system

Abstract

We provide the system. [Solution] A means for transferring information received from a user to an information processing device, The information processing device includes means for analyzing the user's characteristics and generating suggested information based on the results, Means for presenting the proposed information to the user via a display device or audio playback device, A means for converting user input into text data using speech recognition means, A means of reanalyzing user feedback and updating suggestion information, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] Many job seekers find it difficult to objectively evaluate their skills and aptitudes, making it difficult to make an optimal career choice. In addition, due to inappropriate career information and inaccurate data, job seekers may make incorrect career choices. The present invention aims to solve these problems and provide a system that provides accurate career plans to users.

Means for Solving the Problems

[0005] The present invention provides a system that transfers information received from a user to a processing device, analyzes the user's characteristics on the processing device, generates suggested information based on the results, and presents the suggested information to the user. The suggested information can include multiple career options based on the user's interests and skills, and the system also includes means for receiving feedback from the user regarding the suggested information and readjusting the suggested information based on that feedback.

[0006] A "user" refers to an individual who uses the system to evaluate their own skills and aptitudes and receive career plan suggestions.

[0007] "Information" refers to personal data provided by users, including work history, educational background, skill set, areas of interest, and career goals.

[0008] A "processing device" refers to a computer system that analyzes information received from users and generates suitability assessments and suggestion information.

[0009] "Suggested information" refers to information including career plans and job options generated based on the user's skills and aptitudes.

[0010] "Feedback" refers to the act of a user returning opinions or requests regarding suggested information to the system, or the content of such feedback. [Brief explanation of the drawing]

[0011] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0012] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0013] First, let's explain the terminology used in the following explanation.

[0014] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0015] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0016] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0017] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. 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), or Bluetooth (registered trademark).

[0018] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0019] [First Embodiment]

[0020] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0021] As shown in Figure 1, the 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.

[0022] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0023] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0024] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0025] 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 perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0026] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0027] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0028] As shown in Figure 2, in the data processing device 12, a specific processing 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" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0029] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0030] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0031] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0032] This invention provides an AI agent system that automatically proposes career plans based on information provided by the user. The system operates in a process where the user inputs information through a terminal, and that information is analyzed on a server. The server utilizes generative AI technology to generate suggestion information based on the user's skills, aptitudes, and past success stories.

[0033] The server is responsible for analyzing the user information it receives. For example, when a user enters their educational background, work history, acquired skills, and areas of interest into a terminal, the server receives this data and uses machine learning algorithms to evaluate the user's strengths and weaknesses. This allows for an objective and fair assessment of the user's suitability and identifies the most suitable career options. The server also takes into account the latest industry trend data to create a career plan that includes useful information for the user.

[0034] The generated suggestion information is sent to the terminal and displayed to the user. The user can evaluate the presented career plan and, if necessary, enter feedback into the terminal. The user's feedback is re-analyzed on the server, and the plan is updated as needed. This process helps users make the best career choices for themselves. For example, if a recent graduate aspiring to be an engineer enters their programming skills and technologies of interest into the terminal, the server analyzes this information and suggests specific job roles in the IT industry, required skills, and recommended methods for skill development.

[0035] The following describes the processing flow.

[0036] Step 1:

[0037] The user accesses the terminal and enters personal information, including data such as work history, education, skills, and areas of interest. The terminal receives the user's input and prepares the data according to the specified format.

[0038] Step 2:

[0039] The terminal sends the prepared user information to the server. The terminal uses secure communication methods during data transmission to maintain the confidentiality of user data.

[0040] Step 3:

[0041] The server stores the received user information in a database for analysis. The server then begins analyzing the data using the latest generative AI algorithms.

[0042] Step 4:

[0043] The server uses AI to evaluate the user's skills and aptitudes based on the input user data. The server also refers to a database of past success stories and the latest trends to generate the optimal career plan for the user.

[0044] Step 5:

[0045] The server generates a carrier plan and sends it to the device. The server formats the proposed information into a user-friendly format and sends it.

[0046] Step 6:

[0047] The device presents the received carrier plan to the user. The device displays plan details, recommended job roles, and additional information via the user interface.

[0048] Step 7:

[0049] Users review the presented career plan and provide feedback as needed. User feedback can include ratings, questions, and further requests.

[0050] Step 8:

[0051] The device sends user feedback to the server. The device formats the feedback data and quickly transmits it to the server.

[0052] Step 9:

[0053] The server receives the feedback and performs another analysis. The server takes the feedback into consideration, adjusts the career plan as needed, and makes new suggestions to the user.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] In today's increasingly diverse work environment, providing appropriate career advice based on individual interests, skills, and market trends is challenging. Traditionally, many career planning tools tend to take a uniform approach, making it difficult to provide personalized suggestions for each user.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for transferring information obtained from the user to an information processing device, means for analyzing the user's characteristics using a generation AI model and generating suggested information based on the results, and means for visually presenting the suggested information to the user. This enables career planning tailored to the individual needs of the user.

[0059] A "user" is an entity that uses the system to input their information and receive a career plan.

[0060] An "information processing device" is a computer system that receives and analyzes information obtained from users.

[0061] A "generative AI model" is an algorithm or software that utilizes artificial intelligence technology to analyze user characteristics and generate suggested information.

[0062] "Characteristics" refer to individual attributes of a user, such as their skills, aptitudes, and interests.

[0063] "Suggested information" refers to career options and advice generated based on the user's characteristics and market trends.

[0064] "Visual presentation" refers to displaying proposed information through a display or screen in a way that users can easily understand.

[0065] "Job options" refer to job and career choices that are deemed appropriate for the user.

[0066] "Input" refers to the feedback and additional information that users provide through the system.

[0067] This invention is a system aimed at providing users with appropriate suggestions regarding their career plans. Users first input information such as their educational background, work experience, skills, and areas of interest using a terminal. This input is done, for example, through a form on a smartphone or computer screen. The input information is then transmitted to a server via the internet.

[0068] The server acts as an information processing unit, receiving data from users. After preprocessing the received data, the server uses a generative AI model to perform data analysis. This model incorporates machine learning algorithms to analyze user characteristics and generate individually optimized career plans.

[0069] The career plan reflects the latest industry trends and suggests specific job options, such as "skills required as a data scientist" or "experience in front-end development." This suggested information is sent from the server to the user's terminal and presented visually. Users can review the suggestions on the screen and evaluate them based on their own thoughts and preferences.

[0070] Furthermore, users can input feedback on the proposed career plan from their device and send it back to the server. The server can then analyze this feedback and adjust or update the proposed plan.

[0071] As a concrete example, a prompt might say, "Please suggest suitable job roles for a recent graduate user aspiring to be an engineer." Using this prompt, the generating AI model will create specific career options that are appropriate for the user.

[0072] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0073] Step 1:

[0074] The user inputs information using a terminal. The user enters information such as educational background, work history, skills, and areas of interest into a form. This input data is then prepared by the terminal to be sent to the server. Specifically, the entered information is formatted in a digital format and converted into packets according to a communication protocol.

[0075] Step 2:

[0076] The server receives data from the terminal. The server preprocesses this received data. Specifically, it cleanses the data by imputing missing values ​​and detecting outliers. This process prepares the data for analysis. The input is the user's raw data, and the output is the processed dataset.

[0077] Step 3:

[0078] The server analyzes user data using a generated AI model. The server activates machine learning algorithms to analyze user characteristics. Specifically, it quantifies and evaluates user skills and aptitudes, and generates an appropriate career plan based on the results. The input is a pre-processed dataset, and the output is the evaluation result based on the analysis.

[0079] Step 4:

[0080] The server generates suggestion information based on the analysis results. Here, the generating AI model creates specific suggestion information that includes a career plan optimized for the user. This plan reflects job options based on the user's interests and skills, as well as industry trends. The server uses prompts to ask the AI ​​model appropriate questions and generate information. The output is visual information to be presented to the user.

[0081] Step 5:

[0082] The server sends the generated proposal information to the terminal. The terminal displays the received proposal information. The user can visually review the plan and provide evaluations and feedback. The output is in a format that the user can view.

[0083] Step 6:

[0084] Users input feedback to the server via their devices. Users provide feedback such as evaluations of the proposed career plan and requests for revisions. This feedback is then prepared to be sent back to the server as data. The input consists of user feedback information.

[0085] Step 7:

[0086] The server analyzes user feedback and updates the suggested information as needed. The server processes the feedback data and performs a re-analysis to generate a new career plan. This process enables optimization based on user feedback, ensuring that the final suggested information is better tailored to the user's needs.

[0087] (Application Example 1)

[0088] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Traditionally, users have required considerable time and effort to obtain career plans based on their aptitudes. Furthermore, there is a lack of systems that utilize voice recognition to provide career suggestions through natural, two-way communication with users. Therefore, there is a need for a new information provision system that offers intuitive and immediate suggestions to users.

[0090] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0091] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, and means for presenting the suggested information to the user via a display device or audio playback device. This allows the user to intuitively obtain an optimal career plan based on their interests and abilities, and enables natural interaction through communication utilizing speech recognition.

[0092] A "user" refers to an individual who inputs information and receives career plan suggestions.

[0093] An "information processing device" refers to a computer or server that analyzes data received from a user and generates suggested information.

[0094] "Characteristics" refers to the individual attributes and abilities necessary for generating a career plan, such as the user's educational background, work history, skills, and interests.

[0095] "Suggested information" refers to information that includes optimal career plans and occupational options for the user, generated based on the results of an analysis of the user's characteristics.

[0096] A "display device" refers to a screen or monitor used to visually present generated suggestion information to the user.

[0097] A "sound playback device" refers to a speaker used to present generated suggestion information to the user audibly.

[0098] "Voice recognition means" refers to a system or technology for converting a user's voice input into text data.

[0099] "Feedback" refers to the opinions and suggestions for improvement that users provide regarding proposed information.

[0100] "Interaction" refers to the exchanges and responses that occur between the user and the system.

[0101] To implement this invention, it is necessary to construct a system that combines a speech recognition function, a generative AI model, and an information processing device. A specific embodiment of this system is shown below.

[0102] First, a speech recognition system is installed in the consumer robot. For speech recognition, Google's Speech-to-Text API can be used. This speech recognition system captures voice input from the user and converts that voice into text data. The robot then accurately understands the user's questions and passes them on to the next processing step.

[0103] Next, the converted text data is sent to an information processing device. This device is set up as a high-performance computer and provides an environment for running a generative AI model. For example, the generative AI model used is OpenAI's GPT-4, which analyzes user input and generates career suggestions. This model creates optimal occupational options and career plans based on the user's characteristics, interests, skills, and other relevant information.

[0104] The generated suggestion information is then presented to the user through the robot's display and audio playback devices. Visually, a touchscreen display is used, and aurally, a built-in speaker is used. This allows the user to receive information both visually and aurally.

[0105] Furthermore, users can provide feedback on the suggested information, and this feedback is sent back to the information processing device via the speech recognition system. This feedback information is then re-evaluated by the generative AI model, and the career plan is updated as needed.

[0106] As a concrete example, if a recent graduate aspiring to be an engineer says to a robot, "I am interested in data science," a speech recognition system will convert it into text, an information processing system will analyze it, and then present a career suggestion such as, "We recommend that you study the basics of Python and machine learning."

