, the system will make recommendations in a positive tone, and if it is negative, the system will use more detailed and reassuring language than usual.

[1235] Sending and displaying recommendations

[1236] The server sends the generated recommendation information in JSON format to the user's device, which then displays the received recommendation information on the screen for the user to view.

[1237] Specific examples

[1238] As a concrete example, if a user inputs "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and a positive emotional state is recognized, the following processing will occur:

[1239] 1. Information input and emotion recognition

[1240] The user enters information into a form on the device, and the emotion engine recognizes positive emotional states.

[1241] 2. Transmission and storage of information

[1242] The terminal transmits the information and the recognized emotional state to a server, which stores it in a storage means.

[1243] 3. Requests and Responses to Generative AI

[1244] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[1245] The generative AI responds and creates recommendations with a positive tone.

[1246] For example: "You'd be well-suited to a company where you can grow in data science. Consider a career as a data analyst or machine learning engineer."

[1247] 4. Display of recommendation information

[1248] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[1249] The system allows users to receive relevant and customized recommendations for companies and industries based on their experience, interests, and emotional state, making their job search more effective.

[1250] The processing flow will be explained below.

[1251] Step 1:

[1252] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into the form displayed on the terminal. For example, the user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[1253] Step 2:

[1254] The device activates an emotion engine to recognize the user's emotions when they input. The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice to determine their emotional state. For example, it classifies emotional states as positive, negative, or neutral.

[1255] Step 3:

[1256] The device sends the input information and the recognized emotional state to the server. The information is sent to the server as a POST request, with example data as follows:

[1257] json

[1258] {

[1259] "experience": "3 years of programming experience",

[1260] "interests": "data science",

[1261] "hobbies": "reading and traveling",

[1262] "emotion": "positive"

[1263] }

[1264] Step 4:

[1265] The server receives the POST request and stores the input information and emotional state in variables. For example, it processes the data as follows:

[1266] python

[1267] experience = request.POST['experience']

[1268] interests = request.POST['interests']

[1269] hobbies = request.POST['hobbies']

[1270] emotion = request.POST['emotion']

[1271] Step 5:

[1272] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, preferences, and emotional state in a database. An example of the storage process is as follows:

[1273] python

[1274] user_profile = UserProfile(

[1275] experience=experience,

[1276] interests=interests,

[1277] hobbies=hobbies,

[1278] emotion=emotion

[1279] )

[1280] user_profile.save()

[1281] Step 6:

[1282] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[1283] python

[1284] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}, Emotion: {user_profile.emotion}"

[1285] Step 7:

[1286] The server sends a prompt to the Generator AI, which makes a request to the Generator AI's API for recommendations of suitable companies and industries. An example request is as follows:

[1287] python

[1288] response = openai.Completion.create(

[1289] engine="text-davinci-003",

[1290] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[1291] max_tokens=150

[1292] )

[1293] Step 8:

[1294] The server receives the response from the AI ​​generator and extracts the recommendation information. For example, the following recommendation may be generated:

[1295] “Based on your profile, you may be interested in companies that offer jobs in the data science field. You may also consider a career as a data analyst or machine learning engineer.”

[1296] Step 9:

[1297] The server sends the generated recommendation information to the user's device. It also returns the information in JSON format to the device. Example:

[1298] python

[1299] return JsonResponse({'recommendations': recommendations})

[1300] Step 10:

[1301] The device receives the JSON response from the server and displays the recommended information on the screen. The user can then check the recommended information displayed on the device screen.

[1302] Step 11:

[1303] The user browses the recommendation information, which allows the user to obtain recommended information on companies and industries based on their own experiences, interests, and emotional state.

[1304] These are the processing steps of this system, which allows users to receive detailed support tailored to their emotional state while effectively and efficiently pursuing their job search.

[1305] Example 2

[1306] 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."

[1307] Conventional job-hunting support systems can only provide simple recommendations based on user input, and have the problem of being unable to provide customized support that takes into account the user's emotional state. This limits the ability of job seekers to find companies and industries that are more suitable for them.

[1308] 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 allowing a user to input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information and the user's emotional state to the server, means for storing the input information and the emotional state received by the server in a storage means, means for generating recommendation information by a generation AI based on the information and the emotional state stored in the storage means, means for transmitting the generated recommendation information to the user, and means for the user to view the transmitted recommendation information. This makes it possible to provide more sophisticated and customized recommendation information that takes into account the user's emotional state.

[1309] "User" refers to an individual who uses the system to input their experiences, areas of interest, and hobbies and preferences and receive recommendation information.

[1310] "Experience" refers to information indicating knowledge and skills related to work, learning, projects, etc. that a user has accumulated in the past.

[1311] "Areas of interest" refers to the job areas or research topics in which the user is interested.

[1312] "Hobbies and preferences" refers to information that indicates the activities that a user enjoys on a daily basis and the things that the user likes.

[1313] "Emotional state" refers to the psychological and emotional state of the user when inputting information, and is classified as positive, negative, or the like.

[1314] "Device" refers to the electronic device used by a user to input information and receive recommendation information, such as a PC, smartphone, or tablet.

[1315] "Server" refers to a computer system that receives and stores information from users, creates recommendation information based on the generation AI, and sends it to users.

[1316] "Storage means" refers to a database or storage device used by the server to store the user's input information and emotional state.

[1317] "Generative AI" refers to an artificial intelligence module that creates appropriate recommendations based on the user's input information and emotional state.

[1318] A "prompt" refers to an instruction or request sent to the generating AI, including the user's input information and emotional state.

[1319] "Recommendation information" refers to information about companies and industries recommended to users that is created by the generative AI based on the user's input information and emotional state.

[1320] This invention is a system that uses a generative AI and an emotion engine to help users conduct job hunting more effectively. Specific embodiments of this system are described below.

[1321] User input

[1322] Users use their own devices (PC, smartphone, tablet, etc.) to enter their experiences, areas of interest, and hobbies and preferences. This input is done using an HTML form, and data is collected through UI elements such as text boxes and drop-down lists. For example, users can enter "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[1323] Information transmission and emotion recognition

[1324] Once the user has finished entering the information, the device sends this information to the server as a POST request. During this transmission process, the device's built-in emotion recognition software recognizes the user's emotional state. Emotion recognition is performed using the device's built-in camera and microphone to capture the user's facial expression and voice data, and then uses an emotion recognition algorithm (such as OpenCV or Microsoft Azure's Emotion API). The emotional state is evaluated as "positive" or "negative."

[1325] Information storage

[1326] The server receives the information and emotional state sent by the user and stores them in a database (e.g., PostgreSQL). The stored information includes:

[1327] Experience: 3 years of programming experience

[1328] Area of ​​interest: Data Science

[1329] Hobbies: Reading and traveling

[1330] Emotional state: Positive

[1331] Generating recommendations

[1332] The server creates and sends prompts to the AI ​​based on the information stored in the memory. These prompts include the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the prompt text might look like this:

[1333] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[1334] The server sends this prompt to a generative AI (e.g., OpenAI's GPT-3 model), which then generates recommendations for appropriate companies and industries.

[1335] Sending and displaying recommendations

[1336] The server sends the recommendation information received from the generation AI in JSON format to the user's device. The device analyzes the received recommendation information and displays it on the screen. The display uses JavaScript to dynamically update the UI, allowing the user to view information about recommended companies and industries.

