system

Abstract

We provide the system. [Solution] The information processing device provides a means for collecting posted data from the user's communication platform, The aforementioned posted data is analyzed using natural language processing technology to identify the sentiment and topic of the posts, Using a generative model, a means of recommending suitable occupations and activities to users based on the analysis results, A means of visually displaying the aforementioned recommendations and promoting self-understanding by the user, 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 chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern communication platforms, individuals routinely post their thoughts and feelings on a daily basis, but there is no specific method to comprehensively analyze these posts to understand their own personalities and career suitability. As a result, individuals are losing the opportunity to understand their own strengths and appropriate careers. In addition, conventional methods have the problem that the analysis results are difficult to intuitively understand and are difficult for users to utilize.

Means for Solving the Problems

[0005] This invention is a system that collects posted data from users' communication platforms and analyzes this data using natural language processing technology to identify the sentiment and topic of the posts. Furthermore, by using a generative model and comparing it with other classified data, it recommends occupations and activities suitable for individual users. The recommendation results are displayed in a visual format, providing a mechanism that allows users to easily deepen their self-understanding. This provides a means for individual users to grasp their own characteristics and make choices that are suitable for their future careers.

[0006] An "information processing device" is a computer system that collects, processes, and analyzes data.

[0007] A "user" is an individual or legal entity that uses the system and has data from their communication platform analyzed.

[0008] A "communication platform" refers to services such as social networking services (SNS) and chat applications that allow users to communicate and share information online.

[0009] "Posted data" refers to text, images, videos, and associated metadata that users publish or transmit on a communication platform.

[0010] "Natural language processing technology" refers to technologies that enable computers to understand, interpret, and generate human language, and includes text analysis, sentiment analysis, and topic extraction.

[0011] A "generative model" is an algorithm or machine learning model that learns patterns from large amounts of data to generate or predict new information.

[0012] "Occupation or activity" refers to the types of jobs that the user may be suited for, or the social or personal activities in which they can participate.

[0013] "Visual display" refers to presenting analysis results and information to users in a visual format such as dashboards and graphs. [Brief explanation of the drawing]

[0014] [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]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a 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), etc.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is a system that acquires posted data from users' communication platforms, analyzes it, and recommends suitable occupations and activities for the users. This system mainly consists of three main entities: terminals, servers, and users.

[0036] The device collects posted data from the communication platform based on user consent. The collected data is sent to a server and analyzed using natural language processing technology. Natural language processing technology is used to identify the sentiment and topic of the posts.

[0037] The server inputs the analysis results obtained from this process into a generative model, which compares the user's posted data with other datasets. The generative model learns the characteristics of various occupations and activities and identifies other users and occupations with similar posting patterns. Based on these comparison results, suitable occupations and activities for the user are identified.

[0038] The analysis results are sent from the server to the terminal and displayed visually to the user. This allows users to easily understand their own personality traits and aptitudes, and make decisions regarding their career and lifestyle.

[0039] As a concrete example, consider a user who frequently shares technology-related articles on social media and posts detailed descriptions of their own projects. In this case, natural language processing techniques are used to extract the technical orientation and creative thinking tendencies from the posts. The generative model can then recommend professions such as software developer or project manager, given these characteristics. This result is visually displayed on a dashboard, allowing the user to gain insights into their own aptitudes and potential.

[0040] This invention provides users with concrete tools to analyze their own posting patterns and deepen their self-understanding. This enables users to find the optimal career path for themselves and obtain information to achieve more fulfilling activities.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The device accesses the user's communication platform account and collects posted data via an API. This data includes post content, posting date and time, hashtags, and the number of reactions. The device securely transmits this data to the server.

[0044] Step 2:

[0045] The server preprocesses the received data. Specifically, the server cleanses the text data, removing special characters and emojis, and eliminating unnecessary spaces. Next, the server tokenizes the text, preparing it for analysis.

[0046] Step 3:

[0047] The server applies natural language processing techniques to perform sentiment analysis on text data. The server categorizes the content of posts into positive, negative, and neutral sentiment categories. Furthermore, topic modeling is used to extract the themes of the posts and identify the user's interests.

[0048] Step 4:

[0049] The server uses a generative model to compare the user's analysis results with other data. The server matches them against occupation lists and known patterns to identify occupations and activities similar to the user.

[0050] Step 5:

[0051] The server compiles the analysis results and selects recommended occupations and activities for the user. Next, the server visually organizes the results and sends the data to the user's terminal in an easy-to-understand format.

[0052] Step 6:

[0053] Based on the data received by the device, the results are displayed to the user in the form of a dashboard or report. Based on these results, the user can deepen their self-understanding and consider a career path that suits them.

[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 world, it is difficult for users to identify appropriate occupations and activities based on their own submitted data and find the career path that best suits them. Furthermore, analyzing submitted data and recommending occupations requires advanced technology, and there is a need for efficient methods to perform these tasks. In addition, security during the data collection process is essential for protecting personal information.

[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 collecting information posted from a user information exchange platform, means for analyzing the posted information using natural language processing techniques to identify emotions and themes, and means for suggesting appropriate occupations and activities from the analysis results using a generative model. This makes it possible for users to easily find occupations and activities that are best suited to them, thereby deepening their self-awareness.

[0059] An "information processing device" is a mechanical or electronic device that has the function of collecting, analyzing, and processing data.

[0060] An "information exchange platform" is an online platform used by users to post, share, and exchange information.

[0061] "Posted information" refers to all content, such as text, images, and videos, that users transmit through the information exchange platform.

[0062] "Natural language processing techniques" are technologies that use computers to analyze and understand human language, and are particularly used for detecting emotions and themes.

[0063] "Emotion and subject matter" refers to the emotional tone and main topic contained in the posted information.

[0064] A "generative model" is a machine learning model used to learn patterns from data and generate new information or suggestions.

[0065] "Appropriate occupation or activity" refers to the occupation or life activity that best suits the user, based on their posting patterns and analysis results.