[0107] An example of a prompt message is, "Analyze the user's career-related information obtained through speech recognition and generate an optimal career plan using a machine learning model." This prompt enables the information processing device to create suggestion information tailored to the user's needs.

[0108] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0109] Step 1:

[0110] The user speaks to the robot and provides voice input. The device is equipped with a voice recognition system that captures this voice input. The input is the user's voice, and the output is the voice data.

[0111] Step 2:

[0112] The audio data captured by the device is converted into text data through a speech recognition system. This process uses a speech recognition API to analyze the audio waveform and output text data. The input is audio data, and the output is text data.

[0113] Step 3:

[0114] The converted text data is transferred to a server and analyzed by a generative AI model on the server. Here, prompt sentences are used to generate optimal career suggestions based on the user's characteristics and interests. The input is text data, and the output is suggestion information including the analysis results.

[0115] Step 4:

[0116] The suggestion information generated by the server is sent to the terminal and presented to the user either visually on the terminal's display or as audio via an audio playback device. The input is the suggestion information from the server, and the output is either a display or audio output.

[0117] Step 5:

[0118] The user reviews the presented suggestion information and inputs their feedback into the device via voice. This feedback is also converted into text data by a voice recognition system. The input is voice feedback, and the output is the text data of that feedback.

[0119] Step 6:

[0120] The server re-evaluates the received feedback text data and updates the suggestion information if necessary. In this process, the feedback is analyzed again using the generative AI model to generate an optimized career plan. The input is the feedback text data, and the output is the updated suggestion information.

[0121] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0122] This invention incorporates an emotion engine that recognizes user emotions into a system that processes user information and proposes a career plan. The system employs a process in which the emotion engine operates during the process of user input from a terminal and processing that information on a server.

[0123] When a user enters their work history, education, skills, and areas of interest via their device, the emotion engine analyzes the user's facial expressions, tone of voice, and emotion-related keywords in the text in real time, extracting them as emotion data. The server then combines and analyzes the received user information and emotion data to propose a career plan that is suitable for the user's feelings and psychological state.

[0124] For example, if the emotion engine detects feelings of tension or anxiety when a user enters their desired job type, the server will take that into consideration and include industry information and recommended skill-building methods to provide reassurance in its suggestions. Furthermore, if feelings of enjoyment or excitement are detected during the interaction with the user, the presentation method and content of the plan will be adjusted to enhance motivation.

[0125] This system allows users to receive more personalized career plans based not only on their skills and aptitudes, but also on their emotions and psychological state, ultimately enabling them to make more satisfying choices.

[0126] The following describes the processing flow.

[0127] Step 1:

[0128] The user accesses the device and enters profile information, interests, work history, etc. Upon receiving this information, the device activates its camera and microphone to record the user's emotions and prepares to acquire emotional data.

[0129] Step 2:

[0130] The device transmits the user's facial expressions and voice, along with the input information, to the emotion engine in real time. The emotion engine uses facial recognition technology and voice analysis to identify the user's emotional state.

[0131] Step 3:

[0132] The emotion engine analyzes the user's emotions from the obtained facial expressions and voice, and generates emotion tags such as tension, joy, and anxiety. These emotion tags are sent to the server along with the user information.

[0133] Step 4:

[0134] The server receives user information and emotion tags, and uses a generation AI to analyze and generate a career plan based on the user's skills, aptitudes, and emotional state. The server adjusts the plan content considering the emotional state, for example, by incorporating suggestions that provide a sense of security or information that motivates the user.

[0135] Step 5:

[0136] The server generates a carrier plan and sends it to the device. The device then displays the suggested information to the user in an easy-to-understand format, providing visual feedback.

[0137] Step 6:

[0138] Users provide feedback by reviewing the provided career plan and entering their thoughts and requests. Upon receiving feedback, the device records emotional data again and captures the user's reaction.

[0139] Step 7:

[0140] The device sends user feedback and newly acquired sentiment data to the server. The server re-evaluates this feedback and sentiment state, adjusts the career plan as needed, and prepares to provide updated suggestion information.

[0141] (Example 2)

[0142] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0143] Conventional career plan proposal systems relied solely on user input information and failed to consider the user's emotions or psychological state. As a result, in situations where users felt anxious or stressed, appropriate suggestions were not provided, leading to a decrease in user satisfaction.

[0144] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0145] In this invention, the server includes means for analyzing the user's emotions, means for transmitting the information received from the user to a device for processing the information, and means for adjusting the presented information in consideration of the emotions. This makes it possible to propose a career plan that takes the user's emotional state into account, resulting in more personalized suggestions.

[0146] A "user" refers to an entity that inputs information into the system and receives career plan suggestions.

[0147] A "processing device" refers to a computer that receives information transmitted by a user and performs analysis on it.

[0148] "Attributes" refer to data about the user, such as work history, education, skills, and areas of interest.

[0149] "Presented information" refers to the career plans and proposals offered to users.

[0150] "Emotions" refers to data such as facial expressions, tone of voice, and keywords in the text that indicate the user's psychological state.

[0151] "Reaction" refers to the feedback or reaction a user gives to the information presented by the system.

[0152] This invention relates to a career plan suggestion system that takes into account the user's characteristics and emotions. The system achieves more personalized suggestions through a process where the user provides information via a terminal, and a server generates a career plan based on that information.

[0153] Users input information such as their work history, education, skills, and areas of interest using a device. The device is equipped with a camera and microphone, which record the user's facial expressions and voice in real time. This data is analyzed by an emotion engine within the device and extracted as emotion data using software such as Python and TENSORFLOW®.

[0154] User information and emotional data are encrypted and sent to the server. The server organizes the received data using Python's pandas library and generates a career plan tailored to the user's emotional state using scikit-learn. This allows the server to suggest the most suitable career path for the user. For example, if the server detects anxiety about a job type entered by the user, it will include reassuring information and methods for skill development related to that job in its suggestions. Conversely, if positive emotions are detected, it will add success stories and visions of the future to boost the user's motivation.

[0155] For example, if a user expresses interest in a "digital marketing" position and enters their preferences enthusiastically, the server can include visual content showcasing future career prospects in its suggestions. This allows for suggestions that resonate with the user's interests and emotions.

[0156] Examples of prompts to input into a generative AI model

[0157] "Please generate a digital marketing career plan based on user sentiment data. It should include an engaging story and suggestions for skill development."

[0158] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0159] Step 1:

[0160] Users input their work history, education, skills, and areas of interest using a terminal. This information is entered through a GUI built on the terminal. The entered data reflects the user's career goals and interests and is stored as basic data necessary for subsequent processing.

[0161] Step 2:

[0162] The device captures the user's facial expressions with a camera and records their voice with a microphone. These inputs are sent to an emotion engine and analyzed in real time using OpenCV and TensorFlow. The analysis results in data representing the user's emotional state. This emotional data reflects the user's psychological state and is used in the next stage of career plan generation.

[0163] Step 3:

[0164] The device sends input information and sentiment data to the server. The data is encrypted during transmission to maintain security. The server first organizes the received data and structures it as a dataframe using the Python pandas library. This structured data is then ready to be input into the model.

[0165] Step 4:

[0166] The server performs analysis using scikit-learn based on organized information and sentiment data. This analysis generates a career plan that takes into account the user's work history, education, and emotional state. The output here is a career plan that includes optimal job candidates and skill development suggestions for the user.

[0167] Step 5:

[0168] The server sends the generated carrier plan to the device. The device displays the proposal in a visually easy-to-understand format. The user can then refer to this plan and decide on their next course of action. The output in this process is proposal information processed in a way that is easy for the user to understand.

[0169] (Application Example 2)

[0170] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0171] Traditional career planning systems primarily offer suggestions based on the user's basic information and aptitudes, lacking personalized suggestions that take into account their emotions and psychological state. As a result, users often feel anxious or dissatisfied with the suggested career plans, making the selection process difficult.

[0172] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0173] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, means for analyzing emotional data using an emotion recognition device that recognizes the user's emotional state, and means for adjusting and presenting the suggested information based on the user's emotional state. This makes it possible to provide a personalized career plan that is tailored to the user's emotions and psychological state.

[0174] "Information received from users" refers to information such as work history, educational background, skills, and areas of interest that users enter via their devices.

[0175] An "information processing device" is a digital device that analyzes information received from a user and generates appropriate suggestions.

[0176] "Analyzing characteristics" means analyzing a user's basic data, behavior, preferences, etc., to extract individual features.

[0177] "Suggested information" refers to information about the next actions or options a user should take, generated based on the analysis results.

[0178] An "emotion recognition device" is a device that determines a user's emotional state based on their facial expressions, tone of voice, and other factors.

[0179] "Emotional data" refers to digital data about a user's emotions acquired by an emotion recognition device.

[0180] "Adjusting and presenting based on emotional state" means appropriately arranging the proposed content according to the user's emotions and communicating it to the user.

[0181] The system for implementing this invention consists of a user terminal, an information processing server, and an emotion recognition device. The user terminal has an interface for inputting information such as work history, educational background, skills, and areas of interest. This information is transferred to the server via a network.

[0182] The server first processes the information received from the user and analyzes the user's characteristics. This analysis includes, for example, referencing databases and utilizing machine learning models. Based on the analysis results, it generates appropriate suggestion information for the user. This suggestion information includes career options based on the user's interests and abilities.

[0183] In this process, the emotion recognition device analyzes the user's facial expressions and tone of voice, generating emotion data in real time. This emotion data is sent to a server and used to adjust the suggested information. The server, taking the emotional state into consideration, presents the suggested information in the most beneficial way for the user.

[0184] For example, if the server detects tension when a user enters their desired job type, it will provide relaxing music or reassuring information. Furthermore, if the user shows strong excitement or interest, it will present a career plan that further enhances those feelings.

[0185] An example of a prompt message when using a generative AI model is as follows: "User information: Work experience = 5 years, Skills = Java (registered trademark), Interests = Web development, Emotions = Stress. Based on this, please propose a detailed career plan."

[0186] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0187] Step 1:

[0188] The user enters their information from a terminal. The user operates the terminal and enters information such as their work history, education, skills, and areas of interest. This information is transferred from the terminal to the server in digital format. During this process, a simple validation check is performed to verify the accuracy of the entered information.

[0189] Step 2:

[0190] The server analyzes user characteristics. The server processes the received user information, refers to a database, and extracts user information with similar characteristics. A machine learning model is used to generate personalized suggestion information. The input is basic user information, and the output is suggested candidate information.

[0191] Step 3:

[0192] Collection of emotional data using an emotion recognition device. While the user is using the device, the camera and microphone record the user's facial expressions and voice tone. Based on this data, the emotion recognition device analyzes emotions in real time and generates emotional data. The input is the user's facial expressions and voice, and the output is emotional data.

[0193] Step 4:

[0194] The server integrates emotional data and trait analysis results. The server combines the trait analysis results with the collected emotional data to adjust the suggested information, taking into account the user's current psychological state. This enables more personalized suggestions. The output is the adjusted suggested information.

[0195] Step 5:

[0196] The server presents suggested information to the user. The refined suggested information is sent to the terminal and displayed through the user interface. The order and format of the information presentation are carefully designed to attract the user's interest. The input is the refined suggested information, and the output is the content displayed to the user.

[0197] Step 6:

[0198] Collecting and analyzing user feedback. Users can provide feedback on suggested information. This feedback is then analyzed on the server and used to improve future suggested information. The input is user feedback, and the output is the analyzed feedback results.