[1337] Specific examples

[1338] For example, if a user enters "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and the emotional state is recognized as positive, the system will act as follows:

[1339] 1. Information input and emotion recognition

[1340] The user enters information into a form on the device, and emotion recognition software recognizes positive emotional states.

[1341] 2. Transmission and storage of information

[1342] The device sends the information and the perceived emotional state to a server, which stores it in a database.

[1343] 3. Requests and Responses to Generative AI

[1344] The server creates a prompt and sends an API request to the generating AI.

[1345] The generative AI creates recommendations in a positive tone, such as, "You'd be well suited to a company where you can grow in the field of data science. You might also want to consider a career as a data analyst or machine learning engineer."

[1346] 4. Sending and Displaying Recommendations

[1347] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[1348] The system allows users to receive customized company and industry recommendations based on their experience, interests, and emotional state, enabling them to conduct a more effective job search.

[1349] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1350] Step 1: Enter your information

[1351] Users enter their experiences, areas of interest, and hobbies and preferences into a form on their device (PC, smartphone, tablet, etc.). This form is set up in HTML format, and data is collected through UI elements such as text boxes and drop-down lists. For example, a user might enter "3 years of programming experience," "Interested in data science," and "My hobbies are reading and traveling." The entered information is temporarily saved in the device's browser.

[1352] input:

[1353] User experience, areas of interest, hobbies and preferences

[1354] output:

[1355] Data stored on the device as user-entered information

[1356] Step 2: Information transmission and emotion recognition

[1357] The device sends the information entered by the user to the server as a POST request. At the same time, the device's built-in camera and microphone capture the user's facial expression and voice data, which are then sent to emotion recognition software (such as OpenCV or Microsoft Azure's Emotion API). This emotion recognition algorithm analyzes the user's emotional state at the time of input and classifies it as positive, negative, etc.

[1358] input:

[1359] User experience, areas of interest, hobbies and preferences

[1360] User's facial expression data, voice data

[1361] output:

[1362] User data and emotional state sent to the server as a POST request

[1363] Step 3: Save your information

[1364] The server receives POST requests from the device and processes the input information and emotional state. This information is then stored in a database such as PostgreSQL. The data stored includes the user's experience, areas of interest, hobbies, and emotional state.

[1365] input:

[1366] User input information, emotional state

[1367] output:

[1368] Information stored in a database

[1369] Step 4: Generate a prompt statement

[1370] The server creates a prompt sentence to be sent to the generation AI based on the information stored in the storage means. This prompt sentence includes the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the following prompt sentence is generated:

[1371] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[1372] input:

[1373] User information and emotional state stored in the database

[1374] output:

[1375] Prompt to send to the generation AI

[1376] Step 5: Generate recommendations

[1377] The server sends a prompt to a generative AI (e.g., OpenAI's GPT-3 model), which generates recommendations for companies and industries suitable for the user based on the prompt. The generated recommendations contain positive tones and specific suggestions.

[1378] input:

[1379] Prompt statement

[1380] output:

[1381] Generated recommendations

[1382] Step 6: Submit and view your recommendations

[1383] The server receives the recommendation information returned by the generation AI, converts it to JSON format, and sends it to the user's device. The device then analyzes the received recommendation information and generates HTML elements to display on the screen. Dynamic UI updates are performed using JavaScript, allowing the user to view information on recommended companies and industries.

[1384] input:

[1385] Generated recommendations

[1386] output:

[1387] Recommendation information displayed on the user's device

[1388] Through the above processing steps, users can receive customized recommendation information based on their experiences, interests, hobbies, preferences, and emotional state, allowing them to conduct a more effective job search.

[1389] (Application example 2)

[1390] 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."

[1391] Conventional job-hunting support systems can provide recommended information based on a user's experience, areas of interest, and hobbies and preferences, but they cannot provide customized recommended information that takes into account the user's emotional state. This makes it difficult for users to obtain recommended information that is truly interesting and psychologically appropriate.

[1392] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for allowing a user to input their experiences, areas of interest, and hobbies and preferences; means for transmitting the input information to the server; means for storing the input information received by the server in a storage means; means for generating recommendation information using a generation AI based on the information stored in the storage means; means for transmitting the generated recommendation information to the user; means for the user to view the sent recommendation information; means for recognizing the user's emotional state from voice and facial expressions using an emotion engine; and means for generating recommendation information taking the emotional state into consideration. This enables the user to obtain customized recommendation information based not only on their own experiences and interests but also on their current emotional state.

[1393] A "user" is an entity that uses the system to input their experiences, areas of interest, hobbies, and preferences.

[1394] "Experience" is information indicating the activities and skills that the user has engaged in in the past.

[1395] "Areas of interest" is information that indicates areas of expertise or topics that interest a user.

[1396] "Hobbies and preferences" is information that indicates the activities and preferences that a user enjoys on a daily basis.

[1397] A "server" is a central device that receives, stores, and processes information sent by users.

[1398] "Storage means" refers to data storage for saving input information received by the server.

[1399] "Generation AI" is artificial intelligence that generates recommendation information based on information stored in a storage device.

[1400] "Recommended information" is information on appropriate content, industries, companies, etc. provided by the generation AI based on user input information.

[1401] An "emotion engine" is an algorithm or system that analyzes a user's voice and facial expressions to assess their emotional state.

[1402] A "prompt" is data containing information such as a user's experience and emotional state that is used as input to a generative AI.

[1403] "Content" refers to information such as movies, books, podcasts, etc. that is provided as recommended information.

[1404] This invention is a system that provides recommended content based on a user's experience, areas of interest, hobbies, preferences, and current emotional state. This system collects user input information, sends it to a server, and generates customized recommendation information using a generative AI and an emotion engine.

[1405] The server performs processing using the following hardware and software. For hardware, the server uses a cloud server equipped with high-performance data storage and processors. For software, a web framework is built using Flask, emotion recognition is performed using EmotionEngine, and recommendation processing is performed using an AIRecommender generative AI model. A database is also used as storage.

[1406] First, a user uses a smartphone or desktop device to enter information about their experiences, areas of interest, and hobbies and preferences. Specifically, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." At the same time, the user's current emotional state is also captured using voice input or facial recognition.

[1407] The device sends the information entered by the user and the collected emotional data to the server. Upon receiving this information, the server analyzes the emotional state using the Emotion Engine and stores all information along with the analysis results in a database. The server then generates a prompt based on the storage means and sends the prompt to the generation AI. Based on this prompt, the generation AI generates recommended content that is optimal for the user.

[1408] The generated recommendation content is sent from the server to the user's device and displayed on the device screen. For example, if the user expresses positive emotions, the server will display recommended content with a positive tone, such as "recommended action movies," "fantasy web novels," and "related podcasts."

[1409] For example, the following prompt is generated and sent to the generator AI:

[1410] User Information:

[1411] Experience: I watch a lot of action movies

[1412] Areas of interest: Fantasy

[1413] Hobbies and interests: Reading

[1414] Emotional state: Positive

[1415] Using this prompt, the AI ​​generates recommendations for movies, books, podcasts, and other content that are best suited to the user, and sends them to the user's device, allowing the user to obtain customized recommendations based on their interests and emotional state.

[1416] The invention is characterized by the fact that a recommendation system using generative AI provides customized information that takes into account the user's emotions, making it easier for users to efficiently discover content that will provide them with greater satisfaction.