[0066] "Personal confidentiality" refers to a state in which users' personal information is protected from being leaked to external parties.

[0067] This invention is an information processing system aimed at enabling users to make optimal choices regarding their careers and lifestyles based on their activities on an information exchange platform. This system mainly consists of three components: a terminal, a server, and a user, each playing a specific role.

[0068] The device plays the role of collecting information posted from the information exchange platform with the user's consent. This collection utilizes secure communication methods, such as the HTTPS protocol, to safely protect the information. This ensures the confidentiality of the user's personal information.

[0069] The server analyzes the information received from the terminal based on natural language processing (NLP) techniques. These techniques utilize libraries such as SpaCy and NLTK. Through this analysis, the server identifies the sentiment and theme of the posted information and inputs the data into a generative model based on this information.

[0070] The generative model uses pre-trained machine learning algorithms to suggest appropriate occupations and activities from user posts. By comparing posts from other users, the model provides recommendations that match the user's interests and skills. For example, a user who frequently posts technical content can be recommended technical occupations.

[0071] Ultimately, the recommendations are sent from the server to the user's device and displayed visually. Through the dashboard, users can gain insights into their aptitudes and potential. For example, a user might receive a prompt such as, "Which programming language should I learn to benefit my career?" This allows users to take concrete actions toward career development and lifestyle improvement.

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

[0073] Step 1:

[0074] The device collects information posted from the information exchange platform with the user's consent. The input consists of posts made by the user on the platform, and the output is stored on the device as raw data. At this stage, a secure protocol is used to ensure the security of the information.

[0075] Step 2:

[0076] The terminal transfers the collected posted data to the server. The input is the raw data stored on the terminal, and the output is the data sent to the server. This transfer involves specific actions to ensure data security by using the HTTPS protocol.

[0077] Step 3:

[0078] The server analyzes the received data using natural language processing techniques. Raw data is sent to the server as input, and sentiment and topic identification are performed on this data. After this analysis, data with the characteristics of the analyzed sentiment and topic is obtained as output. Specifically, sentiment analysis and keyword extraction are used.

[0079] Step 4:

[0080] The server inputs results from natural language processing techniques into an AI model that recommends suitable occupations and activities for the user. The input is the analysis results, which are compared with the model's training data to generate a list of appropriate occupations and activities as output. Specifically, the model compares and analyzes posting patterns and evaluates similarity.

[0081] Step 5:

[0082] The server sends the generated recommendation list to the terminal. The input is the recommendation list created on the server, and the output is the data sent to the terminal. Here again, a secure method is used for transferring information.

[0083] Step 6:

[0084] The device visually displays a list of recommendations received from the server to the user. The input is received data, and the output is visualized information on the user's dashboard. Based on this information, the user can consider specific carrier choices and lifestyle improvements.

[0085] (Application Example 1)

[0086] 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."

[0087] In recent years, many people have been using communication platforms to share their daily activities and opinions. However, there is a lack of effective means to analyze this information and provide personalized recommendations for suitable occupations, activities, and even financial assets. In particular, it is difficult to systematically analyze consumer behavior data and utilize it as useful investment information. Against this backdrop, there is a need to provide personalized recommendations tailored to individual needs using user behavior data.

[0088] 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.

[0089] In this invention, the server includes means for collecting digital information using an information processing device, means for identifying the sentiment and subject matter of the digital information using natural language processing technology, means for recommending occupations and activities suitable for the individual using a generative model, and means for analyzing the user's consumption history and generating financial asset suggestions. This enables precise analysis based on individual posts and consumption behavior, and makes it possible to suggest occupations, activities, and financial plans optimized for each user.

[0090] An "information processing device" is a computer system used to collect and analyze digital information.

[0091] A "communication platform" is a foundation for exchanging information and messages online, which users use on a daily basis.

[0092] "Digital information" refers to all electronic data that users generate or collect on online platforms.

[0093] "Natural language processing technology" is a technology that enables computers to understand and process natural human language.

[0094] A "generative model" is a type of algorithm that learns patterns from vast amounts of data and generates new recommendations.

[0095] "User consumption history" refers to records of purchases and expenses made by a user.

[0096] "Financial asset recommendations" refer to investment and asset management recommendations based on the user's individual financial situation and actions.

[0097] This invention is a system that proposes the most suitable occupation and financial assets to a user through the collection and analysis of digital information. The server collects digital information from a communication platform with the user's consent and identifies its sentiment and subject matter using natural language processing technology. The terminal transmits the collected digital information to the server, which uses a generative model to create suggestions based on the analysis results. This makes it possible to analyze the user's consumption history and propose appropriate financial assets.

[0098] The server operates a system for collecting and processing data using programming languages ​​such as Python. Natural language processing techniques utilize NLP libraries and APIs. The generative model uses a neural network model that learns from large datasets and generates new recommendations. The final recommendations are displayed on the user's device using visualization tools.

[0099] For example, if a user has recently purchased many technology-related products, we might suggest a stock fund related to technology companies. In this way, detailed suggestions based on individual behavioral data become possible. An example of a prompt message is shown below.

[0100] "This user has recently purchased many technology-related products. Based on this trend, what investment products would you recommend? Please consider the generated answer and take market trends into account."

[0101] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0102] Step 1:

[0103] The device collects digital information from the communication platform with the user's consent. This information includes posts and purchase history that reflect the user's daily activities and consumption behavior. Because the collected information is difficult to analyze directly, it is converted into an appropriate format and sent to the server. The input is user posts and purchase history, and the output is a data format that can be transferred to the server.

[0104] Step 2:

[0105] The server receives digital information transmitted from the terminal and performs analysis using natural language processing (NLP) techniques. Specifically, it extracts sentiment and themes from text using an NLP library and organizes them as structured data. The input is the digital information received from the terminal, and the output is the sentiment and theme information as a result of the analysis. This result is then prepared for transmission to a generative model.