[0199] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating 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.

[0200] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0201] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0202] [Second Embodiment]

[0203] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0204] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0205] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0206] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0207] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0208] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0209] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0210] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0211] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0212] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0213] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0214] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. 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".

[0215] This invention provides an AI agent system that automatically proposes career plans based on information provided by the user. The system operates in a process where the user inputs information through a terminal, and that information is analyzed on a server. The server utilizes generative AI technology to generate suggestion information based on the user's skills, aptitudes, and past success stories.

[0216] The server is responsible for analyzing the user information it receives. For example, when a user enters their educational background, work history, acquired skills, and areas of interest into a terminal, the server receives this data and uses machine learning algorithms to evaluate the user's strengths and weaknesses. This allows for an objective and fair assessment of the user's suitability and identifies the most suitable career options. The server also takes into account the latest industry trend data to create a career plan that includes useful information for the user.

[0217] The generated suggestion information is sent to the terminal and displayed to the user. The user can evaluate the presented career plan and, if necessary, enter feedback into the terminal. The user's feedback is re-analyzed on the server, and the plan is updated as needed. This process helps users make the best career choices for themselves. For example, if a recent graduate aspiring to be an engineer enters their programming skills and technologies of interest into the terminal, the server analyzes this information and suggests specific job roles in the IT industry, required skills, and recommended methods for skill development.

[0218] The following describes the processing flow.

[0219] Step 1:

[0220] The user accesses the terminal and enters personal information, including data such as work history, education, skills, and areas of interest. The terminal receives the user's input and prepares the data according to the specified format.

[0221] Step 2:

[0222] The terminal sends the prepared user information to the server. The terminal uses secure communication methods during data transmission to maintain the confidentiality of user data.

[0223] Step 3:

[0224] The server stores the received user information in a database for analysis. The server then begins analyzing the data using the latest generative AI algorithms.

[0225] Step 4:

[0226] The server uses AI to evaluate the user's skills and aptitudes based on the input user data. The server also refers to a database of past success stories and the latest trends to generate the optimal career plan for the user.

[0227] Step 5:

[0228] The server generates a carrier plan and sends it to the device. The server formats the proposed information into a user-friendly format and sends it.

[0229] Step 6:

[0230] The device presents the received carrier plan to the user. The device displays plan details, recommended job roles, and additional information via the user interface.

[0231] Step 7:

[0232] Users review the presented career plan and provide feedback as needed. User feedback can include ratings, questions, and further requests.

[0233] Step 8:

[0234] The device sends user feedback to the server. The device formats the feedback data and quickly transmits it to the server.

[0235] Step 9:

[0236] The server receives the feedback and performs another analysis. The server takes the feedback into consideration, adjusts the career plan as needed, and makes new suggestions to the user.

[0237] (Example 1)

[0238] Next, we will describe Example 1. 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".

[0239] In today's increasingly diverse work environment, providing appropriate career advice based on individual interests, skills, and market trends is challenging. Traditionally, many career planning tools tend to take a uniform approach, making it difficult to provide personalized suggestions for each user.

[0240] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0241] In this invention, the server includes means for transferring information obtained from the user to an information processing device, means for analyzing the user's characteristics using a generation AI model and generating suggested information based on the results, and means for visually presenting the suggested information to the user. This enables career planning tailored to the individual needs of the user.

[0242] A "user" is an entity that uses the system to input their information and receive a career plan.

[0243] An "information processing device" is a computer system that receives and analyzes information obtained from users.

[0244] A "generative AI model" is an algorithm or software that utilizes artificial intelligence technology to analyze user characteristics and generate suggested information.

[0245] "Characteristics" refer to individual attributes of a user, such as their skills, aptitudes, and interests.

[0246] "Suggested information" refers to career options and advice generated based on the user's characteristics and market trends.

[0247] "Visual presentation" refers to displaying proposed information through a display or screen in a way that users can easily understand.

[0248] "Job options" refer to job and career choices that are deemed appropriate for the user.

[0249] "Input" refers to the feedback and additional information that users provide through the system.

[0250] This invention is a system aimed at providing users with appropriate suggestions regarding their career plans. Users first input information such as their educational background, work experience, skills, and areas of interest using a terminal. This input is done, for example, through a form on a smartphone or computer screen. The input information is then transmitted to a server via the internet.

[0251] The server acts as an information processing unit, receiving data from users. After preprocessing the received data, the server uses a generative AI model to perform data analysis. This model incorporates machine learning algorithms to analyze user characteristics and generate individually optimized career plans.

[0252] The career plan reflects the latest industry trends and suggests specific job options, such as "skills required as a data scientist" or "experience in front-end development." This suggested information is sent from the server to the user's terminal and presented visually. Users can review the suggestions on the screen and evaluate them based on their own thoughts and preferences.

[0253] Furthermore, users can input feedback on the proposed career plan from their device and send it back to the server. The server can then analyze this feedback and adjust or update the proposed plan.

[0254] As a concrete example, a prompt might say, "Please suggest suitable job roles for a recent graduate user aspiring to be an engineer." Using this prompt, the generating AI model will create specific career options that are appropriate for the user.

[0255] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0256] Step 1:

[0257] The user inputs information using a terminal. The user enters information such as educational background, work history, skills, and areas of interest into a form. This input data is then prepared by the terminal to be sent to the server. Specifically, the entered information is formatted in a digital format and converted into packets according to a communication protocol.

[0258] Step 2:

[0259] The server receives data from the terminal. The server preprocesses this received data. Specifically, it cleanses the data by imputing missing values ​​and detecting outliers. This process prepares the data for analysis. The input is the user's raw data, and the output is the processed dataset.

[0260] Step 3:

[0261] The server analyzes user data using a generated AI model. The server activates machine learning algorithms to analyze user characteristics. Specifically, it quantifies and evaluates user skills and aptitudes, and generates an appropriate career plan based on the results. The input is a pre-processed dataset, and the output is the evaluation result based on the analysis.

[0262] Step 4:

[0263] The server generates suggestion information based on the analysis results. Here, the generating AI model creates specific suggestion information that includes a career plan optimized for the user. This plan reflects job options based on the user's interests and skills, as well as industry trends. The server uses prompts to ask the AI ​​model appropriate questions and generate information. The output is visual information to be presented to the user.

[0264] Step 5:

[0265] The server sends the generated proposal information to the terminal. The terminal displays the received proposal information. The user can visually review the plan and provide evaluations and feedback. The output is in a format that the user can view.

[0266] Step 6:

[0267] Users input feedback to the server via their devices. Users provide feedback such as evaluations of the proposed career plan and requests for revisions. This feedback is then prepared to be sent back to the server as data. The input consists of user feedback information.

[0268] Step 7:

[0269] The server analyzes user feedback and updates the suggested information as needed. The server processes the feedback data and performs a re-analysis to generate a new career plan. This process enables optimization based on user feedback, ensuring that the final suggested information is better tailored to the user's needs.

[0270] (Application Example 1)

[0271] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0272] Traditionally, users have required considerable time and effort to obtain career plans based on their aptitudes. Furthermore, there is a lack of systems that utilize voice recognition to provide career suggestions through natural, two-way communication with users. Therefore, there is a need for a new information provision system that offers intuitive and immediate suggestions to users.

[0273] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0274] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, and means for presenting the suggested information to the user via a display device or audio playback device. This allows the user to intuitively obtain an optimal career plan based on their interests and abilities, and enables natural interaction through communication utilizing speech recognition.

[0275] A "user" refers to an individual who inputs information and receives career plan suggestions.

[0276] An "information processing device" refers to a computer or server that analyzes data received from a user and generates suggested information.

[0277] "Characteristics" refers to personal attributes and abilities necessary for career plan generation, such as the user's education background, work experience, skills, interests, etc.

[0278] "Proposed information" refers to information including career plans and career options optimized for the user, generated based on the results of analyzing the user's characteristics.

[0279] "Display device" refers to a screen or monitor for visually presenting the generated proposed information to the user.

[0280] "Audio playback device" refers to a speaker for aurally presenting the generated proposed information to the user.

[0281] "Speech recognition means" refers to a system or technology for converting the user's voice input into text data.

[0282] "Feedback" refers to opinions or information for improvement provided by the user regarding the proposed information.

[0283] "Interaction" refers to the exchanges and reactions occurring between the user and the system.

[0284] To implement this invention, it is necessary to construct a system that combines a speech recognition function, a generative AI model, and an information processing device. The specific embodiments are shown below.

[0285] First, install a speech recognition system in a consumer robot. For speech recognition, Google Speech-to-Text API or the like can be used. This speech recognition system captures the user's voice input and converts the voice into text data. It plays the role of enabling the robot to accurately understand the user's query and pass it on to the next process.

[0286] Next, the converted text data is sent to the information processing device. This information processing device is installed as a high-performance computer and provides an environment for running the generation AI model. For example, OpenAI's GPT-4 is used as the generation AI model to analyze user input and generate career suggestions. This model creates optimal career options and career plans based on the user's characteristics, interests, skills, and other relevant information.

[0287] After that, the generated proposal information is presented to the user through the display device and audio playback device of the robot. A touch screen display is used visually, and a built-in speaker is used auditorily. This enables the user to receive information both visually and auditorily.

[0288] Furthermore, the user can provide feedback on the proposal information, and this feedback is sent to the information processing device through the speech recognition system again. This feedback information is re-evaluated by the generation AI model, and the career plan is updated as needed.

[0289] As a specific example, when a fresh graduate engineer aspirant talks to the robot saying "I'm interested in data science", the speech recognition system converts it into text, the information processing device analyzes it, and presents a career suggestion such as "It is recommended that you have a foundation in Python and machine learning".

[0290] As an example of the prompt text, there is "Analyze the user's career-related information obtained by speech recognition and generate an optimal career plan using a machine learning model". This prompt enables the information processing device to create proposal information that meets the user's needs.

[0291] The flow of the specific process in Application Example 1 will be described using FIG. 12.

[0292] Step 1:

[0293] The user speaks to the robot and provides voice input. The device is equipped with a voice recognition system that captures this voice input. The input is the user's voice, and the output is the voice data.

[0294] Step 2:

[0295] The audio data captured by the device is converted into text data through a speech recognition system. This process uses a speech recognition API to analyze the audio waveform and output text data. The input is audio data, and the output is text data.

[0296] Step 3:

[0297] The converted text data is transferred to a server and analyzed by a generative AI model on the server. Here, prompt sentences are used to generate optimal career suggestions based on the user's characteristics and interests. The input is text data, and the output is suggestion information including the analysis results.

[0298] Step 4:

[0299] The suggestion information generated by the server is sent to the terminal and presented to the user either visually on the terminal's display or as audio via an audio playback device. The input is the suggestion information from the server, and the output is either a display or audio output.

[0300] Step 5:

[0301] The user reviews the presented suggestion information and inputs their feedback into the device via voice. This feedback is also converted into text data by a voice recognition system. The input is voice feedback, and the output is the text data of that feedback.

[0302] Step 6:

[0303] The server re-evaluates the received feedback text data and updates the proposed information if necessary. In this process, the regenerated AI model is used to analyze the feedback and generate an optimized career plan. The input is the feedback text data, and the output is the updated proposed information.

[0304] Furthermore, an emotion engine for estimating the user's emotion may be combined. That is, the specific processing unit 290 may estimate the user's emotion using the emotion recognition model 59 and perform specific processing using the user's emotion.