[1417] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1418] Step 1:

[1419] Users use their smartphones or desktop devices to enter information about their experiences, areas of interest, and hobbies. For example, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." Input is done using pull-down menus and free text format.

[1420] Input: User experience, areas of interest, hobbies and preferences

[1421] Output: User input information

[1422] Step 2:

[1423] After the user completes the input, the Emotion Engine recognizes the user's emotional state at that time using voice input or facial recognition. The Emotion Engine analyzes voice tone and facial expression data to classify the emotional state as positive, negative, neutral, etc.

[1424] Input: User voice or facial recognition data

[1425] Output: User's emotional state

[1426] Step 3:

[1427] The device sends the user-entered information and the recognized emotional state to the server, structured as a POST request via the API.

[1428] Input: User input information, user emotional state

[1429] Output: API request to the server

[1430] Step 4:

[1431] The server stores the received inputs and emotional states in a database, which organizes them for each user and later uses them to send prompts to the generative AI model.

[1432] Input: API request data (user input information, emotional state)

[1433] Output: User information stored in the database

[1434] Step 5:

[1435] The server creates prompts based on the information stored in the database and sends API requests to the generative AI model (AIRecommender). The prompts include the user's experience, areas of interest, hobbies, and emotional state.

[1436] Input: Database user information

[1437] Output: prompts to the generative AI model

[1438] Step 6:

[1439] The generative AI model receives the prompts and generates optimal recommended content based on the user's information and emotional state, which is returned in JSON format and sent to the server.

[1440] Input: prompt to generative AI model

[1441] Output: Recommended content (JSON format)

[1442] Step 7:

[1443] The server then sends the generated recommended content to the device, which then displays it to the user, who can then browse the recommended information for movies, books, podcasts, etc. on the screen.

[1444] Input: Recommended content (JSON format)

[1445] Output: Recommendation information displayed on the user's device

[1446] Through the above processing steps, users can receive content recommendations that are customized according to their interests and emotional state. This system allows users to efficiently discover content that will provide them with greater satisfaction.

[1447] 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.

[1448] 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.

[1449] 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.

[1450] [Fourth embodiment]

[1451] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1452] 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.

[1453] 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).

[1454] 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.

[1455] 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.

[1456] 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).

[1457] 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.

[1458] 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.

[1459] 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.

[1460] 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.

[1461] 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.

[1462] 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.

[1463] 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."

[1464] This invention is a system that utilizes generative AI to support students in their job hunting activities. Users can input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server to obtain recommended information on companies and industries that suit them. This system includes the following means.

[1465] User input

[1466] Users enter information such as their experience, areas of interest, hobbies, etc. into a form on the device. For example, they can enter "3 years of programming experience" in the experience section, "data science" in the area of ​​interest, and "reading and traveling" in the hobbies and hobbies section.

[1467] Sending and storing information

[1468] The device sends the above input information to the server as a POST request. When the server receives this request, it stores the obtained information in variables and saves it in the UserProfile model. For example, the information is recorded as follows:

[1469] Experience: 3 years of programming experience

[1470] Area of ​​interest: Data Science

[1471] Hobbies: Reading and traveling

[1472] Generating recommendations

[1473] The server generates a prompt based on the user information stored in the storage device and sends an API request to the AI ​​generator. This prompt includes the user's experience, areas of interest, and hobbies and preferences. The AI ​​generator then uses this information to create recommendations for appropriate companies and industries. For example, the following response might be generated:

[1474] “Based on your profile, you would be interested in companies where you can work in the field of data science. Specifically, companies with a reputation for being a data analyst, machine learning engineer, or data scientist.”

[1475] Sending and displaying recommendations

[1476] The server sends the generated recommendation information to the user in JSON format, and the device displays the received recommendation information on the screen so that the user can view it.

[1477] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[1478] Specific examples

[1479] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[1480] 1. Sending input information

[1481] The user enters information into a form on the terminal and sends it to the server.

[1482] 2. Storage of Information

[1483] The server stores the received information in the UserProfile model.

[1484] 3. Requests to Generative AI

[1485] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[1486] 4. Receiving Recommendations

[1487] Receive the response from the generation AI and extract the recommendation information.

[1488] 5. Display of Recommendations

[1489] The extracted information is sent in JSON format to the user's device, and the device displays the recommended information.

[1490] This allows users to receive specific recommendations such as "companies where you can work in the field of data science" or "companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[1491] The processing flow will be explained below.

[1492] Step 1:

[1493] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into a form displayed on the terminal. For example, "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[1494] Step 2:

[1495] The terminal sends the entered information to the server. The entered information is sent in the form of a POST request. An example of the data sent is as follows:

[1496] json

[1497] {

[1498] "experience": "3 years of programming experience",

[1499] "interests": "data science",

[1500] "hobbies": "reading and traveling"

[1501] }

[1502] Step 3:

[1503] The server receives the POST request and receives the input information. Specifically, it stores the data sent by the user in a variable using the request.POST method.

[1504] Step 4:

[1505] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, and preferences in a database. An example of the storage process is as follows:

[1506] python

[1507] user_profile = UserProfile(

[1508] experience=request.POST['experience'],

[1509] interests=request.POST['interests'],

[1510] hobbies=request.POST['hobbies']

[1511] )

[1512] user_profile.save()

[1513] Step 5:

[1514] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[1515] python

[1516] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}"

[1517] Step 6:

[1518] The server sends a prompt to the Generator AI. Specifically, it sends a request to the Generator AI's API, asking for a response to recommend companies and industries suitable for the user. An example request is as follows:

[1519] python

[1520] response = openai.Completion.create(

[1521] engine="text-davinci-003",

[1522] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[1523] max_tokens=150

[1524] )

[1525] Step 7:

[1526] The server receives a response from the generative AI, which includes company and industry recommendations based on the user's input. For example, the response might include recommendations like:

[1527] "You'll be interested in companies where you can work in the data science field. For example, there are companies that are well-known for being data analysts, machine learning engineers, and data scientists."

[1528] Step 8:

[1529] The server extracts the generated AI's response as recommendation information and sends it back to the user's device in JSON format. An example of sending the extracted information as a JSON response is as follows:

[1530] python

[1531] return JsonResponse({'recommendations': recommendations})

[1532] Step 9:

[1533] The device receives the JSON response from the server, analyzes the received recommendation information, and displays it on the screen.

[1534] Step 10:

[1535] The user browses the recommendations displayed on the device screen, providing specific information to help them find the right company or industry based on their experience and interests.

[1536] These are the processing steps of this system, which allows users to proceed with their job search effectively and efficiently.

[1537] Example 1

[1538] 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."

[1539] Conventional job-hunting support systems have difficulty recommending appropriate companies and industries based on users' experiences and interests, forcing students to search through a wide variety of information to find the right fit. Furthermore, the methods for inputting information and displaying recommended information are limited, resulting in a suboptimal user experience.

[1540] 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.

[1541] In this invention, the server includes a means for allowing the user to input their experiences, areas of interest, and hobbies and preferences, a means for sending prompts to the generation AI, and a means for organizing the recommendation information received from the generation AI, thereby enabling the user to receive accurate and appropriate recommendations for companies and industries based on their own information.

[1542] "User" refers to an individual who uses the system to receive support in their job search.

[1543] "Experience" refers to the knowledge, skills, and work experience that a user has accumulated in the past.