[0106] Step 3:

[0107] The server inputs the analysis results into a generative model and initiates a process to recommend suitable occupations and financial assets for the individual. The generative model is a neural network that searches for user-like profiles from pre-trained data and generates optimal suggestions. The input is the analysis results of natural language processing, and the output is recommended information on occupations and assets.

[0108] Step 4:

[0109] The server visualizes the generated suggestions and sends them to the terminal. The user can then view the suggested occupations and financial assets suitable for them through a visual dashboard. The terminal receives this information and displays it to the user in an intuitive and easy-to-understand manner. The input is the recommendations from the generative model, and the output is the visualized information.

[0110] Step 5:

[0111] Users review the information presented on their devices and make decisions regarding their careers and investments. User feedback may be used to further improve the system. Input is the visualized information from the device, and output is the user's actions and feedback.

[0112] 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.

[0113] This invention is a system that combines an emotion engine that recognizes user emotions, thereby comprehensively analyzing user-generated data from communication platforms and using the results to recommend suitable occupations and activities to users.

[0114] The device collects posted data from the user's communication platform. Based on the user's consent, it can include not only text data but also audio and image data. This allows for the creation of richer datasets. The collected data is securely transmitted to the server.

[0115] The server analyzes the received data using natural language processing technology. In addition to conventional text analysis, it utilizes an emotion engine to analyze the emotions and nuances hidden within posts. This emotion engine detects not only the user's short-term emotional state but also their long-term emotional patterns, and generates analysis results that take both into account.

[0116] The analysis results are input into a generative model on the server and compared with known data related to specific occupations or activities. This generative model has been trained on classified occupational data and can recommend suitable occupations and activities to users based on their similarity to the posted data.

[0117] Based on the analysis, if suitable occupations or activities are recommended for the user, the server visualizes this information and sends it back to the terminal. The terminal displays the analysis results to the user using graphs, charts, etc., allowing the user to easily understand their own characteristics and potential.

[0118] For example, if a user frequently shares emotionally rich technical experiences or posts images and audio, the sentiment engine analyzes this to identify creative personality traits in the technical field. Based on this, a generative model recommends engineering and design jobs to the user, and the device displays this in a dashboard format.

[0119] This system allows users to understand their inner emotional characteristics through their own posts and better comprehend their career and activity options.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The device accesses the user's communication platform account and collects posted data, including text, audio, and images, via an API. The collected data is sent to the server via a secure protocol.

[0123] Step 2:

[0124] The server cleanses and preprocesses the data it receives. This includes removing special characters and tokenizing text data, converting audio data to text using speech recognition technology, and extracting specific features from image data using an image recognition engine.

[0125] Step 3:

[0126] The server uses natural language processing techniques to perform sentiment analysis on text data. Next, it uses a sentiment engine to integrate and analyze all data (text, audio, and images) to identify short-term and long-term sentiment patterns.

[0127] Step 4:

[0128] The server applies a generative model and compares the aforementioned sentiment analysis results with other categorized occupational data. This allows it to evaluate the similarity to the user's occupation and activities and identify their suitability.

[0129] Step 5:

[0130] The server generates occupation and activity recommendations based on the analysis results and prepares visualization data to send to the terminal. The visualization data includes a description of the user's characteristics and recommended occupations and suggestions.

[0131] Step 6:

[0132] The device displays the received visualization data to the user as a dashboard or report. This allows the user to gain a detailed understanding of their emotional characteristics and the resulting career aptitudes.

[0133] (Example 2)

[0134] 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".

[0135] Finding suitable occupations and activities based on one's emotional state and interests is a challenging task. Traditional methods have limited emotional data collection and analysis capabilities, sometimes failing to provide optimal recommendations to users. Protecting data privacy is also a critical issue.

[0136] 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.

[0137] In this invention, the server includes means for collecting digital information from the user's digital communication infrastructure, means for analyzing the digital information using language analysis technology to extract emotional states and themes, means for recommending suitable occupations and activities to the user based on the analysis results using a generative AI model, and means for securely transmitting the digital information while protecting privacy. This enables users to find more appropriate occupations and activities based on their posts and emotional data.

[0138] A "digital communication infrastructure" is a system that enables the exchange of information between users via the internet and communication terminals.

[0139] "Digital information" refers to all data that users post to communication platforms, including text, audio, and images, expressed in digital format.

[0140] "Language analysis technology" is a technique that uses natural language processing to analyze text and audio data, and to analyze the meaning and emotions contained within them.

[0141] "Emotional state" refers to the emotions and moods of users at any given time, inferred from their posted data.

[0142] A "generative AI model" refers to an artificial intelligence algorithm that generates new data or makes recommendations based on a training dataset.

[0143] "Transmitting while protecting privacy" refers to a process that ensures data is securely transferred to the server without being leaked externally.

[0144] "Analyzing similarity" is the process of finding similarities between different datasets and evaluating their relationships.

[0145] "Other digital information categorized by occupation" refers to a collection of digital data organized based on an already categorized occupation directory.

[0146] This invention is a system that analyzes digital information collected from a user's digital communication infrastructure and recommends the most suitable occupation or activity for that user. This system is implemented using terminals and servers.

[0147] The device first collects various digital information, such as text, audio, and images, posted to the communication platform, with the user's consent. This process is carried out using dedicated data collection software, and the collected data is protected by encryption technology and transmitted to the server via a secure connection.

[0148] The server analyzes the received digital information using natural language processing techniques. This analysis process includes a text analysis engine and speech / image processing algorithms, and in particular, uses a generative AI model to derive emotional states and themes. The emotion engine detects short-term and long-term emotional patterns and generates detailed analysis results based on them.

[0149] The generative AI model receives the analysis results as input data and compares them with classification data related to occupations that it has already learned. This model is designed to suggest suitable occupations and activities for users and analyzes the similarity of information with high accuracy.

[0150] For example, if a user makes posts that are rich in emotion related to technology, the emotion engine analyzes them and identifies creative personality traits in that field. Based on this, the generative AI model can recommend engineering or design jobs.