[0305] The present invention incorporates an emotion engine for recognizing the user's emotion into a system that processes user information and proposes a career plan. In the implementation of this system, a process is adopted in which the user inputs information from a terminal and the emotion engine operates in the process where the information is processed by the server.

[0306] When the user inputs work history, educational background, skills, and areas of interest via the terminal, the emotion engine analyzes in real time the user's facial expression, voice tone, keywords related to the emotion in the text, etc., and extracts them as emotion data. The server combines and analyzes the received user information and emotion data and proposes a career plan suitable for the user's mood and mental state.

[0307] For example, when emotions such as tension or anxiety are recognized by the emotion engine when the user inputs the desired occupation, the server takes that situation into consideration and includes in the proposal industry information and recommended skill improvement means that give a sense of security. Also, when emotions such as fun or excitement are recognized during the interaction with the user, the presentation method and content of the plan are arranged and adjusted to enhance motivation.

[0308] This system allows users to receive more personalized career plans based not only on their skills and aptitudes, but also on their emotions and psychological state, ultimately enabling them to make more satisfying choices.

[0309] The following describes the processing flow.

[0310] Step 1:

[0311] The user accesses the device and enters profile information, interests, work history, etc. Upon receiving this information, the device activates its camera and microphone to record the user's emotions and prepares to acquire emotional data.

[0312] Step 2:

[0313] The device transmits the user's facial expressions and voice, along with the input information, to the emotion engine in real time. The emotion engine uses facial recognition technology and voice analysis to identify the user's emotional state.

[0314] Step 3:

[0315] The emotion engine analyzes the user's emotions from the obtained facial expressions and voice, and generates emotion tags such as tension, joy, and anxiety. These emotion tags are sent to the server along with the user information.

[0316] Step 4:

[0317] The server receives user information and emotion tags, and uses a generation AI to analyze and generate a career plan based on the user's skills, aptitudes, and emotional state. The server adjusts the plan content considering the emotional state, for example, by incorporating suggestions that provide a sense of security or information that motivates the user.

[0318] Step 5:

[0319] The server generates a carrier plan and sends it to the device. The device then displays the suggested information to the user in an easy-to-understand format, providing visual feedback.

[0320] Step 6:

[0321] Users provide feedback by reviewing the provided career plan and entering their thoughts and requests. Upon receiving feedback, the device records emotional data again and captures the user's reaction.

[0322] Step 7:

[0323] The device sends user feedback and newly acquired sentiment data to the server. The server re-evaluates this feedback and sentiment state, adjusts the career plan as needed, and prepares to provide updated suggestion information.

[0324] (Example 2)

[0325] Next, we will describe Example 2. 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".

[0326] Conventional career plan proposal systems relied solely on user input information and failed to consider the user's emotions or psychological state. As a result, in situations where users felt anxious or stressed, appropriate suggestions were not provided, leading to a decrease in user satisfaction.

[0327] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0328] In this invention, the server includes means for analyzing the user's emotions, means for transmitting the information received from the user to a device for processing the information, and means for adjusting the presented information in consideration of the emotions. This makes it possible to propose a career plan that takes the user's emotional state into account, resulting in more personalized suggestions.

[0329] A "user" refers to an entity that inputs information into the system and receives career plan suggestions.

[0330] A "processing device" refers to a computer that receives information transmitted by a user and performs analysis on it.

[0331] "Attributes" refer to data about the user, such as work history, education, skills, and areas of interest.

[0332] "Presented information" refers to the career plans and proposals offered to users.

[0333] "Emotions" refers to data such as facial expressions, tone of voice, and keywords in the text that indicate the user's psychological state.

[0334] "Reaction" refers to the feedback or reaction a user gives to the information presented by the system.

[0335] This invention relates to a career plan suggestion system that takes into account the user's characteristics and emotions. The system achieves more personalized suggestions through a process where the user provides information via a terminal, and a server generates a career plan based on that information.

[0336] Users input information such as their work history, education, skills, and areas of interest using a device. The device is equipped with a camera and microphone, which record the user's facial expressions and voice in real time. This data is analyzed by an emotion engine within the device and extracted as emotion data using software such as Python and TensorFlow.

[0337] User information and emotional data are encrypted and sent to the server. The server organizes the received data using Python's pandas library and generates a career plan tailored to the user's emotional state using scikit-learn. This allows the server to suggest the most suitable career path for the user. For example, if the server detects anxiety about a job type entered by the user, it will include reassuring information and methods for skill development related to that job in its suggestions. Conversely, if positive emotions are detected, it will add success stories and visions of the future to boost the user's motivation.

[0338] For example, if a user expresses interest in a "digital marketing" position and enters their preferences enthusiastically, the server can include visual content showcasing future career prospects in its suggestions. This allows for suggestions that resonate with the user's interests and emotions.

[0339] Examples of prompts to input into a generative AI model

[0340] "Please generate a digital marketing career plan based on user sentiment data. It should include an engaging story and suggestions for skill development."

[0341] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0342] Step 1:

[0343] Users input their work history, education, skills, and areas of interest using a terminal. This information is entered through a GUI built on the terminal. The entered data reflects the user's career goals and interests and is stored as basic data necessary for subsequent processing.

[0344] Step 2:

[0345] The device captures the user's facial expressions with a camera and records their voice with a microphone. These inputs are sent to an emotion engine and analyzed in real time using OpenCV and TensorFlow. The analysis results in data representing the user's emotional state. This emotional data reflects the user's psychological state and is used in the next stage of career plan generation.

[0346] Step 3:

[0347] The device sends input information and sentiment data to the server. The data is encrypted during transmission to maintain security. The server first organizes the received data and structures it as a dataframe using the Python pandas library. This structured data is then ready to be input into the model.

[0348] Step 4:

[0349] The server performs analysis using scikit-learn based on organized information and sentiment data. This analysis generates a career plan that takes into account the user's work history, education, and emotional state. The output here is a career plan that includes optimal job candidates and skill development suggestions for the user.

[0350] Step 5:

[0351] The server sends the generated carrier plan to the device. The device displays the proposal in a visually easy-to-understand format. The user can then refer to this plan and decide on their next course of action. The output in this process is proposal information processed in a way that is easy for the user to understand.

[0352] (Application Example 2)

[0353] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0354] Traditional career planning systems primarily offer suggestions based on the user's basic information and aptitudes, lacking personalized suggestions that take into account their emotions and psychological state. As a result, users often feel anxious or dissatisfied with the suggested career plans, making the selection process difficult.

[0355] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0356] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, means for analyzing emotional data using an emotion recognition device that recognizes the user's emotional state, and means for adjusting and presenting the suggested information based on the user's emotional state. This makes it possible to provide a personalized career plan that is tailored to the user's emotions and psychological state.

[0357] "Information received from users" refers to information such as work history, educational background, skills, and areas of interest that users enter via their devices.

[0358] An "information processing device" is a digital device that analyzes information received from a user and generates appropriate suggestions.

[0359] "Analyzing characteristics" means analyzing a user's basic data, behavior, preferences, etc., to extract individual features.

[0360] "Suggested information" refers to information about the next actions or options a user should take, generated based on the analysis results.

[0361] An "emotion recognition device" is a device that determines a user's emotional state based on their facial expressions, tone of voice, and other factors.

[0362] "Emotional data" refers to digital data about a user's emotions acquired by an emotion recognition device.

[0363] "Adjusting and presenting based on emotional state" means appropriately arranging the proposed content according to the user's emotions and communicating it to the user.

[0364] The system for implementing this invention consists of a user terminal, an information processing server, and an emotion recognition device. The user terminal has an interface for inputting information such as work history, educational background, skills, and areas of interest. This information is transferred to the server via a network.

[0365] The server first processes the information received from the user and analyzes the user's characteristics. This analysis includes, for example, referencing databases and utilizing machine learning models. Based on the analysis results, it generates appropriate suggestion information for the user. This suggestion information includes career options based on the user's interests and abilities.

[0366] In this process, the emotion recognition device analyzes the user's facial expressions and tone of voice, generating emotion data in real time. This emotion data is sent to a server and used to adjust the suggested information. The server, taking the emotional state into consideration, presents the suggested information in the most beneficial way for the user.

[0367] For example, if the server detects tension when a user enters their desired job type, it will provide relaxing music or reassuring information. Furthermore, if the user shows strong excitement or interest, it will present a career plan that further enhances those feelings.

[0368] An example of a prompt message when using a generative AI model is as follows: "User information: Work experience = 5 years, Skills = Java, Interests = Web development, Emotions = Stress. Based on this, please propose a detailed career plan."

[0369] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0370] Step 1:

[0371] The user enters their information from a terminal. The user operates the terminal and enters information such as their work history, education, skills, and areas of interest. This information is transferred from the terminal to the server in digital format. During this process, a simple validation check is performed to verify the accuracy of the entered information.

[0372] Step 2:

[0373] The server analyzes user characteristics. The server processes the received user information, refers to a database, and extracts user information with similar characteristics. A machine learning model is used to generate personalized suggestion information. The input is basic user information, and the output is suggested candidate information.

[0374] Step 3:

[0375] Collection of emotional data using an emotion recognition device. While the user is using the device, the camera and microphone record the user's facial expressions and voice tone. Based on this data, the emotion recognition device analyzes emotions in real time and generates emotional data. The input is the user's facial expressions and voice, and the output is emotional data.

[0376] Step 4:

[0377] The server integrates emotional data and trait analysis results. The server combines the trait analysis results with the collected emotional data to adjust the suggested information, taking into account the user's current psychological state. This enables more personalized suggestions. The output is the adjusted suggested information.

[0378] Step 5:

[0379] The server presents suggested information to the user. The refined suggested information is sent to the terminal and displayed through the user interface. The order and format of the information presentation are carefully designed to attract the user's interest. The input is the refined suggested information, and the output is the content displayed to the user.

[0380] Step 6:

[0381] Collecting and analyzing user feedback. Users can provide feedback on suggested information. This feedback is then analyzed on the server and used to improve future suggested information. The input is user feedback, and the output is the analyzed feedback results.

[0382] 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 user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0383] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0384] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0385] [Third Embodiment]

[0386] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0387] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0388] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0389] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0390] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0391] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0392] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0393] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0394] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0395] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0396] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0397] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0398] This invention provides an AI agent system that automatically proposes career plans based on information provided by the user. The system operates in a process where the user inputs information through a terminal, and that information is analyzed on a server. The server utilizes generative AI technology to generate suggestion information based on the user's skills, aptitudes, and past success stories.

[0399] The server is responsible for analyzing the user information it receives. For example, when a user enters their educational background, work history, acquired skills, and areas of interest into a terminal, the server receives this data and uses machine learning algorithms to evaluate the user's strengths and weaknesses. This allows for an objective and fair assessment of the user's suitability and identifies the most suitable career options. The server also takes into account the latest industry trend data to create a career plan that includes useful information for the user.

[0400] The generated suggestion information is sent to the terminal and displayed to the user. The user can evaluate the presented career plan and, if necessary, enter feedback into the terminal. The user's feedback is re-analyzed on the server, and the plan is updated as needed. This process helps users make the best career choices for themselves. For example, if a recent graduate aspiring to be an engineer enters their programming skills and technologies of interest into the terminal, the server analyzes this information and suggests specific job roles in the IT industry, required skills, and recommended methods for skill development.