[1544] "Areas of interest" refers to a particular industry or research area that interests a user.

[1545] "Hobbies" refers to activities and tendencies that a user personally enjoys.

[1546] "Terminal" refers to a device, such as a computer or smartphone, that a user uses to input information.

[1547] "Server" refers to a computer system responsible for receiving, storing, and processing information sent by users.

[1548] "Storage means" refers to a database or storage system for saving user information on a server.

[1549] "Generative AI" refers to an artificial intelligence model that generates recommendation information based on user input information.

[1550] A "prompt sentence" refers to an input sentence that provides the necessary information to the generation AI.

[1551] "Recommended information" refers to information about appropriate companies and industries generated by the generating AI based on information input by the user.

[1552] This invention is a system that uses generative AI to support students in their job hunting. Users input information such as their experience, areas of interest, hobbies, and preferences into a terminal and send it to a server, allowing them to obtain recommended information on companies and industries that suit them.

[1553] Hardware and software used

[1554] The system uses the following hardware and software:

[1555] Terminal: A device such as a computer or smartphone on which a user inputs information and views recommendations.

[1556] Server: A computer system that processes information received from the user, sends prompts to the generation AI, and sends recommendation information to the user.

[1557] Storage means: A database or storage system on the server for saving user input information

[1558] Generative AI: An artificial intelligence model that generates recommendations based on user input (e.g., GPT-3)

[1559] Data processing and calculation

[1560] User input

[1561] Users use a form on the device to enter information about their experience, areas of interest, hobbies, etc. For example, a user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[1562] Sending and storing information

[1563] The device converts the input information into JSON format and sends it to the server as a POST request. The server analyzes the received information, stores it in variables, and saves it in a storage means (database). For example, the following information is saved:

[1564] Experience: 3 years of programming experience

[1565] Area of ​​interest: Data Science

[1566] Hobbies: Reading and traveling

[1567] Generating recommendations

[1568] The server generates a prompt to send to the AI ​​based on the user information stored in the memory. This prompt has the following format:

[1569] User Information:

[1570] Experience: 3 years of programming experience

[1571] Area of ​​interest: Data Science

[1572] Hobbies: Reading and traveling

[1573] Recommend companies and industries that fit this user.

[1574] The server sends this prompt to the generation AI, which generates recommendation information for appropriate companies and industries. The generation AI generates recommendation information based on the prompt and responds to the server.

[1575] Sending and displaying recommendations

[1576] The server organizes the recommendation information received from the generation AI and sends it in JSON format to the user's device, where it is displayed for viewing by the user.

[1577] Specific examples

[1578] For example, if a user enters "3 years of programming experience," "Interested in data science," and "Hobbies are reading and traveling," the following processing will occur:

[1579] 1. The user enters information into a form on the terminal and sends it to the server.

[1580] 2. The server stores the received information in a storage means.

[1581] 3. The server generates a prompt based on the stored information and sends a request to the generation AI.

[1582] 4. The generation AI generates recommendation information and responds to the server.

[1583] 5. The server organizes the recommendation information and sends it to the user's device.

[1584] 6. The device displays the recommended information and the user views it.

[1585] This system allows students to receive recommendations from appropriate companies and industries based on their experience and interests, making their job search more effective.

[1586] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1587] Step 1:

[1588] The user uses a device to input information about their experience, areas of interest, hobbies, and preferences. The input information may be "3 years of programming experience," "interest in data science," or "hobbies are reading and traveling." The input data is converted into JSON format.

[1589] Step 2:

[1590] The device sends the entered information to the server as a POST request in JSON format. For example, the following JSON data is sent to the server:

[1591] json

[1592] {

[1593] "experience": "3 years of programming experience",

[1594] "interest": "data science",

[1595] "hobbies": "reading and traveling"

[1596] }

[1597] Input: User-entered data

[1598] Output: POST request in JSON format

[1599] Step 3:

[1600] The server receives the POST request, analyzes its contents, and stores them in variables. The server then saves this information in a storage means (database). A database operation is performed to save the information in the storage means.

[1601] Input: User information in JSON format

[1602] Output: User information stored in the database

[1603] Step 4:

[1604] The server generates a prompt sentence to send to the generation AI based on the user information stored in the storage means. The prompt sentence is specifically constructed based on the user information. For example, the following prompt sentence is generated:

[1605] User Information:

[1606] Experience: 3 years of programming experience

[1607] Area of ​​interest: Data Science

[1608] Hobbies: Reading and traveling

[1609] Recommend companies and industries that fit this user.

[1610] Input: User information stored in the database

[1611] Output: Generated prompt statement

[1612] Step 5:

[1613] The server sends the generated prompt to the AI's API, creates an API request, and sends it to the AI ​​model (e.g., GPT-3). At this time, the server formats the prompt to fit the AI's needs.

[1614] Input: Generated prompt text

[1615] Output: API request

[1616] Step 6:

[1617] The Generator AI receives API requests from the server, processes them, and generates recommendations for companies and industries suitable for the user. The following data is returned as recommendations:

[1618] json

[1619] {

[1620] "recommendations": [

[1621] "Companies where you can thrive in the field of data science,"

[1622] "A well-known company for data analysts, machine learning engineers, and data scientists"

[1623] ]

[1624] }

[1625] Input: API request

[1626] Output: Recommendation

[1627] Step 7:

[1628] The server analyzes the recommendation information received from the AI ​​generator and sends it to the user's device in JSON format, where data may be reformatted or filtered.

[1629] Input: Recommendation information received from the generation AI

[1630] Output: Recommendations in JSON format

[1631] Step 8:

[1632] The device displays the JSON-formatted recommendation information received from the server on its screen, and the user can view the recommended companies and industry information on the device screen.

[1633] Input: Recommendation information in JSON format

[1634] Output: Recommendations displayed on screen

[1635] (Application example 1)

[1636] 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."

[1637] In today's job-hunting environment, students are faced with a vast amount of information to find the right company or industry, making it difficult to effectively select candidates. With the proliferation of online job fairs and company information sessions, students lack the means to obtain information in a virtual space and connect with companies that are right for them. This problem prevents students from finding the right company and reduces the efficiency of their job-hunting process.

[1638] 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.

[1639] In this invention, the server includes means for having the user input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information to the server, and means for storing the input information received by the server in storage means. This allows the server to view the transmitted recommendation information, means for the user to visit recommended company booths in the virtual space and participate in company information sessions and interview simulations, and means for transmitting the generated recommendation information to the user, making it possible for the generation AI to recommend industries or companies based on the user's input information.

[1640] "Users" refer to individuals who use the system, particularly students looking for jobs.

[1641] "Experience" refers to the skills and knowledge that a user has acquired through study, work, etc.

[1642] "Areas of interest" refers to academic or industrial fields in which the user is interested.

[1643] "Hobbies and preferences" refer to the activities and interests that a user likes to engage in in their daily life.

[1644] A "server" is a computer system that receives, stores, and processes information from users.

[1645] "Storage means" refers to a database or storage system for saving information input by a user.

[1646] "Generative AI" refers to artificial intelligence that generates appropriate recommendation information based on user information.

[1647] "Recommendation information" refers to information about companies and industries that is generated by the generative AI and presented to users.

[1648] The "viewing means" refers to a method by which a user can check the recommended information through a terminal or device.