[0151] A concrete example of a prompt might be the instruction, "Analyze tech-related posts that evoke rich emotions and recommend related professions."

[0152] This system allows users to understand their inner characteristics through their own posts and sentiment data, and to discover new possibilities for their careers and activities.

[0153] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0154] Step 1:

[0155] The terminal collects digital information in text, audio, and image formats from the user's digital communication infrastructure. The user must consent to this data collection. Input is user-submitted data, and output is a collected dataset. The terminal operates by launching a data collection program and targeting the necessary information.

[0156] Step 2:

[0157] The terminal encrypts the collected digital information and sends it to the server using a secure communication protocol. The input is the collected dataset, and the output is the encrypted transmission data. This operation ensures that the data is securely transferred to the server without being leaked externally.

[0158] Step 3:

[0159] The server begins analyzing the received digital information using a natural language processing engine. It decrypts encrypted data as input and analyzes text, audio, and image data. The output provides analysis results regarding emotions and themes. Specifically, the engine extracts keywords and emotion indicators from the data.

[0160] Step 4:

[0161] The server inputs the analyzed data into a generating AI model. This model evaluates the similarity of the analysis results to existing occupational data. The input is the analysis results of sentiment and themes, and the output is a list of recommended occupations and activities. The server's operation includes matching with existing databases and model training.

[0162] Step 5:

[0163] The server visualizes the generated occupation and activity recommendations and sends them to the terminal along with prompt messages. The input is recommendation data from the model, and the output is visualized recommendation information. Specifically, it generates graphs and charts.

[0164] Step 6:

[0165] The device displays the received visualization information to the user. The input is the visualized recommendation results, and the output is visual feedback to the user. The device displays graphs and charts on its screen, allowing the user to deepen their understanding of their own characteristics and recommended carriers.

[0166] (Application Example 2)

[0167] 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".

[0168] In today's information network environment, it is difficult for users to find the optimal products and activities that match their emotional state, and traditional recommendation systems have the challenge of not being able to provide personalized recommendations that reflect these emotional changes. Furthermore, from a privacy perspective, there is a need to provide effective recommendations while ensuring the security of user data.

[0169] 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.

[0170] In this invention, the server includes means for collecting data from a user's communication platform using an information processing device, means for analyzing the data using natural language processing technology to identify the sentiment and topic of the data, and means for recommending products or activities suitable for the user based on the analysis results using a generative model. This enables instantaneous analysis of the user's sentiment, highly accurate recommendations of products and activities that respond to changes, and effectively promotes the user's willingness to purchase.

[0171] An "information processing device" is a device used to collect and analyze data from a user's communication platform.

[0172] "Data" refers to information posted by users on a communication platform, including text, audio, and images.

[0173] "Natural language processing technology" is a technique that uses computers to analyze human language and extract specific meanings and emotions.

[0174] A "generative model" is a model that generates new information based on input data, and is used to recommend products and activities that are suitable for the user based on the analysis results.

[0175] "Emotions" refer to the mental state analyzed from users' posts and actions, and they influence users' preferences and purchasing behavior.

[0176] A "topic" refers to a theme or subject identified based on user-submitted data.

[0177] "Recommending a product or activity" means presenting highly relevant products or activities based on the user's emotional state and preferences.

[0178] "Visual display" refers to displaying analyzed data and recommended information on the screen using graphs, charts, and other visual aids.

[0179] "Security" refers to technical measures taken to prevent unauthorized access to and leakage of data, and to protect user privacy.

[0180] The system implementing this invention first collects data from the user's communication platform using an information processing device. The data includes text, audio, and image data, which are collected with the user's consent and transmitted to the server while ensuring security and protecting privacy. The server analyzes this data using natural language processing technology to identify the user's emotions and topics of conversation. Specifically, it uses Python and natural language processing libraries such as NLTK and spaCy to analyze the text.

[0181] By utilizing generative models, the server recommends products or activities suitable for the user based on these analysis results. The generative models employ machine learning libraries such as TENSORFLOW® and PyTorch, comparing product classification data with the user's analyzed sentiment patterns to provide optimal recommendations based on similarity.

[0182] The server then visually displays these recommendations on the terminal to encourage the user's purchase. The terminal displays the analysis and recommendation results in the form of graphs and charts, allowing the user to easily understand the suggested products and activities.

[0183] For example, if a user posts "I want something fun today," the system can analyze this emotion and suggest entertainment-related products that match the user's interests. Another example of a prompt might be: "Build a system that analyzes the emotions of users based on their posts and recommends the most suitable products based on those emotions. Suggest relaxing products if the user is stressed, and celebratory products if they are happy."

[0184] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0185] Step 1:

[0186] The server collects data from the user's communication platform. It takes user-submitted text, audio, and image data as input and stores it securely. The server then converts this data into a format for analysis, preparing it for the next step.

[0187] Step 2:

[0188] The server analyzes the collected data using natural language processing techniques. The input is the data formatted in Step 1. The server uses Python and natural language processing libraries (NLTK and spaCy) to tokenize the text data and perform sentiment analysis. The output is the sentiment and topic extracted from the text.

[0189] Step 3:

[0190] The server uses a generative AI model to recommend products or activities based on the analysis results. The input is sentiment and topic information obtained in step 2. The server uses a generative model based on TensorFlow or PyTorch to calculate the similarity between the product database and the sentiment information. The output is a list of products suitable for the user.

[0191] Step 4:

[0192] The server visually displays recommended product information on the terminal. The input is the product list obtained in step 3. The server generates a graph or chart and sends it to the terminal via API for display on the screen in a format that is easy for the user to understand. The output is the product recommendations displayed on the user's screen.

[0193] Step 5:

[0194] The user reviews the information displayed on the device and considers the recommended products and activities. The input is the product information displayed on the device. The user performs purchase or search actions as needed and makes their own decisions based on the system's recommendations. The output is the next action based on the user's actions.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] [Second Embodiment]

[0199] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0200] 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.

[0201] 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).

[0202] 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.

[0203] 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.

[0204] 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).

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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.