[0401] The following describes the processing flow.

[0402] Step 1:

[0403] The user accesses the terminal and enters personal information, including data such as work history, education, skills, and areas of interest. The terminal receives the user's input and prepares the data according to the specified format.

[0404] Step 2:

[0405] The terminal sends the prepared user information to the server. The terminal uses secure communication methods during data transmission to maintain the confidentiality of user data.

[0406] Step 3:

[0407] The server stores the received user information in a database for analysis. The server then begins analyzing the data using the latest generative AI algorithms.

[0408] Step 4:

[0409] The server uses AI to evaluate the user's skills and aptitudes based on the input user data. The server also refers to a database of past success stories and the latest trends to generate the optimal career plan for the user.

[0410] Step 5:

[0411] The server generates a carrier plan and sends it to the device. The server formats the proposed information into a user-friendly format and sends it.

[0412] Step 6:

[0413] The device presents the received carrier plan to the user. The device displays plan details, recommended job roles, and additional information via the user interface.

[0414] Step 7:

[0415] Users review the presented career plan and provide feedback as needed. User feedback can include ratings, questions, and further requests.

[0416] Step 8:

[0417] The device sends user feedback to the server. The device formats the feedback data and quickly transmits it to the server.

[0418] Step 9:

[0419] The server receives the feedback and performs another analysis. The server takes the feedback into consideration, adjusts the career plan as needed, and makes new suggestions to the user.

[0420] (Example 1)

[0421] Next, we will describe Example 1. 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."

[0422] In today's increasingly diverse work environment, providing appropriate career advice based on individual interests, skills, and market trends is challenging. Traditionally, many career planning tools tend to take a uniform approach, making it difficult to provide personalized suggestions for each user.

[0423] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0424] In this invention, the server includes means for transferring information obtained from the user to an information processing device, means for analyzing the user's characteristics using a generation AI model and generating suggested information based on the results, and means for visually presenting the suggested information to the user. This enables career planning tailored to the individual needs of the user.

[0425] A "user" is an entity that uses the system to input their information and receive a career plan.

[0426] An "information processing device" is a computer system that receives and analyzes information obtained from users.

[0427] A "generative AI model" is an algorithm or software that utilizes artificial intelligence technology to analyze user characteristics and generate suggested information.

[0428] "Characteristics" refer to individual attributes of a user, such as their skills, aptitudes, and interests.

[0429] "Suggested information" refers to career options and advice generated based on the user's characteristics and market trends.

[0430] "Visual presentation" refers to displaying proposed information through a display or screen in a way that users can easily understand.

[0431] "Job options" refer to job and career choices that are deemed appropriate for the user.

[0432] "Input" refers to the feedback and additional information that users provide through the system.

[0433] This invention is a system aimed at providing users with appropriate suggestions regarding their career plans. Users first input information such as their educational background, work experience, skills, and areas of interest using a terminal. This input is done, for example, through a form on a smartphone or computer screen. The input information is then transmitted to a server via the internet.

[0434] The server acts as an information processing unit, receiving data from users. After preprocessing the received data, the server uses a generative AI model to perform data analysis. This model incorporates machine learning algorithms to analyze user characteristics and generate individually optimized career plans.

[0435] The career plan reflects the latest industry trends and suggests specific job options, such as "skills required as a data scientist" or "experience in front-end development." This suggested information is sent from the server to the user's terminal and presented visually. Users can review the suggestions on the screen and evaluate them based on their own thoughts and preferences.

[0436] Furthermore, users can input feedback on the proposed career plan from their device and send it back to the server. The server can then analyze this feedback and adjust or update the proposed plan.

[0437] As a concrete example, a prompt might say, "Please suggest suitable job roles for a recent graduate user aspiring to be an engineer." Using this prompt, the generating AI model will create specific career options that are appropriate for the user.

[0438] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0439] Step 1:

[0440] The user inputs information using a terminal. The user enters information such as educational background, work history, skills, and areas of interest into a form. This input data is then prepared by the terminal to be sent to the server. Specifically, the entered information is formatted in a digital format and converted into packets according to a communication protocol.

[0441] Step 2:

[0442] The server receives data from the terminal. The server preprocesses this received data. Specifically, it cleanses the data by imputing missing values ​​and detecting outliers. This process prepares the data for analysis. The input is the user's raw data, and the output is the processed dataset.

[0443] Step 3:

[0444] The server analyzes user data using a generated AI model. The server activates machine learning algorithms to analyze user characteristics. Specifically, it quantifies and evaluates user skills and aptitudes, and generates an appropriate career plan based on the results. The input is a pre-processed dataset, and the output is the evaluation result based on the analysis.

[0445] Step 4:

[0446] The server generates suggestion information based on the analysis results. Here, the generating AI model creates specific suggestion information that includes a career plan optimized for the user. This plan reflects job options based on the user's interests and skills, as well as industry trends. The server uses prompts to ask the AI ​​model appropriate questions and generate information. The output is visual information to be presented to the user.

[0447] Step 5:

[0448] The server sends the generated proposal information to the terminal. The terminal displays the received proposal information. The user can visually review the plan and provide evaluations and feedback. The output is in a format that the user can view.

[0449] Step 6:

[0450] Users input feedback to the server via their devices. Users provide feedback such as evaluations of the proposed career plan and requests for revisions. This feedback is then prepared to be sent back to the server as data. The input consists of user feedback information.

[0451] Step 7:

[0452] The server analyzes user feedback and updates the suggested information as needed. The server processes the feedback data and performs a re-analysis to generate a new career plan. This process enables optimization based on user feedback, ensuring that the final suggested information is better tailored to the user's needs.

[0453] (Application Example 1)

[0454] Next, we will explain Application Example 1. In the following explanation, 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."

[0455] Traditionally, users have required considerable time and effort to obtain career plans based on their aptitudes. Furthermore, there is a lack of systems that utilize voice recognition to provide career suggestions through natural, two-way communication with users. Therefore, there is a need for a new information provision system that offers intuitive and immediate suggestions to users.

[0456] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0457] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, and means for presenting the suggested information to the user via a display device or audio playback device. This allows the user to intuitively obtain an optimal career plan based on their interests and abilities, and enables natural interaction through communication utilizing speech recognition.

[0458] A "user" refers to an individual who inputs information and receives career plan suggestions.

[0459] An "information processing device" refers to a computer or server that analyzes data received from a user and generates suggested information.

[0460] "Characteristics" refers to the individual attributes and abilities necessary for generating a career plan, such as the user's educational background, work history, skills, and interests.

[0461] "Suggested information" refers to information that includes optimal career plans and occupational options for the user, generated based on the results of an analysis of the user's characteristics.

[0462] A "display device" refers to a screen or monitor used to visually present generated suggestion information to the user.

[0463] A "sound playback device" refers to a speaker used to present generated suggestion information to the user audibly.

[0464] "Voice recognition means" refers to a system or technology for converting a user's voice input into text data.

[0465] "Feedback" refers to the opinions and suggestions for improvement that users provide regarding proposed information.

[0466] "Interaction" refers to the exchanges and responses that occur between the user and the system.

[0467] To implement this invention, it is necessary to construct a system that combines a speech recognition function, a generative AI model, and an information processing device. A specific embodiment of this system is shown below.

[0468] First, a speech recognition system is installed in the consumer robot. APIs such as the Google Speech-to-Text API can be used for speech recognition. This speech recognition system captures voice input from the user and converts that audio into text data. The robot's role is to accurately understand the user's questions and pass them on to the next processing step.

[0469] Next, the converted text data is sent to an information processing device. This device is set up as a high-performance computer and provides an environment for running a generative AI model. For example, the generative AI model uses OpenAI's GPT-4 to analyze user input and generate career suggestions. This model creates optimal job options and career plans based on the user's characteristics, interests, skills, and other relevant information.

[0470] The generated suggestion information is then presented to the user through the robot's display and audio playback devices. Visually, a touchscreen display is used, and aurally, a built-in speaker is used. This allows the user to receive information both visually and aurally.

[0471] Furthermore, users can provide feedback on the suggested information, and this feedback is sent back to the information processing device via the speech recognition system. This feedback information is then re-evaluated by the generative AI model, and the career plan is updated as needed.

[0472] As a concrete example, if a recent graduate aspiring to be an engineer says to a robot, "I am interested in data science," a speech recognition system will convert it into text, an information processing system will analyze it, and then present a career suggestion such as, "We recommend that you study the basics of Python and machine learning."

[0473] An example of a prompt message is, "Analyze the user's career-related information obtained through speech recognition and generate an optimal career plan using a machine learning model." This prompt enables the information processing device to create suggestion information tailored to the user's needs.

[0474] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0475] Step 1:

[0476] The user speaks to the robot and provides voice input. The device is equipped with a voice recognition system that captures this voice input. The input is the user's voice, and the output is the voice data.

[0477] Step 2:

[0478] The audio data captured by the device is converted into text data through a speech recognition system. This process uses a speech recognition API to analyze the audio waveform and output text data. The input is audio data, and the output is text data.

[0479] Step 3:

[0480] The converted text data is transferred to a server and analyzed by a generative AI model on the server. Here, prompt sentences are used to generate optimal career suggestions based on the user's characteristics and interests. The input is text data, and the output is suggestion information including the analysis results.

[0481] Step 4:

[0482] The suggestion information generated by the server is sent to the terminal and presented to the user either visually on the terminal's display or as audio via an audio playback device. The input is the suggestion information from the server, and the output is either a display or audio output.

[0483] Step 5:

[0484] The user reviews the presented suggestion information and inputs their feedback into the device via voice. This feedback is also converted into text data by a voice recognition system. The input is voice feedback, and the output is the text data of that feedback.

[0485] Step 6:

[0486] The server re-evaluates the received feedback text data and updates the suggestion information if necessary. In this process, the feedback is analyzed again using the generative AI model to generate an optimized career plan. The input is the feedback text data, and the output is the updated suggestion information.

[0487] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0488] This invention incorporates an emotion engine that recognizes user emotions into a system that processes user information and proposes a career plan. The system employs a process in which the emotion engine operates during the process of user input from a terminal and processing that information on a server.

[0489] When a user enters their work history, education, skills, and areas of interest via their device, the emotion engine analyzes the user's facial expressions, tone of voice, and emotion-related keywords in the text in real time, extracting them as emotion data. The server then combines and analyzes the received user information and emotion data to propose a career plan that is suitable for the user's feelings and psychological state.

[0490] For example, if the emotion engine detects feelings of tension or anxiety when a user enters their desired job type, the server will take that into consideration and include industry information and recommended skill-building methods to provide reassurance in its suggestions. Furthermore, if feelings of enjoyment or excitement are detected during the interaction with the user, the presentation method and content of the plan will be adjusted to enhance motivation.

[0491] This system allows users to receive more personalized career plans based not only on their skills and aptitudes, but also on their emotions and psychological state, ultimately enabling them to make more satisfying choices.

[0492] The following describes the processing flow.

[0493] Step 1:

[0494] The user accesses the device and enters profile information, interests, work history, etc. Upon receiving this information, the device activates its camera and microphone to record the user's emotions and prepares to acquire emotional data.

[0495] Step 2:

[0496] The device transmits the user's facial expressions and voice, along with the input information, to the emotion engine in real time. The emotion engine uses facial recognition technology and voice analysis to identify the user's emotional state.