[1649] "Virtual space" refers to a virtual reality environment created by computer simulation.

[1650] A "company booth" is anything other than a virtual location within a virtual space where a specific company gives a company presentation or conducts interviews.

[1651] A "company information session" is an event where a company introduces its company overview, vision, recruitment information, etc. to students.

[1652] An "interview simulation" is an interactive process that allows users to virtually experience an interview with a company.

[1653] A "prompt" is text that provides questions or instructions to the generating AI based on user information.

[1654] The present invention is a system for enabling students to more effectively conduct their job hunting activities.

[1655] The system starts when the user inputs information such as their experiences, areas of interest, hobbies, and preferences via a terminal. This terminal can be a smartphone or a head-mounted display (HMD). The input information is sent to the server and stored in the server's memory.

[1656] The server generates a prompt based on the stored information and sends an API request to the generative AI. This API uses OpenAI's generative AI model. An example of a generated prompt is, "User experience: 3 years of programming experience\nArea of ​​interest: Data science\nHobbies: Reading and travel\nBased on this, please generate recommendations for appropriate companies and industries."

[1657] Based on this, the AI ​​generates recommendations for companies and industries that are suitable for the user. The recommendation information is sent from the server in JSON format to the user's device, where it is displayed.

[1658] Furthermore, users can visit recommended company booths in the virtual space and participate in company information sessions and interview simulations. This virtual space is realized using an HMD.

[1659] Specifically, the process is as follows:

[1660] 1. The user uses a smartphone or HMD to input information such as their experiences, areas of interest, hobbies, and preferences.

[1661] 2. The terminal sends the entered information to the server.

[1662] 3. The server stores the received information in a storage means.

[1663] 4. The server generates a prompt for the AI ​​based on the stored information and sends an API request.

[1664] 5. The generation AI generates recommendation information for appropriate companies and industries and returns it to the server.

[1665] 6. The server sends the recommendation information to the user's device, which displays it.

[1666] 7. Users visit the recommended company booths in the virtual space and participate in company information sessions and interview simulations.

[1667] The specific hardware used includes smartphones and HMDs (e.g., Oculus Rift), and the servers are general cloud servers (e.g., AWS EC2).The software used includes Flask (a Python framework), OpenAI's generative AI API, and SQL.

[1668] This allows students to receive recommendations for suitable companies and industries based on their experience and interests, and conduct more effective job hunting through virtual company information sessions and interview experiences.

[1669] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1670] Step 1:

[1671] Users use a smartphone or HMD to input information such as their experience, areas of interest, and hobbies and preferences. This input information includes "3 years of programming experience" as experience, "data science" as an area of ​​interest, and "reading and traveling" as hobbies and preferences. The device then captures this input information into a form.

[1672] Step 2:

[1673] The terminal sends the information entered by the user to the server. Specifically, the input information is sent to the server as a POST request. The data format when sent is JSON, as shown below.

[1674] JSON

[1675] {

[1676] "experience": "3 years of programming experience",

[1677] "interest": "data science",

[1678] "hobby": "reading and traveling"

[1679] }

[1680] Step 3:

[1681] The server saves the received information in a storage device. The server analyzes the received JSON data and stores the information in the corresponding fields. Specifically, it is stored in the UserProfile model. The data processing here involves storing the JSON data fields in variables and inserting them into the corresponding columns in the database.

[1682] Step 4:

[1683] The server generates a prompt for the AI ​​based on the information stored in the storage means. Specifically, it generates the following prompt sentence:

[1684] "User experience: 3 years of programming experience.\nInterests: Data science.\nHobbies: Reading and travel.\nBased on this, generate recommendations for appropriate companies and industries."

[1685] Step 5:

[1686] The server sends an API request containing the generated prompt to the AI ​​generator. This uses the OpenAI AI generator API. The API request includes the prompt text. When the server sends this request, the AI ​​generator responds.

[1687] Step 6:

[1688] Based on the prompt received, the generation AI generates recommendations for companies and industries that are suitable for the user. The generation AI performs natural language processing and data analysis internally to generate appropriate recommendations. This recommendation information is returned in the form of a statement such as, "Companies where you can work in the field of data science. Specifically, companies that are well-known for data analysts, machine learning engineers, and data scientists are considered."

[1689] Step 7:

[1690] The server sends the recommendation information received from the generation AI to the user. Specifically, it converts the generated recommendation information into JSON format and sends it to the device. The JSON data sent is in the following format.

[1691] JSON

[1692] {

[1693] "recommendations": "Companies where you can work in the field of data science. Specifically, companies that are well-known for their data analysts, machine learning engineers, and data scientists."

[1694] }

[1695] Step 8:

[1696] The device displays the received recommendation information on its screen. The user can view the information and visit company booths in the virtual space as needed. The virtual space is controlled using an HMD, allowing users to participate in company information sessions and interview simulations.

[1697] 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.

[1698] This invention is a system that utilizes generative AI and an emotion engine to support students in their job hunting. Users input their experiences, areas of interest, and hobbies and preferences into a terminal, and the emotion engine recognizes the user's emotions at the time of input, generating more precisely customized recommendation information. We will explain the specific system flow and the operation of each element.

[1699] User input

[1700] Users enter their experience, areas of interest, and hobbies into a form on their device. For example, they can enter "3 years of programming experience," "Interested in data science," or "My hobbies are reading and traveling."

[1701] Information transmission and emotion recognition

[1702] When the device sends the above input information to the server as a POST request, the emotion engine recognizes the emotion of the user when they input the information. The emotion engine analyzes the user's voice and facial expressions to evaluate their emotional state. For example, if the input is made with a happy expression, it is recognized as "positive," and if it is made with a confused expression, it is recognized as "negative."

[1703] Information storage

[1704] The server receives the POST request and stores the input information and the evaluation results of the emotion engine in a storage device. For example, the following information is recorded:

[1705] Experience: 3 years of programming experience

[1706] Area of ​​interest: Data Science

[1707] Hobbies: Reading and traveling

[1708] Emotional state: Positive

[1709] Generating recommendations

[1710] The server creates a prompt for the generation AI based on the information stored in the memory and sends an API request. This prompt includes the user's experience, areas of interest, hobbies, and preferences, as well as the emotional state evaluated by the emotion engine. The generation AI uses this information to create recommendations for appropriate companies and industries. If the emotional state is positive, the system will make recommendations in a positive tone, and if it is negative, the system will use more detailed and reassuring language than usual.

[1711] Sending and displaying recommendations

[1712] The server sends the generated recommendation information in JSON format to the user's device, which then displays the received recommendation information on the screen for the user to view.

[1713] Specific examples

[1714] As a concrete example, if a user inputs "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and a positive emotional state is recognized, the following processing will occur:

[1715] 1. Information input and emotion recognition

[1716] The user enters information into a form on the device, and the emotion engine recognizes positive emotional states.

[1717] 2. Transmission and storage of information

[1718] The terminal transmits the information and the recognized emotional state to a server, which stores it in a storage means.

[1719] 3. Requests and Responses to Generative AI

[1720] The server generates a prompt based on the stored information and sends an API request to the generation AI.

[1721] The generative AI responds and creates recommendations with a positive tone.

[1722] For example: "You'd be well-suited to a company where you can grow in data science. Consider a career as a data analyst or machine learning engineer."