[0210] 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".

[0211] This invention is a system that acquires posted data from users' communication platforms, analyzes it, and recommends suitable occupations and activities for the users. This system mainly consists of three main entities: terminals, servers, and users.

[0212] The device collects posted data from the communication platform based on user consent. The collected data is sent to a server and analyzed using natural language processing technology. Natural language processing technology is used to identify the sentiment and topic of the posts.

[0213] The server inputs the analysis results obtained from this process into a generative model, which compares the user's posted data with other datasets. The generative model learns the characteristics of various occupations and activities and identifies other users and occupations with similar posting patterns. Based on these comparison results, suitable occupations and activities for the user are identified.

[0214] The analysis results are sent from the server to the terminal and displayed visually to the user. This allows users to easily understand their own personality traits and aptitudes, and make decisions regarding their career and lifestyle.

[0215] As a concrete example, consider a user who frequently shares technology-related articles on social media and posts detailed descriptions of their own projects. In this case, natural language processing techniques are used to extract the technical orientation and creative thinking tendencies from the posts. The generative model can then recommend professions such as software developer or project manager, given these characteristics. This result is visually displayed on a dashboard, allowing the user to gain insights into their own aptitudes and potential.

[0216] This invention provides users with concrete tools to analyze their own posting patterns and deepen their self-understanding. This enables users to find the optimal career path for themselves and obtain information to achieve more fulfilling activities.

[0217] The following describes the processing flow.

[0218] Step 1:

[0219] The device accesses the user's communication platform account and collects posted data via an API. This data includes post content, posting date and time, hashtags, and the number of reactions. The device securely transmits this data to the server.

[0220] Step 2:

[0221] The server preprocesses the received data. Specifically, the server cleanses the text data, removing special characters and emojis, and eliminating unnecessary spaces. Next, the server tokenizes the text, preparing it for analysis.

[0222] Step 3:

[0223] The server applies natural language processing techniques to perform sentiment analysis on text data. The server categorizes the content of posts into positive, negative, and neutral sentiment categories. Furthermore, topic modeling is used to extract the themes of the posts and identify the user's interests.

[0224] Step 4:

[0225] The server uses a generative model to compare the user's analysis results with other data. The server matches them against occupation lists and known patterns to identify occupations and activities similar to the user.

[0226] Step 5:

[0227] The server compiles the analysis results and selects recommended occupations and activities for the user. Next, the server visually organizes the results and sends the data to the user's terminal in an easy-to-understand format.

[0228] Step 6:

[0229] Based on the data received by the device, the results are displayed to the user in the form of a dashboard or report. Based on these results, the user can deepen their self-understanding and consider a career path that suits them.

[0230] (Example 1)

[0231] 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."

[0232] In today's world, it is difficult for users to identify appropriate occupations and activities based on their own submitted data and find the career path that best suits them. Furthermore, analyzing submitted data and recommending occupations requires advanced technology, and there is a need for efficient methods to perform these tasks. In addition, security during the data collection process is essential for protecting personal information.

[0233] 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.

[0234] In this invention, the server includes means for collecting information posted from a user information exchange platform, means for analyzing the posted information using natural language processing techniques to identify emotions and themes, and means for suggesting appropriate occupations and activities from the analysis results using a generative model. This makes it possible for users to easily find occupations and activities that are best suited to them, thereby deepening their self-awareness.

[0235] An "information processing device" is a mechanical or electronic device that has the function of collecting, analyzing, and processing data.

[0236] An "information exchange platform" is an online platform used by users to post, share, and exchange information.

[0237] "Posted information" refers to all content, such as text, images, and videos, that users transmit through the information exchange platform.

[0238] "Natural language processing techniques" are technologies that use computers to analyze and understand human language, and are particularly used for detecting emotions and themes.

[0239] "Emotion and subject matter" refers to the emotional tone and main topic contained in the posted information.

[0240] A "generative model" is a machine learning model used to learn patterns from data and generate new information or suggestions.

[0241] "Appropriate occupation or activity" refers to the occupation or life activity that best suits the user, based on their posting patterns and analysis results.

[0242] "Personal confidentiality" refers to a state in which users' personal information is protected from being leaked to external parties.

[0243] This invention is an information processing system aimed at enabling users to make optimal choices regarding their careers and lifestyles based on their activities on an information exchange platform. This system mainly consists of three components: a terminal, a server, and a user, each playing a specific role.

[0244] The device plays the role of collecting information posted from the information exchange platform with the user's consent. This collection utilizes secure communication methods, such as the HTTPS protocol, to safely protect the information. This ensures the confidentiality of the user's personal information.

[0245] The server analyzes the information received from the terminal based on natural language processing (NLP) techniques. These techniques utilize libraries such as SpaCy and NLTK. Through this analysis, the server identifies the sentiment and theme of the posted information and inputs the data into a generative model based on this information.

[0246] The generative model uses pre-trained machine learning algorithms to suggest appropriate occupations and activities from user posts. By comparing posts from other users, the model provides recommendations that match the user's interests and skills. For example, a user who frequently posts technical content can be recommended technical occupations.

[0247] Ultimately, the recommendations are sent from the server to the user's device and displayed visually. Through the dashboard, users can gain insights into their aptitudes and potential. For example, a user might receive a prompt such as, "Which programming language should I learn to benefit my career?" This allows users to take concrete actions toward career development and lifestyle improvement.

[0248] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0249] Step 1:

[0250] The device collects information posted from the information exchange platform with the user's consent. The input consists of posts made by the user on the platform, and the output is stored on the device as raw data. At this stage, a secure protocol is used to ensure the security of the information.

[0251] Step 2:

[0252] The terminal transfers the collected posted data to the server. The input is the raw data stored on the terminal, and the output is the data sent to the server. This transfer involves specific actions to ensure data security by using the HTTPS protocol.

[0253] Step 3:

[0254] The server analyzes the received data using natural language processing techniques. Raw data is sent to the server as input, and sentiment and topic identification are performed on this data. After this analysis, data with the characteristics of the analyzed sentiment and topic is obtained as output. Specifically, sentiment analysis and keyword extraction are used.