[0497] Step 3:

[0498] The emotion engine analyzes the user's emotions from the obtained facial expressions and voice, and generates emotion tags such as tension, joy, and anxiety. These emotion tags are sent to the server along with the user information.

[0499] Step 4:

[0500] The server receives user information and emotion tags, and uses a generation AI to analyze and generate a career plan based on the user's skills, aptitudes, and emotional state. The server adjusts the plan content considering the emotional state, for example, by incorporating suggestions that provide a sense of security or information that motivates the user.

[0501] Step 5:

[0502] The server generates a carrier plan and sends it to the device. The device then displays the suggested information to the user in an easy-to-understand format, providing visual feedback.

[0503] Step 6:

[0504] Users provide feedback by reviewing the provided career plan and entering their thoughts and requests. Upon receiving feedback, the device records emotional data again and captures the user's reaction.

[0505] Step 7:

[0506] The device sends user feedback and newly acquired sentiment data to the server. The server re-evaluates this feedback and sentiment state, adjusts the career plan as needed, and prepares to provide updated suggestion information.

[0507] (Example 2)

[0508] Next, we will describe Example 2. 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."

[0509] Conventional career plan proposal systems relied solely on user input information and failed to consider the user's emotions or psychological state. As a result, in situations where users felt anxious or stressed, appropriate suggestions were not provided, leading to a decrease in user satisfaction.

[0510] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0511] In this invention, the server includes means for analyzing the user's emotions, means for transmitting the information received from the user to a device for processing the information, and means for adjusting the presented information in consideration of the emotions. This makes it possible to propose a career plan that takes the user's emotional state into account, resulting in more personalized suggestions.

[0512] A "user" refers to an entity that inputs information into the system and receives career plan suggestions.

[0513] A "processing device" refers to a computer that receives information transmitted by a user and performs analysis on it.

[0514] "Attributes" refer to data about the user, such as work history, education, skills, and areas of interest.

[0515] "Presented information" refers to the career plans and proposals offered to users.

[0516] "Emotions" refers to data such as facial expressions, tone of voice, and keywords in the text that indicate the user's psychological state.

[0517] "Reaction" refers to the feedback or reaction a user gives to the information presented by the system.

[0518] This invention relates to a career plan suggestion system that takes into account the user's characteristics and emotions. The system achieves more personalized suggestions through a process where the user provides information via a terminal, and a server generates a career plan based on that information.

[0519] Users input information such as their work history, education, skills, and areas of interest using a device. The device is equipped with a camera and microphone, which record the user's facial expressions and voice in real time. This data is analyzed by an emotion engine within the device and extracted as emotion data using software such as Python and TensorFlow.

[0520] User information and emotional data are encrypted and sent to the server. The server organizes the received data using Python's pandas library and generates a career plan tailored to the user's emotional state using scikit-learn. This allows the server to suggest the most suitable career path for the user. For example, if the server detects anxiety about a job type entered by the user, it will include reassuring information and methods for skill development related to that job in its suggestions. Conversely, if positive emotions are detected, it will add success stories and visions of the future to boost the user's motivation.

[0521] For example, if a user expresses interest in a "digital marketing" position and enters their preferences enthusiastically, the server can include visual content showcasing future career prospects in its suggestions. This allows for suggestions that resonate with the user's interests and emotions.

[0522] Examples of prompts to input into a generative AI model

[0523] "Please generate a digital marketing career plan based on user sentiment data. It should include an engaging story and suggestions for skill development."

[0524] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0525] Step 1:

[0526] Users input their work history, education, skills, and areas of interest using a terminal. This information is entered through a GUI built on the terminal. The entered data reflects the user's career goals and interests and is stored as basic data necessary for subsequent processing.

[0527] Step 2:

[0528] The device captures the user's facial expressions with a camera and records their voice with a microphone. These inputs are sent to an emotion engine and analyzed in real time using OpenCV and TensorFlow. The analysis results in data representing the user's emotional state. This emotional data reflects the user's psychological state and is used in the next stage of career plan generation.

[0529] Step 3:

[0530] The device sends input information and sentiment data to the server. The data is encrypted during transmission to maintain security. The server first organizes the received data and structures it as a dataframe using the Python pandas library. This structured data is then ready to be input into the model.

[0531] Step 4:

[0532] The server performs analysis using scikit-learn based on organized information and sentiment data. This analysis generates a career plan that takes into account the user's work history, education, and emotional state. The output here is a career plan that includes optimal job candidates and skill development suggestions for the user.

[0533] Step 5:

[0534] The server sends the generated carrier plan to the device. The device displays the proposal in a visually easy-to-understand format. The user can then refer to this plan and decide on their next course of action. The output in this process is proposal information processed in a way that is easy for the user to understand.

[0535] (Application Example 2)

[0536] Next, we will explain application example 2. In the following explanation, 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."

[0537] Traditional career planning systems primarily offer suggestions based on the user's basic information and aptitudes, lacking personalized suggestions that take into account their emotions and psychological state. As a result, users often feel anxious or dissatisfied with the suggested career plans, making the selection process difficult.

[0538] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0539] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, means for analyzing emotional data using an emotion recognition device that recognizes the user's emotional state, and means for adjusting and presenting the suggested information based on the user's emotional state. This makes it possible to provide a personalized career plan that is tailored to the user's emotions and psychological state.

[0540] "Information received from users" refers to information such as work history, educational background, skills, and areas of interest that users enter via their devices.

[0541] An "information processing device" is a digital device that analyzes information received from a user and generates appropriate suggestions.

[0542] "Analyzing characteristics" means analyzing a user's basic data, behavior, preferences, etc., to extract individual features.

[0543] "Suggested information" refers to information about the next actions or options a user should take, generated based on the analysis results.

[0544] An "emotion recognition device" is a device that determines a user's emotional state based on their facial expressions, tone of voice, and other factors.

[0545] "Emotional data" refers to digital data about a user's emotions acquired by an emotion recognition device.

[0546] "Adjusting and presenting based on emotional state" means appropriately arranging the proposed content according to the user's emotions and communicating it to the user.

[0547] The system for implementing this invention consists of a user terminal, an information processing server, and an emotion recognition device. The user terminal has an interface for inputting information such as work history, educational background, skills, and areas of interest. This information is transferred to the server via a network.

[0548] The server first processes the information received from the user and analyzes the user's characteristics. This analysis includes, for example, referencing databases and utilizing machine learning models. Based on the analysis results, it generates appropriate suggestion information for the user. This suggestion information includes career options based on the user's interests and abilities.

[0549] In this process, the emotion recognition device analyzes the user's facial expressions and tone of voice, generating emotion data in real time. This emotion data is sent to a server and used to adjust the suggested information. The server, taking the emotional state into consideration, presents the suggested information in the most beneficial way for the user.

[0550] For example, if the server detects tension when a user enters their desired job type, it will provide relaxing music or reassuring information. Furthermore, if the user shows strong excitement or interest, it will present a career plan that further enhances those feelings.

[0551] An example of a prompt message when using a generative AI model is as follows: "User information: Work experience = 5 years, Skills = Java, Interests = Web development, Emotions = Stress. Based on this, please propose a detailed career plan."

[0552] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0553] Step 1:

[0554] The user enters their information from a terminal. The user operates the terminal and enters information such as their work history, education, skills, and areas of interest. This information is transferred from the terminal to the server in digital format. During this process, a simple validation check is performed to verify the accuracy of the entered information.

[0555] Step 2:

[0556] The server analyzes user characteristics. The server processes the received user information, refers to a database, and extracts user information with similar characteristics. A machine learning model is used to generate personalized suggestion information. The input is basic user information, and the output is suggested candidate information.

[0557] Step 3:

[0558] Collection of emotional data using an emotion recognition device. While the user is using the device, the camera and microphone record the user's facial expressions and voice tone. Based on this data, the emotion recognition device analyzes emotions in real time and generates emotional data. The input is the user's facial expressions and voice, and the output is emotional data.

[0559] Step 4:

[0560] The server integrates emotional data and trait analysis results. The server combines the trait analysis results with the collected emotional data to adjust the suggested information, taking into account the user's current psychological state. This enables more personalized suggestions. The output is the adjusted suggested information.

[0561] Step 5:

[0562] The server presents suggested information to the user. The refined suggested information is sent to the terminal and displayed through the user interface. The order and format of the information presentation are carefully designed to attract the user's interest. The input is the refined suggested information, and the output is the content displayed to the user.

[0563] Step 6:

[0564] Collecting and analyzing user feedback. Users can provide feedback on suggested information. This feedback is then analyzed on the server and used to improve future suggested information. The input is user feedback, and the output is the analyzed feedback results.

[0565] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0566] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0567] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0568] [Fourth Embodiment]

[0569] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0570] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0571] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0572] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0573] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0574] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0575] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0576] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0577] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0578] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0579] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0580] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0581] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0582] This invention provides an AI agent system that automatically proposes career plans based on information provided by the user. The system operates in a process where the user inputs information through a terminal, and that information is analyzed on a server. The server utilizes generative AI technology to generate suggestion information based on the user's skills, aptitudes, and past success stories.

[0583] The server is responsible for analyzing the user information it receives. For example, when a user enters their educational background, work history, acquired skills, and areas of interest into a terminal, the server receives this data and uses machine learning algorithms to evaluate the user's strengths and weaknesses. This allows for an objective and fair assessment of the user's suitability and identifies the most suitable career options. The server also takes into account the latest industry trend data to create a career plan that includes useful information for the user.

[0584] The generated suggestion information is sent to the terminal and displayed to the user. The user can evaluate the presented career plan and, if necessary, enter feedback into the terminal. The user's feedback is re-analyzed on the server, and the plan is updated as needed. This process helps users make the best career choices for themselves. For example, if a recent graduate aspiring to be an engineer enters their programming skills and technologies of interest into the terminal, the server analyzes this information and suggests specific job roles in the IT industry, required skills, and recommended methods for skill development.

[0585] The following describes the processing flow.

[0586] Step 1:

[0587] The user accesses the terminal and enters personal information, including data such as work history, education, skills, and areas of interest. The terminal receives the user's input and prepares the data according to the specified format.

[0588] Step 2:

[0589] The terminal sends the prepared user information to the server. The terminal uses secure communication methods during data transmission to maintain the confidentiality of user data.

[0590] Step 3:

[0591] The server stores the received user information in a database for analysis. The server then begins analyzing the data using the latest generative AI algorithms.

[0592] Step 4:

[0593] The server uses AI to evaluate the user's skills and aptitudes based on the input user data. The server also refers to a database of past success stories and the latest trends to generate the optimal career plan for the user.

[0594] Step 5:

[0595] The server generates a carrier plan and sends it to the device. The server formats the proposed information into a user-friendly format and sends it.

[0596] Step 6:

[0597] The device presents the received carrier plan to the user. The device displays plan details, recommended job roles, and additional information via the user interface.

[0598] Step 7:

[0599] Users review the presented career plan and provide feedback as needed. User feedback can include ratings, questions, and further requests.

[0600] Step 8:

[0601] The device sends user feedback to the server. The device formats the feedback data and quickly transmits it to the server.

[0602] Step 9:

[0603] The server receives the feedback and performs another analysis. The server takes the feedback into consideration, adjusts the career plan as needed, and makes new suggestions to the user.