[1723] 4. Display of recommendation information

[1724] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[1725] The system allows users to receive relevant and customized recommendations for companies and industries based on their experience, interests, and emotional state, making their job search more effective.

[1726] The processing flow will be explained below.

[1727] Step 1:

[1728] The user enters information into the terminal. Specifically, the user enters their experience, areas of interest, and hobbies into the form displayed on the terminal. For example, the user might enter "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling."

[1729] Step 2:

[1730] The device activates an emotion engine to recognize the user's emotions when they input. The emotion engine uses a camera and microphone to analyze the user's facial expressions and voice to determine their emotional state. For example, it classifies emotional states as positive, negative, or neutral.

[1731] Step 3:

[1732] The device sends the input information and the recognized emotional state to the server. The information is sent to the server as a POST request, with example data as follows:

[1733] json

[1734] {

[1735] "experience": "3 years of programming experience",

[1736] "interests": "data science",

[1737] "hobbies": "reading and traveling",

[1738] "emotion": "positive"

[1739] }

[1740] Step 4:

[1741] The server receives the POST request and stores the input information and emotional state in variables. For example, it processes the data as follows:

[1742] python

[1743] experience = request.POST['experience']

[1744] interests = request.POST['interests']

[1745] hobbies = request.POST['hobbies']

[1746] emotion = request.POST['emotion']

[1747] Step 5:

[1748] The server stores the received information in a UserProfile model, which stores the user's experiences, interests, preferences, and emotional state in a database. An example of the storage process is as follows:

[1749] python

[1750] user_profile = UserProfile(

[1751] experience=experience,

[1752] interests=interests,

[1753] hobbies=hobbies,

[1754] emotion=emotion

[1755] )

[1756] user_profile.save()

[1757] Step 6:

[1758] The server creates a prompt for the AI ​​based on the information stored in the storage device. The created prompt is as follows:

[1759] python

[1760] user_input = f"Experience: {user_profile.experience}, Interests: {user_profile.interests}, Hobbies: {user_profile.hobbies}, Emotion: {user_profile.emotion}"

[1761] Step 7:

[1762] The server sends a prompt to the Generator AI, which makes a request to the Generator AI's API for recommendations of suitable companies and industries. An example request is as follows:

[1763] python

[1764] response = openai.Completion.create(

[1765] engine="text-davinci-003",

[1766] prompt=f"Recommend jobs or companies based on the following user profile: {user_input}",

[1767] max_tokens=150

[1768] )

[1769] Step 8:

[1770] The server receives the response from the AI ​​generator and extracts the recommendation information. For example, the following recommendation may be generated:

[1771] “Based on your profile, you may be interested in companies that offer jobs in the data science field. You may also consider a career as a data analyst or machine learning engineer.”

[1772] Step 9:

[1773] The server sends the generated recommendation information to the user's device. It also returns the information in JSON format to the device. Example:

[1774] python

[1775] return JsonResponse({'recommendations': recommendations})

[1776] Step 10:

[1777] The device receives the JSON response from the server and displays the recommended information on the screen. The user can then check the recommended information displayed on the device screen.

[1778] Step 11:

[1779] The user browses the recommendation information, which allows the user to obtain recommended information on companies and industries based on their own experiences, interests, and emotional state.

[1780] These are the processing steps of this system, which allows users to receive detailed support tailored to their emotional state while effectively and efficiently pursuing their job search.

[1781] Example 2

[1782] 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."

[1783] Conventional job-hunting support systems can only provide simple recommendations based on user input, and have the problem of being unable to provide customized support that takes into account the user's emotional state. This limits the ability of job seekers to find companies and industries that are more suitable for them.

[1784] 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 allowing a user to input their experiences, areas of interest, and hobbies and preferences, means for transmitting the input information and the user's emotional state to the server, means for storing the input information and the emotional state received by the server in a storage means, means for generating recommendation information by a generation AI based on the information and the emotional state stored in the storage means, means for transmitting the generated recommendation information to the user, and means for the user to view the transmitted recommendation information. This makes it possible to provide more sophisticated and customized recommendation information that takes into account the user's emotional state.

[1785] "User" refers to an individual who uses the system to input their experiences, areas of interest, and hobbies and preferences and receive recommendation information.

[1786] "Experience" refers to information indicating knowledge and skills related to work, learning, projects, etc. that a user has accumulated in the past.

[1787] "Areas of interest" refers to the job areas or research topics in which the user is interested.

[1788] "Hobbies and preferences" refers to information that indicates the activities that a user enjoys on a daily basis and the things that the user likes.

[1789] "Emotional state" refers to the psychological and emotional state of the user when inputting information, and is classified as positive, negative, or the like.

[1790] "Device" refers to the electronic device used by a user to input information and receive recommendation information, such as a PC, smartphone, or tablet.

[1791] "Server" refers to a computer system that receives and stores information from users, creates recommendation information based on the generation AI, and sends it to users.

[1792] "Storage means" refers to a database or storage device used by the server to store the user's input information and emotional state.

[1793] "Generative AI" refers to an artificial intelligence module that creates appropriate recommendations based on the user's input information and emotional state.

[1794] A "prompt" refers to an instruction or request sent to the generating AI, including the user's input information and emotional state.

[1795] "Recommendation information" refers to information about companies and industries recommended to users that is created by the generative AI based on the user's input information and emotional state.

[1796] This invention is a system that uses a generative AI and an emotion engine to help users conduct job hunting more effectively. Specific embodiments of this system are described below.

[1797] User input

[1798] Users use their own devices (PC, smartphone, tablet, etc.) to enter their experiences, areas of interest, and hobbies and preferences. This input is done using an HTML form, and data is collected through UI elements such as text boxes and drop-down lists. For example, users can enter "3 years of programming experience," "Interested in data science," "My hobbies are reading and traveling," etc.

[1799] Information transmission and emotion recognition

[1800] Once the user has finished entering the information, the device sends this information to the server as a POST request. During this transmission process, the device's built-in emotion recognition software recognizes the user's emotional state. Emotion recognition is performed using the device's built-in camera and microphone to capture the user's facial expression and voice data, and then uses an emotion recognition algorithm (such as OpenCV or Microsoft Azure's Emotion API). The emotional state is evaluated as "positive" or "negative."

[1801] Information storage

[1802] The server receives the information and emotional state sent by the user and stores them in a database (e.g., PostgreSQL). The stored information includes:

[1803] Experience: 3 years of programming experience

[1804] Area of ​​interest: Data Science

[1805] Hobbies: Reading and traveling

[1806] Emotional state: Positive

[1807] Generating recommendations

[1808] The server creates and sends prompts to the AI ​​based on the information stored in the memory. These prompts include the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the prompt text might look like this:

[1809] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[1810] The server sends this prompt to a generative AI (e.g., OpenAI's GPT-3 model), which then generates recommendations for appropriate companies and industries.

[1811] Sending and displaying recommendations

[1812] The server sends the recommendation information received from the generation AI in JSON format to the user's device. The device analyzes the received recommendation information and displays it on the screen. The display uses JavaScript to dynamically update the UI, allowing the user to view information about recommended companies and industries.

[1813] Specific examples

[1814] For example, if a user enters "3 years of programming experience," "interest in data science," and "hobbies are reading and traveling," and the emotional state is recognized as positive, the system will act as follows:

[1815] 1. Information input and emotion recognition

[1816] The user enters information into a form on the device, and emotion recognition software recognizes positive emotional states.