[0255] Step 4:

[0256] The server inputs results from natural language processing techniques into an AI model that recommends suitable occupations and activities for the user. The input is the analysis results, which are compared with the model's training data to generate a list of appropriate occupations and activities as output. Specifically, the model compares and analyzes posting patterns and evaluates similarity.

[0257] Step 5:

[0258] The server sends the generated recommendation list to the terminal. The input is the recommendation list created on the server, and the output is the data sent to the terminal. Here again, a secure method is used for transferring information.

[0259] Step 6:

[0260] The device visually displays a list of recommendations received from the server to the user. The input is received data, and the output is visualized information on the user's dashboard. Based on this information, the user can consider specific carrier choices and lifestyle improvements.

[0261] (Application Example 1)

[0262] 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."

[0263] In recent years, many people have been using communication platforms to share their daily activities and opinions. However, there is a lack of effective means to analyze this information and provide personalized recommendations for suitable occupations, activities, and even financial assets. In particular, it is difficult to systematically analyze consumer behavior data and utilize it as useful investment information. Against this backdrop, there is a need to provide personalized recommendations tailored to individual needs using user behavior data.

[0264] 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.

[0265] In this invention, the server includes means for collecting digital information using an information processing device, means for identifying the sentiment and subject matter of the digital information using natural language processing technology, means for recommending occupations and activities suitable for the individual using a generative model, and means for analyzing the user's consumption history and generating financial asset suggestions. This enables precise analysis based on individual posts and consumption behavior, and makes it possible to suggest occupations, activities, and financial plans optimized for each user.

[0266] An "information processing device" is a computer system used to collect and analyze digital information.

[0267] A "communication platform" is a foundation for exchanging information and messages online, which users use on a daily basis.

[0268] "Digital information" refers to all electronic data that users generate or collect on online platforms.

[0269] "Natural language processing technology" is a technology that enables computers to understand and process natural human language.

[0270] A "generative model" is a type of algorithm that learns patterns from vast amounts of data and generates new recommendations.

[0271] "User consumption history" refers to records of purchases and expenses made by a user.

[0272] "Financial asset recommendations" refer to investment and asset management recommendations based on the user's individual financial situation and actions.

[0273] This invention is a system that proposes the most suitable occupation and financial assets to a user through the collection and analysis of digital information. The server collects digital information from a communication platform with the user's consent and identifies its sentiment and subject matter using natural language processing technology. The terminal transmits the collected digital information to the server, which uses a generative model to create suggestions based on the analysis results. This makes it possible to analyze the user's consumption history and propose appropriate financial assets.

[0274] The server operates a system for collecting and processing data using programming languages ​​such as Python. Natural language processing techniques utilize NLP libraries and APIs. The generative model uses a neural network model that learns from large datasets and generates new recommendations. The final recommendations are displayed on the user's device using visualization tools.

[0275] For example, if a user has recently purchased many technology-related products, we might suggest a stock fund related to technology companies. In this way, detailed suggestions based on individual behavioral data become possible. An example of a prompt message is shown below.

[0276] "This user has recently purchased many technology-related products. Based on this trend, what investment products would you recommend? Please consider the generated answer and take market trends into account."

[0277] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0278] Step 1:

[0279] The terminal collects digital information after obtaining the user's consent from the communication platform. This information includes posts and purchase histories that reflect the user's daily activities and consumption behaviors. Since the collected information is difficult to analyze as it is, it is converted into an appropriate format and sent to the server. The input is the user's post data and purchase history, and the output is a data format that can be transferred to the server.

[0280] Step 2:

[0281] The server receives the digital information sent from the terminal and performs analysis using natural language processing technology. Specifically, it extracts emotions and themes from the text using an NLP library and organizes them as structured data. The input is the digital information received from the terminal, and the output is the emotion and theme information as the analysis result. Prepare to send this result to the generation model.

[0282] Step 3:

[0283] The server inputs the analysis result into the generation model and starts the process of recommending occupations and financial assets suitable for the individual. The generation model is a neural network that searches for a profile similar to the user from pre-learned data and generates an optimal recommendation. The input is the analysis result of natural language processing, and the output is the recommendation information for occupations and assets.

[0284] Step 4:

[0285] The server visualizes the generated recommendations and sends them to the terminal. The user can view the recommendations for occupations and financial assets suitable for themselves through a visual dashboard. The terminal receives this and displays it intuitively and clearly to the user. The input is the recommendation information from the generation model, and the output is the visualized information.

[0286] Step 5:

[0287] Users review the information presented on their devices and make decisions regarding their careers and investments. User feedback may be used to further improve the system. Input is the visualized information from the device, and output is the user's actions and feedback.

[0288] 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.

[0289] This invention is a system that combines an emotion engine that recognizes user emotions, thereby comprehensively analyzing user-generated data from communication platforms and using the results to recommend suitable occupations and activities to users.

[0290] The device collects posted data from the user's communication platform. Based on the user's consent, it can include not only text data but also audio and image data. This allows for the creation of richer datasets. The collected data is securely transmitted to the server.

[0291] The server analyzes the received data using natural language processing technology. In addition to conventional text analysis, it utilizes an emotion engine to analyze the emotions and nuances hidden within posts. This emotion engine detects not only the user's short-term emotional state but also their long-term emotional patterns, and generates analysis results that take both into account.

[0292] The analysis results are input into a generative model on the server and compared with known data related to specific occupations or activities. This generative model has been trained on classified occupational data and can recommend suitable occupations and activities to users based on their similarity to the posted data.

[0293] Based on the analysis, if suitable occupations or activities are recommended for the user, the server visualizes this information and sends it back to the terminal. The terminal displays the analysis results to the user using graphs, charts, etc., allowing the user to easily understand their own characteristics and potential.