[0604] (Example 1)

[0605] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0606] In today's increasingly diverse work environment, providing appropriate career advice based on individual interests, skills, and market trends is challenging. Traditionally, many career planning tools tend to take a uniform approach, making it difficult to provide personalized suggestions for each user.

[0607] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0608] In this invention, the server includes means for transferring information obtained from the user to an information processing device, means for analyzing the user's characteristics using a generation AI model and generating suggested information based on the results, and means for visually presenting the suggested information to the user. This enables career planning tailored to the individual needs of the user.

[0609] A "user" is an entity that uses the system to input their information and receive a career plan.

[0610] An "information processing device" is a computer system that receives and analyzes information obtained from users.

[0611] A "generative AI model" is an algorithm or software that utilizes artificial intelligence technology to analyze user characteristics and generate suggested information.

[0612] "Characteristics" refer to individual attributes of a user, such as their skills, aptitudes, and interests.

[0613] "Suggested information" refers to career options and advice generated based on the user's characteristics and market trends.

[0614] "Visual presentation" refers to displaying proposed information through a display or screen in a way that users can easily understand.

[0615] "Job options" refer to job and career choices that are deemed appropriate for the user.

[0616] "Input" refers to the feedback and additional information that users provide through the system.

[0617] This invention is a system aimed at providing users with appropriate suggestions regarding their career plans. Users first input information such as their educational background, work experience, skills, and areas of interest using a terminal. This input is done, for example, through a form on a smartphone or computer screen. The input information is then transmitted to a server via the internet.

[0618] The server acts as an information processing unit, receiving data from users. After preprocessing the received data, the server uses a generative AI model to perform data analysis. This model incorporates machine learning algorithms to analyze user characteristics and generate individually optimized career plans.

[0619] The career plan reflects the latest industry trends and suggests specific job options, such as "skills required as a data scientist" or "experience in front-end development." This suggested information is sent from the server to the user's terminal and presented visually. Users can review the suggestions on the screen and evaluate them based on their own thoughts and preferences.

[0620] Furthermore, users can input feedback on the proposed career plan from their device and send it back to the server. The server can then analyze this feedback and adjust or update the proposed plan.

[0621] As a concrete example, a prompt might say, "Please suggest suitable job roles for a recent graduate user aspiring to be an engineer." Using this prompt, the generating AI model will create specific career options that are appropriate for the user.

[0622] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0623] Step 1:

[0624] The user inputs information using a terminal. The user enters information such as educational background, work history, skills, and areas of interest into a form. This input data is then prepared by the terminal to be sent to the server. Specifically, the entered information is formatted in a digital format and converted into packets according to a communication protocol.

[0625] Step 2:

[0626] The server receives data from the terminal. The server preprocesses this received data. Specifically, it cleanses the data by imputing missing values ​​and detecting outliers. This process prepares the data for analysis. The input is the user's raw data, and the output is the processed dataset.

[0627] Step 3:

[0628] The server analyzes user data using a generated AI model. The server activates machine learning algorithms to analyze user characteristics. Specifically, it quantifies and evaluates user skills and aptitudes, and generates an appropriate career plan based on the results. The input is a pre-processed dataset, and the output is the evaluation result based on the analysis.

[0629] Step 4:

[0630] The server generates suggestion information based on the analysis results. Here, the generating AI model creates specific suggestion information that includes a career plan optimized for the user. This plan reflects job options based on the user's interests and skills, as well as industry trends. The server uses prompts to ask the AI ​​model appropriate questions and generate information. The output is visual information to be presented to the user.

[0631] Step 5:

[0632] The server sends the generated proposal information to the terminal. The terminal displays the received proposal information. The user can visually review the plan and provide evaluations and feedback. The output is in a format that the user can view.

[0633] Step 6:

[0634] Users input feedback to the server via their devices. Users provide feedback such as evaluations of the proposed career plan and requests for revisions. This feedback is then prepared to be sent back to the server as data. The input consists of user feedback information.

[0635] Step 7:

[0636] The server analyzes user feedback and updates the suggested information as needed. The server processes the feedback data and performs a re-analysis to generate a new career plan. This process enables optimization based on user feedback, ensuring that the final suggested information is better tailored to the user's needs.

[0637] (Application Example 1)

[0638] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0639] Traditionally, users have required considerable time and effort to obtain career plans based on their aptitudes. Furthermore, there is a lack of systems that utilize voice recognition to provide career suggestions through natural, two-way communication with users. Therefore, there is a need for a new information provision system that offers intuitive and immediate suggestions to users.

[0640] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0641] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, and means for presenting the suggested information to the user via a display device or audio playback device. This allows the user to intuitively obtain an optimal career plan based on their interests and abilities, and enables natural interaction through communication utilizing speech recognition.

[0642] A "user" refers to an individual who inputs information and receives career plan suggestions.

[0643] An "information processing device" refers to a computer or server that analyzes data received from a user and generates suggested information.

[0644] "Characteristics" refers to the individual attributes and abilities necessary for generating a career plan, such as the user's educational background, work history, skills, and interests.

[0645] "Suggested information" refers to information that includes optimal career plans and occupational options for the user, generated based on the results of an analysis of the user's characteristics.

[0646] A "display device" refers to a screen or monitor used to visually present generated suggestion information to the user.

[0647] A "sound playback device" refers to a speaker used to present generated suggestion information to the user audibly.

[0648] "Voice recognition means" refers to a system or technology for converting a user's voice input into text data.

[0649] "Feedback" refers to the opinions and suggestions for improvement that users provide regarding proposed information.

[0650] "Interaction" refers to the exchanges and responses that occur between the user and the system.

[0651] To implement this invention, it is necessary to construct a system that combines a speech recognition function, a generative AI model, and an information processing device. A specific embodiment of this system is shown below.

[0652] First, a speech recognition system is installed in the consumer robot. APIs such as the Google Speech-to-Text API can be used for speech recognition. This speech recognition system captures voice input from the user and converts that audio into text data. The robot's role is to accurately understand the user's questions and pass them on to the next processing step.

[0653] Next, the converted text data is sent to an information processing device. This device is set up as a high-performance computer and provides an environment for running a generative AI model. For example, the generative AI model uses OpenAI's GPT-4 to analyze user input and generate career suggestions. This model creates optimal job options and career plans based on the user's characteristics, interests, skills, and other relevant information.

[0654] The generated suggestion information is then presented to the user through the robot's display and audio playback devices. Visually, a touchscreen display is used, and aurally, a built-in speaker is used. This allows the user to receive information both visually and aurally.

[0655] Furthermore, users can provide feedback on the suggested information, and this feedback is sent back to the information processing device via the speech recognition system. This feedback information is then re-evaluated by the generative AI model, and the career plan is updated as needed.

[0656] As a concrete example, if a recent graduate aspiring to be an engineer says to a robot, "I am interested in data science," a speech recognition system will convert it into text, an information processing system will analyze it, and then present a career suggestion such as, "We recommend that you study the basics of Python and machine learning."

[0657] An example of a prompt message is, "Analyze the user's career-related information obtained through speech recognition and generate an optimal career plan using a machine learning model." This prompt enables the information processing device to create suggestion information tailored to the user's needs.

[0658] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0659] Step 1:

[0660] The user speaks to the robot and provides voice input. The device is equipped with a voice recognition system that captures this voice input. The input is the user's voice, and the output is the voice data.

[0661] Step 2:

[0662] The audio data captured by the device is converted into text data through a speech recognition system. This process uses a speech recognition API to analyze the audio waveform and output text data. The input is audio data, and the output is text data.

[0663] Step 3:

[0664] The converted text data is transferred to a server and analyzed by a generative AI model on the server. Here, prompt sentences are used to generate optimal career suggestions based on the user's characteristics and interests. The input is text data, and the output is suggestion information including the analysis results.

[0665] Step 4:

[0666] The suggestion information generated by the server is sent to the terminal and presented to the user either visually on the terminal's display or as audio via an audio playback device. The input is the suggestion information from the server, and the output is either a display or audio output.

[0667] Step 5:

[0668] The user reviews the presented suggestion information and inputs their feedback into the device via voice. This feedback is also converted into text data by a voice recognition system. The input is voice feedback, and the output is the text data of that feedback.

[0669] Step 6:

[0670] The server re-evaluates the received feedback text data and updates the suggestion information if necessary. In this process, the feedback is analyzed again using the generative AI model to generate an optimized career plan. The input is the feedback text data, and the output is the updated suggestion information.

[0671] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0672] This invention incorporates an emotion engine that recognizes user emotions into a system that processes user information and proposes a career plan. The system employs a process in which the emotion engine operates during the process of user input from a terminal and processing that information on a server.

[0673] When a user enters their work history, education, skills, and areas of interest via their device, the emotion engine analyzes the user's facial expressions, tone of voice, and emotion-related keywords in the text in real time, extracting them as emotion data. The server then combines and analyzes the received user information and emotion data to propose a career plan that is suitable for the user's feelings and psychological state.

[0674] For example, if the emotion engine detects feelings of tension or anxiety when a user enters their desired job type, the server will take that into consideration and include industry information and recommended skill-building methods to provide reassurance in its suggestions. Furthermore, if feelings of enjoyment or excitement are detected during the interaction with the user, the presentation method and content of the plan will be adjusted to enhance motivation.

[0675] This system allows users to receive more personalized career plans based not only on their skills and aptitudes, but also on their emotions and psychological state, ultimately enabling them to make more satisfying choices.

[0676] The following describes the processing flow.

[0677] Step 1:

[0678] The user accesses the device and enters profile information, interests, work history, etc. Upon receiving this information, the device activates its camera and microphone to record the user's emotions and prepares to acquire emotional data.

[0679] Step 2:

[0680] The device transmits the user's facial expressions and voice, along with the input information, to the emotion engine in real time. The emotion engine uses facial recognition technology and voice analysis to identify the user's emotional state.

[0681] Step 3:

[0682] The emotion engine analyzes the user's emotions from the obtained facial expressions and voice, and generates emotion tags such as tension, joy, and anxiety. These emotion tags are sent to the server along with the user information.

[0683] Step 4:

[0684] The server receives user information and emotion tags, and uses a generation AI to analyze and generate a career plan based on the user's skills, aptitudes, and emotional state. The server adjusts the plan content considering the emotional state, for example, by incorporating suggestions that provide a sense of security or information that motivates the user.

[0685] Step 5:

[0686] The server generates a carrier plan and sends it to the device. The device then displays the suggested information to the user in an easy-to-understand format, providing visual feedback.

[0687] Step 6:

[0688] Users provide feedback by reviewing the provided career plan and entering their thoughts and requests. Upon receiving feedback, the device records emotional data again and captures the user's reaction.

[0689] Step 7:

[0690] The device sends user feedback and newly acquired sentiment data to the server. The server re-evaluates this feedback and sentiment state, adjusts the career plan as needed, and prepares to provide updated suggestion information.

[0691] (Example 2)

[0692] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0693] Conventional career plan proposal systems relied solely on user input information and failed to consider the user's emotions or psychological state. As a result, in situations where users felt anxious or stressed, appropriate suggestions were not provided, leading to a decrease in user satisfaction.

[0694] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0695] In this invention, the server includes means for analyzing the user's emotions, means for transmitting the information received from the user to a device for processing the information, and means for adjusting the presented information in consideration of the emotions. This makes it possible to propose a career plan that takes the user's emotional state into account, resulting in more personalized suggestions.