[1817] 2. Transmission and storage of information

[1818] The device sends the information and the perceived emotional state to a server, which stores it in a database.

[1819] 3. Requests and Responses to Generative AI

[1820] The server creates a prompt and sends an API request to the generating AI.

[1821] The generative AI creates recommendations in a positive tone, such as, "You'd be well suited to a company where you can grow in the field of data science. You might also want to consider a career as a data analyst or machine learning engineer."

[1822] 4. Sending and Displaying Recommendations

[1823] The server transmits the generated recommendation information to the terminal, which displays it to the user.

[1824] The system allows users to receive customized company and industry recommendations based on their experience, interests, and emotional state, enabling them to conduct a more effective job search.

[1825] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1826] Step 1: Enter your information

[1827] Users enter their experiences, areas of interest, and hobbies and preferences into a form on their device (PC, smartphone, tablet, etc.). This form is set up in HTML format, and data is collected through UI elements such as text boxes and drop-down lists. For example, a user might enter "3 years of programming experience," "Interested in data science," and "My hobbies are reading and traveling." The entered information is temporarily saved in the device's browser.

[1828] input:

[1829] User experience, areas of interest, hobbies and preferences

[1830] output:

[1831] Data stored on the device as user-entered information

[1832] Step 2: Information transmission and emotion recognition

[1833] The device sends the information entered by the user to the server as a POST request. At the same time, the device's built-in camera and microphone capture the user's facial expression and voice data, which are then sent to emotion recognition software (such as OpenCV or Microsoft Azure's Emotion API). This emotion recognition algorithm analyzes the user's emotional state at the time of input and classifies it as positive, negative, etc.

[1834] input:

[1835] User experience, areas of interest, hobbies and preferences

[1836] User's facial expression data, voice data

[1837] output:

[1838] User data and emotional state sent to the server as a POST request

[1839] Step 3: Save your information

[1840] The server receives POST requests from the device and processes the input information and emotional state. This information is then stored in a database such as PostgreSQL. The data stored includes the user's experience, areas of interest, hobbies, and emotional state.

[1841] input:

[1842] User input information, emotional state

[1843] output:

[1844] Information stored in a database

[1845] Step 4: Generate a prompt statement

[1846] The server creates a prompt sentence to be sent to the generation AI based on the information stored in the storage means. This prompt sentence includes the user's experience, areas of interest, hobbies, preferences, and emotional state. For example, the following prompt sentence is generated:

[1847] "User experience: 3 years of programming experience. Areas of interest: Data Science. Hobbies: Reading and traveling. Emotional state: Positive."

[1848] input:

[1849] User information and emotional state stored in the database

[1850] output:

[1851] Prompt to send to the generation AI

[1852] Step 5: Generate recommendations

[1853] The server sends a prompt to a generative AI (e.g., OpenAI's GPT-3 model), which generates recommendations for companies and industries suitable for the user based on the prompt. The generated recommendations contain positive tones and specific suggestions.

[1854] input:

[1855] Prompt statement

[1856] output:

[1857] Generated recommendations

[1858] Step 6: Submit and view your recommendations

[1859] The server receives the recommendation information returned by the generation AI, converts it to JSON format, and sends it to the user's device. The device then analyzes the received recommendation information and generates HTML elements to display on the screen. Dynamic UI updates are performed using JavaScript, allowing the user to view information on recommended companies and industries.

[1860] input:

[1861] Generated recommendations

[1862] output:

[1863] Recommendation information displayed on the user's device

[1864] Through the above processing steps, users can receive customized recommendation information based on their experiences, interests, hobbies, preferences, and emotional state, allowing them to conduct a more effective job search.

[1865] (Application example 2)

[1866] 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."

[1867] Conventional job-hunting support systems can provide recommended information based on a user's experience, areas of interest, and hobbies and preferences, but they cannot provide customized recommended information that takes into account the user's emotional state. This makes it difficult for users to obtain recommended information that is truly interesting and psychologically appropriate.

[1868] The specification process by the specification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for allowing a user to input their experiences, areas of interest, and hobbies and preferences; means for transmitting the input information to the server; means for storing the input information received by the server in a storage means; means for generating recommendation information using a generation AI based on the information stored in the storage means; means for transmitting the generated recommendation information to the user; means for the user to view the sent recommendation information; means for recognizing the user's emotional state from voice and facial expressions using an emotion engine; and means for generating recommendation information taking the emotional state into consideration. This enables the user to obtain customized recommendation information based not only on their own experiences and interests but also on their current emotional state.

[1869] A "user" is an entity that uses the system to input their experiences, areas of interest, hobbies, and preferences.

[1870] "Experience" is information indicating the activities and skills that the user has engaged in in the past.

[1871] "Areas of interest" is information that indicates areas of expertise or topics that interest a user.

[1872] "Hobbies and preferences" is information that indicates the activities and preferences that a user enjoys on a daily basis.

[1873] A "server" is a central device that receives, stores, and processes information sent by users.

[1874] "Storage means" refers to data storage for saving input information received by the server.

[1875] "Generation AI" is artificial intelligence that generates recommendation information based on information stored in a storage device.

[1876] "Recommended information" is information on appropriate content, industries, companies, etc. provided by the generation AI based on user input information.

[1877] An "emotion engine" is an algorithm or system that analyzes a user's voice and facial expressions to assess their emotional state.

[1878] A "prompt" is data containing information such as a user's experience and emotional state that is used as input to a generative AI.

[1879] "Content" refers to information such as movies, books, podcasts, etc. that is provided as recommended information.

[1880] This invention is a system that provides recommended content based on a user's experience, areas of interest, hobbies, preferences, and current emotional state. This system collects user input information, sends it to a server, and generates customized recommendation information using a generative AI and an emotion engine.

[1881] The server performs processing using the following hardware and software. For hardware, the server uses a cloud server equipped with high-performance data storage and processors. For software, a web framework is built using Flask, emotion recognition is performed using EmotionEngine, and recommendation processing is performed using an AIRecommender generative AI model. A database is also used as storage.

[1882] First, a user uses a smartphone or desktop device to enter information about their experiences, areas of interest, and hobbies and preferences. Specifically, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." At the same time, the user's current emotional state is also captured using voice input or facial recognition.

[1883] The device sends the information entered by the user and the collected emotional data to the server. Upon receiving this information, the server analyzes the emotional state using the Emotion Engine and stores all information along with the analysis results in a database. The server then generates a prompt based on the storage means and sends the prompt to the generation AI. Based on this prompt, the generation AI generates recommended content that is optimal for the user.

[1884] The generated recommendation content is sent from the server to the user's device and displayed on the device screen. For example, if the user expresses positive emotions, the server will display recommended content with a positive tone, such as "recommended action movies," "fantasy web novels," and "related podcasts."

[1885] For example, the following prompt is generated and sent to the generator AI:

[1886] User Information:

[1887] Experience: I watch a lot of action movies

[1888] Areas of interest: Fantasy

[1889] Hobbies and interests: Reading

[1890] Emotional state: Positive

[1891] Using this prompt, the AI ​​generates recommendations for movies, books, podcasts, and other content that are best suited to the user, and sends them to the user's device, allowing the user to obtain customized recommendations based on their interests and emotional state.

[1892] The invention is characterized by the fact that a recommendation system using generative AI provides customized information that takes into account the user's emotions, making it easier for users to efficiently discover content that will provide them with greater satisfaction.