[0294] For example, if a user frequently shares emotionally rich technical experiences or posts images and audio, the sentiment engine analyzes this to identify creative personality traits in the technical field. Based on this, a generative model recommends engineering and design jobs to the user, and the device displays this in a dashboard format.

[0295] This system allows users to understand their inner emotional characteristics through their own posts and better comprehend their career and activity options.

[0296] The following describes the processing flow.

[0297] Step 1:

[0298] The device accesses the user's communication platform account and collects posted data, including text, audio, and images, via an API. The collected data is sent to the server via a secure protocol.

[0299] Step 2:

[0300] The server cleanses and preprocesses the data it receives. This includes removing special characters and tokenizing text data, converting audio data to text using speech recognition technology, and extracting specific features from image data using an image recognition engine.

[0301] Step 3:

[0302] The server uses natural language processing technology to perform sentiment analysis on text data. Next, all data (text, voice, image) is integrated and analyzed using a sentiment engine to identify short-term and long-term sentiment patterns.

[0303] Step 4:

[0304] The server applies a generation model to match the aforementioned sentiment analysis results with other classified occupational data. Thereby, the similarity with the user's occupation and activities is evaluated and the suitability is identified.

[0305] Step 5:

[0306] The server generates recommendations for occupations and activities based on the analysis results and prepares visualization data for transmitting this to the terminal. The visualization data includes an explanation of the user's characteristics and the recommended occupations and suggestions.

[0307] Step 6:

[0308] The terminal displays the received visualization data to the user as a dashboard or report. Thereby, the user can understand in detail their emotional characteristics and the occupational suitability based thereon.

[0309] (Example 2)

[0310] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0311] It is a difficult task for users to find appropriate occupations and activities based on their emotional state and interests. In conventional methods, the collection and analysis of emotional data are limited, and it may not be possible to give optimal recommendations to users. Also, the protection of data privacy is an important issue.

[0312] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following respective means.

[0313] In this invention, the server includes means for collecting digital information from the user's digital communication infrastructure, means for analyzing the digital information using language analysis technology to extract emotional states and themes, means for recommending suitable occupations and activities to the user based on the analysis results using a generative AI model, and means for securely transmitting the digital information while protecting privacy. This enables users to find more appropriate occupations and activities based on their posts and emotional data.

[0314] A "digital communication infrastructure" is a system that enables the exchange of information between users via the internet and communication terminals.

[0315] "Digital information" refers to all data that users post to communication platforms, including text, audio, and images, expressed in digital format.

[0316] "Language analysis technology" is a technique that uses natural language processing to analyze text and audio data, and to analyze the meaning and emotions contained within them.

[0317] "Emotional state" refers to the emotions and moods of users at any given time, inferred from their posted data.

[0318] A "generative AI model" refers to an artificial intelligence algorithm that generates new data or makes recommendations based on a training dataset.

[0319] "Transmitting while protecting privacy" refers to a process that ensures data is securely transferred to the server without being leaked externally.

[0320] "Analyzing similarity" is the process of finding similarities between different datasets and evaluating their relationships.

[0321] "Other digital information categorized by occupation" refers to a collection of digital data organized based on an already categorized occupation directory.

[0322] This invention is a system that analyzes digital information collected from a user's digital communication infrastructure and recommends the most suitable occupation or activity for that user. This system is implemented using terminals and servers.

[0323] The device first collects various digital information, such as text, audio, and images, posted to the communication platform, with the user's consent. This process is carried out using dedicated data collection software, and the collected data is protected by encryption technology and transmitted to the server via a secure connection.

[0324] The server analyzes the received digital information using natural language processing techniques. This analysis process includes a text analysis engine and speech / image processing algorithms, and in particular, uses a generative AI model to derive emotional states and themes. The emotion engine detects short-term and long-term emotional patterns and generates detailed analysis results based on them.

[0325] The generative AI model receives the analysis results as input data and compares them with classification data related to occupations that it has already learned. This model is designed to suggest suitable occupations and activities for users and analyzes the similarity of information with high accuracy.

[0326] For example, if a user makes posts that are rich in emotion related to technology, the emotion engine analyzes them and identifies creative personality traits in that field. Based on this, the generative AI model can recommend engineering or design jobs.

[0327] A concrete example of a prompt might be the instruction, "Analyze tech-related posts that evoke rich emotions and recommend related professions."

[0328] This system allows users to understand their inner characteristics through their own posts and sentiment data, and to discover new possibilities for their careers and activities.

[0329] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0330] Step 1:

[0331] The terminal collects digital information in text, audio, and image formats from the user's digital communication infrastructure. The user must consent to this data collection. Input is user-submitted data, and output is a collected dataset. The terminal operates by launching a data collection program and targeting the necessary information.

[0332] Step 2:

[0333] The terminal encrypts the collected digital information and sends it to the server using a secure communication protocol. The input is the collected dataset, and the output is the encrypted transmission data. This operation ensures that the data is securely transferred to the server without being leaked externally.

[0334] Step 3:

[0335] The server begins analyzing the received digital information using a natural language processing engine. It decrypts encrypted data as input and analyzes text, audio, and image data. The output provides analysis results regarding emotions and themes. Specifically, the engine extracts keywords and emotion indicators from the data.

[0336] Step 4:

[0337] The server inputs the analyzed data into a generating AI model. This model evaluates the similarity of the analysis results to existing occupational data. The input is the analysis results of sentiment and themes, and the output is a list of recommended occupations and activities. The server's operation includes matching with existing databases and model training.

[0338] Step 5:

[0339] The server visualizes the generated occupation and activity recommendations and sends them to the terminal along with prompt messages. The input is recommendation data from the model, and the output is visualized recommendation information. Specifically, it generates graphs and charts.

[0340] Step 6:

[0341] The device displays the received visualization information to the user. The input is the visualized recommendation results, and the output is visual feedback to the user. The device displays graphs and charts on its screen, allowing the user to deepen their understanding of their own characteristics and recommended carriers.

[0342] (Application Example 2)

[0343] 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."