[0696] A "user" refers to an entity that inputs information into the system and receives career plan suggestions.

[0697] A "processing device" refers to a computer that receives information transmitted by a user and performs analysis on it.

[0698] "Attributes" refer to data about the user, such as work history, education, skills, and areas of interest.

[0699] "Presented information" refers to the career plans and proposals offered to users.

[0700] "Emotions" refers to data such as facial expressions, tone of voice, and keywords in the text that indicate the user's psychological state.

[0701] "Reaction" refers to the feedback or reaction a user gives to the information presented by the system.

[0702] This invention relates to a career plan suggestion system that takes into account the user's characteristics and emotions. The system achieves more personalized suggestions through a process where the user provides information via a terminal, and a server generates a career plan based on that information.

[0703] Users input information such as their work history, education, skills, and areas of interest using a device. The device is equipped with a camera and microphone, which record the user's facial expressions and voice in real time. This data is analyzed by an emotion engine within the device and extracted as emotion data using software such as Python and TensorFlow.

[0704] User information and emotional data are encrypted and sent to the server. The server organizes the received data using Python's pandas library and generates a career plan tailored to the user's emotional state using scikit-learn. This allows the server to suggest the most suitable career path for the user. For example, if the server detects anxiety about a job type entered by the user, it will include reassuring information and methods for skill development related to that job in its suggestions. Conversely, if positive emotions are detected, it will add success stories and visions of the future to boost the user's motivation.

[0705] For example, if a user expresses interest in a "digital marketing" position and enters their preferences enthusiastically, the server can include visual content showcasing future career prospects in its suggestions. This allows for suggestions that resonate with the user's interests and emotions.

[0706] Examples of prompts to input into a generative AI model

[0707] "Please generate a digital marketing career plan based on user sentiment data. It should include an engaging story and suggestions for skill development."

[0708] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0709] Step 1:

[0710] Users input their work history, education, skills, and areas of interest using a terminal. This information is entered through a GUI built on the terminal. The entered data reflects the user's career goals and interests and is stored as basic data necessary for subsequent processing.

[0711] Step 2:

[0712] The device captures the user's facial expressions with a camera and records their voice with a microphone. These inputs are sent to an emotion engine and analyzed in real time using OpenCV and TensorFlow. The analysis results in data representing the user's emotional state. This emotional data reflects the user's psychological state and is used in the next stage of career plan generation.

[0713] Step 3:

[0714] The device sends input information and sentiment data to the server. The data is encrypted during transmission to maintain security. The server first organizes the received data and structures it as a dataframe using the Python pandas library. This structured data is then ready to be input into the model.

[0715] Step 4:

[0716] The server performs analysis using scikit-learn based on organized information and sentiment data. This analysis generates a career plan that takes into account the user's work history, education, and emotional state. The output here is a career plan that includes optimal job candidates and skill development suggestions for the user.

[0717] Step 5:

[0718] The server sends the generated carrier plan to the device. The device displays the proposal in a visually easy-to-understand format. The user can then refer to this plan and decide on their next course of action. The output in this process is proposal information processed in a way that is easy for the user to understand.

[0719] (Application Example 2)

[0720] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0721] Traditional career planning systems primarily offer suggestions based on the user's basic information and aptitudes, lacking personalized suggestions that take into account their emotions and psychological state. As a result, users often feel anxious or dissatisfied with the suggested career plans, making the selection process difficult.

[0722] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0723] In this invention, the server includes means for transferring information received from the user to an information processing device, means for analyzing the user's characteristics and generating suggested information based on the results, means for analyzing emotional data using an emotion recognition device that recognizes the user's emotional state, and means for adjusting and presenting the suggested information based on the user's emotional state. This makes it possible to provide a personalized career plan that is tailored to the user's emotions and psychological state.

[0724] "Information received from users" refers to information such as work history, educational background, skills, and areas of interest that users enter via their devices.

[0725] An "information processing device" is a digital device that analyzes information received from a user and generates appropriate suggestions.

[0726] "Analyzing characteristics" means analyzing a user's basic data, behavior, preferences, etc., to extract individual features.

[0727] "Suggested information" refers to information about the next actions or options a user should take, generated based on the analysis results.

[0728] An "emotion recognition device" is a device that determines a user's emotional state based on their facial expressions, tone of voice, and other factors.

[0729] "Emotional data" refers to digital data about a user's emotions acquired by an emotion recognition device.

[0730] "Adjusting and presenting based on emotional state" means appropriately arranging the proposed content according to the user's emotions and communicating it to the user.

[0731] The system for implementing this invention consists of a user terminal, an information processing server, and an emotion recognition device. The user terminal has an interface for inputting information such as work history, educational background, skills, and areas of interest. This information is transferred to the server via a network.

[0732] The server first processes the information received from the user and analyzes the user's characteristics. This analysis includes, for example, referencing databases and utilizing machine learning models. Based on the analysis results, it generates appropriate suggestion information for the user. This suggestion information includes career options based on the user's interests and abilities.

[0733] In this process, the emotion recognition device analyzes the user's facial expressions and tone of voice, generating emotion data in real time. This emotion data is sent to a server and used to adjust the suggested information. The server, taking the emotional state into consideration, presents the suggested information in the most beneficial way for the user.

[0734] For example, if the server detects tension when a user enters their desired job type, it will provide relaxing music or reassuring information. Furthermore, if the user shows strong excitement or interest, it will present a career plan that further enhances those feelings.

[0735] An example of a prompt message when using a generative AI model is as follows: "User information: Work experience = 5 years, Skills = Java, Interests = Web development, Emotions = Stress. Based on this, please propose a detailed career plan."

[0736] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0737] Step 1:

[0738] The user enters their information from a terminal. The user operates the terminal and enters information such as their work history, education, skills, and areas of interest. This information is transferred from the terminal to the server in digital format. During this process, a simple validation check is performed to verify the accuracy of the entered information.

[0739] Step 2:

[0740] The server analyzes user characteristics. The server processes the received user information, refers to a database, and extracts user information with similar characteristics. A machine learning model is used to generate personalized suggestion information. The input is basic user information, and the output is suggested candidate information.

[0741] Step 3:

[0742] Collection of emotional data using an emotion recognition device. While the user is using the device, the camera and microphone record the user's facial expressions and voice tone. Based on this data, the emotion recognition device analyzes emotions in real time and generates emotional data. The input is the user's facial expressions and voice, and the output is emotional data.

[0743] Step 4:

[0744] The server integrates emotional data and trait analysis results. The server combines the trait analysis results with the collected emotional data to adjust the suggested information, taking into account the user's current psychological state. This enables more personalized suggestions. The output is the adjusted suggested information.

[0745] Step 5:

[0746] The server presents suggested information to the user. The refined suggested information is sent to the terminal and displayed through the user interface. The order and format of the information presentation are carefully designed to attract the user's interest. The input is the refined suggested information, and the output is the content displayed to the user.

[0747] Step 6:

[0748] Collecting and analyzing user feedback. Users can provide feedback on suggested information. This feedback is then analyzed on the server and used to improve future suggested information. The input is user feedback, and the output is the analyzed feedback results.

[0749] 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 controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0750] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0751] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0752] Furthermore, the emotion identification model 59, acting 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 a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0753] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0754] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0755] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0756] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0757] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is 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 the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0758] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0759] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0760] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0761] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0762] 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.

[0763] Furthermore, it is not necessary to store the entirety 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 the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0764] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0765] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of 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). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0766] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0767] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0768] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0769] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0770] The following is further disclosed regarding the embodiments described above.

[0771] (Claim 1)

[0772] A means for transferring information received from the user to a processing unit,

[0773] The processing device includes means for analyzing the user's characteristics and generating suggested information based on the results,

[0774] A means for presenting the aforementioned proposed information to the user,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, comprising means for including multiple career options based on the user's interests and skills in the suggested information.

[0778] (Claim 3)

[0779] The system according to claim 1, further comprising means for receiving feedback from users regarding the proposed information and readjusting the proposed information based on that feedback.

[0780] "Example 1"

[0781] (Claim 1)

[0782] A means for transferring information obtained from a user to an information processing device,

[0783] A means for analyzing user characteristics using a generated AI model on the aforementioned information processing device and generating suggested information based on the results,

[0784] A means for visually presenting the aforementioned proposed information to the user,

[0785] A system that includes this.

[0786] (Claim 2)

[0787] The system according to claim 1, comprising means for including multiple job options in the proposed information based on the user's aptitude and the latest industry trends.

[0788] (Claim 3)

[0789] The system according to claim 1, comprising means for receiving input regarding proposal information from a user and adjusting and updating the proposal information based on that input.

[0790] "Application Example 1"

[0791] (Claim 1)

[0792] A means for transferring information received from a user to an information processing device,

[0793] The information processing device includes means for analyzing the user's characteristics and generating suggested information based on the results,

[0794] Means for presenting the proposed information to the user via a display device or audio playback device,

[0795] A means for converting user input into text data using speech recognition means,

[0796] A means of reanalyzing user feedback and updating suggestion information,

[0797] A system that includes this.

[0798] (Claim 2)

[0799] The system according to claim 1, comprising means for including multiple career options based on the user's interests and abilities in the suggested information.

[0800] (Claim 3)

[0801] The system according to claim 1, comprising speech recognition and speech synthesis means for supporting voice communication by the user.

[0802] "Example 2 of combining an emotion engine"

[0803] (Claim 1)

[0804] A means of transmitting information received from a user to a device that processes that information,

[0805] The aforementioned processing device includes means for analyzing user attributes and generating presentation information based on the results,

[0806] Means for providing the aforementioned information to the user,

[0807] A means of analyzing user emotions,

[0808] Means for adjusting the presented information in consideration of the aforementioned emotions,

[0809] A system that includes this.

[0810] (Claim 2)

[0811] The system according to claim 1, comprising means for including multiple job options based on the user's areas of interest and skills in the information presented.

[0812] (Claim 3)

[0813] The system according to claim 1, further comprising means for receiving a response from a user regarding the presented information and readjusting the presented information based on the content of that response.

[0814] "Application example 2 when combining with an emotional engine"

[0815] (Claim 1)

[0816] A means for transferring information received from a user to an information processing device,

[0817] The information processing device includes means for analyzing the user's characteristics and generating suggested information based on the results,

[0818] A means for analyzing emotional data using an emotion recognition device that recognizes the user's emotional state,

[0819] A means for adjusting and presenting the aforementioned proposed information based on the user's emotional state,

[0820] A system that includes this.

[0821] (Claim 2)

[0822] The system according to claim 1, comprising means for including multiple career options based on the user's interests and abilities in the suggested information.

[0823] (Claim 3)

[0824] The system according to claim 1, further comprising means for receiving feedback from users regarding the proposed information and readjusting the proposed information based on that feedback. [Explanation of symbols]

[0825] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for transferring information received from a user to an information processing device, The information processing device includes means for analyzing the user's characteristics and generating suggested information based on the results, Means for presenting the proposed information to the user via a display device or audio playback device, A means for converting user input into text data using speech recognition means, A means of reanalyzing user feedback and updating suggestion information, A system that includes this.

2. The system according to claim 1, comprising means for including multiple career options based on the user's interests and abilities in the suggested information.

3. The system according to claim 1, comprising speech recognition and speech synthesis means for supporting voice communication by the user.

Images