[1893] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1894] Step 1:

[1895] Users use their smartphones or desktop devices to enter information about their experiences, areas of interest, and hobbies. For example, they enter information such as "I've been watching a lot of action movies lately," "The book I read recently was 'fantasy novels,'" and "My interest is fantasy." Input is done using pull-down menus and free text format.

[1896] Input: User experience, areas of interest, hobbies and preferences

[1897] Output: User input information

[1898] Step 2:

[1899] After the user completes the input, the Emotion Engine recognizes the user's emotional state at that time using voice input or facial recognition. The Emotion Engine analyzes voice tone and facial expression data to classify the emotional state as positive, negative, neutral, etc.

[1900] Input: User voice or facial recognition data

[1901] Output: User's emotional state

[1902] Step 3:

[1903] The device sends the user-entered information and the recognized emotional state to the server, structured as a POST request via the API.

[1904] Input: User input information, user emotional state

[1905] Output: API request to the server

[1906] Step 4:

[1907] The server stores the received inputs and emotional states in a database, which organizes them for each user and later uses them to send prompts to the generative AI model.

[1908] Input: API request data (user input information, emotional state)

[1909] Output: User information stored in the database

[1910] Step 5:

[1911] The server creates prompts based on the information stored in the database and sends API requests to the generative AI model (AIRecommender). The prompts include the user's experience, areas of interest, hobbies, and emotional state.

[1912] Input: Database user information

[1913] Output: prompts to the generative AI model

[1914] Step 6:

[1915] The generative AI model receives the prompts and generates optimal recommended content based on the user's information and emotional state, which is returned in JSON format and sent to the server.

[1916] Input: prompt to generative AI model

[1917] Output: Recommended content (JSON format)

[1918] Step 7:

[1919] The server then sends the generated recommended content to the device, which then displays it to the user, who can then browse the recommended information for movies, books, podcasts, etc. on the screen.

[1920] Input: Recommended content (JSON format)

[1921] Output: Recommendation information displayed on the user's device

[1922] Through the above processing steps, users can receive content recommendations that are customized according to their interests and emotional state. This system allows users to efficiently discover content that will provide them with greater satisfaction.

[1923] 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.

[1924] 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.

[1925] 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.

[1926] 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.

[1927] 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.

[1928] 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.

[1929] 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).

[1930] 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.

[1931] 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."

[1932] 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.

[1933] 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).

[1934] 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.

[1935] 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.

[1936] 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.

[1937] 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.

[1938] 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.

[1939] 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.

[1940] 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.

[1941] 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.

[1942] 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.

[1943] 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.

[1944] The following is further disclosed regarding the above embodiment.

[1945] (Claim 1)

[1946] A means for allowing a user to input their experiences, areas of interest, hobbies, and preferences;

[1947] means for transmitting the input information to a server;

[1948] A means for storing input information received by the server in a storage means;

[1949] A means for generating recommendation information by a generation AI based on the information stored in the storage means;

[1950] means for transmitting the generated recommendation information to a user;

[1951] A means for users to view the recommendations sent to them;

[1952] A system including:

[1953] (Claim 2)

[1954] The system of claim 1, characterized in that the generating AI recommends industries or companies based on user input information.

[1955] (Claim 3)

[1956] 2. The system of claim 1, further comprising means for generating a prompt using user input information and sending the prompt to the generation AI.

[1957] "Example 1"

[1958] (Claim 1)

[1959] A means for allowing a user to input their experiences, areas of interest, hobbies, and preferences;

[1960] means for transmitting the input information to a server;

[1961] A means for storing input information received by the server in a storage means;

[1962] A means for generating recommendation information by a generation AI based on the information stored in the storage means;

[1963] means for transmitting the generated recommendation information to a user;

[1964] A means for a user to view the sent recommendation information;

[1965] a means for sending a prompt to the generating AI;

[1966] A means for organizing the recommendation information received from the generative AI;

[1967] A system including:

[1968] (Claim 2)

[1969] The system of claim 1, characterized in that the generating AI recommends industries or companies based on user input information.

[1970] (Claim 3)

[1971] 2. The system according to claim 1, further comprising means for generating a prompt using information input by a user and sending the prompt sentence to the generation AI.

[1972] "Application Example 1"

[1973] (Claim 1)

[1974] A means for allowing a user to input their experiences, areas of interest, hobbies, and preferences;

[1975] means for transmitting the input information to a server;

[1976] A means for storing input information received by the server in a storage means;

[1977] A means for generating recommendation information by a generation AI based on the information stored in the storage means;

[1978] means for transmitting the generated recommendation information to a user;

[1979] A means for a user to view the sent recommendation information;

[1980] Users can visit recommended company booths in a virtual space and participate in company information sessions and interview simulations.

[1981] A system including:

[1982] (Claim 2)

[1983] The system of claim 1, characterized in that the generating AI recommends industries or companies based on user input information.

[1984] (Claim 3)

[1985] 2. The system of claim 1, further comprising means for generating a prompt using user input information and sending the prompt to the generation AI.

[1986] "Example 2: Combining Emotion Engines"

[1987] (Claim 1)

[1988] A means for allowing a user to input their experiences, areas of interest, hobbies, and preferences;

[1989] means for transmitting the input information and the user's emotional state to a server;

[1990] a means for storing the input information and emotional state received by the server in a storage means;

[1991] a means for generating recommendation information by a generation AI based on the information and emotional state stored in the storage means;

[1992] means for transmitting the generated recommendation information to a user;

[1993] A means for users to view the recommendations sent to them;

[1994] A system including:

[1995] (Claim 2)

[1996] The system of claim 1, wherein the generative AI recommends industries or companies based on the user's input information and emotional state.

[1997] (Claim 3)

[1998] 10. The system of claim 1, further comprising means for generating prompts using the user's input information and emotional state and sending the prompts to the generation AI.

[1999] "Application example 2 when combining emotion engines"

[2000] (Claim 1)

[2001] A means for allowing a user to input their experiences, areas of interest, hobbies, and preferences;

[2002] means for transmitting the input information to a server;

[2003] A means for storing input information received by the server in a storage means;

[2004] A means for generating recommendation information by a generation AI based on the information stored in the storage means;

[2005] means for transmitting the generated recommendation information to a user;

[2006] A means for a user to view the sent recommendation information;

[2007] A means for recognizing the user's emotional state from voice and facial expressions using an emotion engine;

[2008] means for generating recommendation information taking into account emotional states;

[2009] A system including:

[2010] (Claim 2)

[2011] The system of claim 1, characterized in that the generative AI recommends content based on the user's input information and emotional state.

[2012] (Claim 3)

[2013] 10. The system of claim 1, further comprising means for generating prompts using the user's input information and emotional state and sending the prompts to the generation AI. [Explanation of symbols]

[2014] 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 allowing a user to input their experiences, areas of interest, hobbies, and preferences; means for transmitting the input information to a server; A means for storing input information received by the server in a storage means; A means for generating recommendation information by a generation AI based on the information stored in the storage means; means for transmitting the generated recommendation information to a user; A means for users to view the recommendations sent to them; A system including:

2. The system of claim 1, wherein the generating AI recommends industries or companies based on user input information.

3. 2. The system of claim 1, further comprising means for generating a prompt using information input by a user and sending the prompt to the generation AI.

Images