[0344] In today's information network environment, it is difficult for users to find the optimal products and activities that match their emotional state, and traditional recommendation systems have the challenge of not being able to provide personalized recommendations that reflect these emotional changes. Furthermore, from a privacy perspective, there is a need to provide effective recommendations while ensuring the security of user data.

[0345] 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.

[0346] In this invention, the server includes means for collecting data from a user's communication platform using an information processing device, means for analyzing the data using natural language processing technology to identify the sentiment and topic of the data, and means for recommending products or activities suitable for the user based on the analysis results using a generative model. This enables instantaneous analysis of the user's sentiment, highly accurate recommendations of products and activities that respond to changes, and effectively promotes the user's willingness to purchase.

[0347] An "information processing device" is a device used to collect and analyze data from a user's communication platform.

[0348] "Data" refers to information posted by users on a communication platform, including text, audio, and images.

[0349] "Natural language processing technology" is a technique that uses computers to analyze human language and extract specific meanings and emotions.

[0350] A "generative model" is a model that generates new information based on input data, and is used to recommend products and activities that are suitable for the user based on the analysis results.

[0351] "Emotions" refer to the mental state analyzed from users' posts and actions, and they influence users' preferences and purchasing behavior.

[0352] A "topic" refers to a theme or subject identified based on user-submitted data.

[0353] "Recommending a product or activity" means presenting highly relevant products or activities based on the user's emotional state and preferences.

[0354] "Visual display" refers to displaying analyzed data and recommended information on the screen using graphs, charts, and other visual aids.

[0355] "Security" refers to technical measures taken to prevent unauthorized access to and leakage of data, and to protect user privacy.

[0356] The system implementing this invention first collects data from the user's communication platform using an information processing device. The data includes text, audio, and image data, which are collected with the user's consent and transmitted to the server while ensuring security and protecting privacy. The server analyzes this data using natural language processing technology to identify the user's emotions and topics of conversation. Specifically, it uses Python and natural language processing libraries such as NLTK and spaCy to analyze the text.

[0357] By utilizing generative models, the server recommends products or activities suitable for the user based on these analysis results. These generative models employ machine learning libraries such as TensorFlow and PyTorch, comparing product classification data with the user's analyzed sentiment patterns to provide optimal recommendations based on similarity.

[0358] The server then visually displays these recommendations on the terminal to encourage the user's purchase. The terminal displays the analysis and recommendation results in the form of graphs and charts, allowing the user to easily understand the suggested products and activities.

[0359] For example, if a user posts "I want something fun today," the system can analyze this emotion and suggest entertainment-related products that match the user's interests. Another example of a prompt might be: "Build a system that analyzes the emotions of users based on their posts and recommends the most suitable products based on those emotions. Suggest relaxing products if the user is stressed, and celebratory products if they are happy."

[0360] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0361] Step 1:

[0362] The server collects data from the user's communication platform. It takes user-submitted text, audio, and image data as input and stores it securely. The server then converts this data into a format for analysis, preparing it for the next step.

[0363] Step 2:

[0364] The server analyzes the collected data using natural language processing techniques. The input is the data formatted in Step 1. The server uses Python and natural language processing libraries (NLTK and spaCy) to tokenize the text data and perform sentiment analysis. The output is the sentiment and topic extracted from the text.

[0365] Step 3:

[0366] The server uses a generative AI model to recommend products or activities based on the analysis results. The input is sentiment and topic information obtained in step 2. The server uses a generative model based on TensorFlow or PyTorch to calculate the similarity between the product database and the sentiment information. The output is a list of products suitable for the user.

[0367] Step 4:

[0368] The server visually displays recommended product information on the terminal. The input is the product list obtained in step 3. The server generates a graph or chart and sends it to the terminal via API for display on the screen in a format that is easy for the user to understand. The output is the product recommendations displayed on the user's screen.

[0369] Step 5:

[0370] The user reviews the information displayed on the device and considers the recommended products and activities. The input is the product information displayed on the device. The user performs purchase or search actions as needed and makes their own decisions based on the system's recommendations. The output is the next action based on the user's actions.

[0371] 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.

[0372] 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.

[0373] 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.

[0374] [Third Embodiment]

[0375] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0376] 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.

[0377] 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).

[0378] 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.

[0379] 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.

[0380] 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).

[0381] 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.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] 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.

[0386] 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".

[0387] This invention is a system that acquires posted data from users' communication platforms, analyzes it, and recommends suitable occupations and activities for the users. This system mainly consists of three main entities: terminals, servers, and users.

[0388] The device collects posted data from the communication platform based on user consent. The collected data is sent to a server and analyzed using natural language processing technology. Natural language processing technology is used to identify the sentiment and topic of the posts.

[0389] The server inputs the analysis results obtained from this process into a generative model, which compares the user's posted data with other datasets. The generative model learns the characteristics of various occupations and activities and identifies other users and occupations with similar posting patterns. Based on these comparison results, suitable occupations and activities for the user are identified.

[0390] The analysis results are sent from the server to the terminal and displayed visually to the user. This allows users to easily understand their own personality traits and aptitudes, and make decisions regarding their career and lifestyle.

[0391] As a concrete example, consider a user who frequently shares technology-related articles on social media and posts detailed descriptions of their own projects. In this case, natural language processing techniques are used to extract the technical orientation and creative thinking tendencies from the posts. The generative model can then recommend professions such as software developer or project manager, given these characteristics. This result is visually displayed on a dashboard, allowing the user to gain insights into their own aptitudes and potential.

[0392] This invention provides users with concrete tools to analyze their own posting patterns and deepen their self-understanding. This enables users to find the optimal career path for themselves and obtain information to achieve more fulfilling activities.

[0393] The following describes the processing flow.

[0394] Step 1:

[0395] The device accesses the user's communication platform account and collects posted data via an API. This data includes post content, posting date and time, hashtags, and the number of reactions. The device securely transmits this data to the server.

[0396] Step 2:

[0397] The server preprocesses the received data. Specifically, the server cleanses the text data, removing special characters and emojis, and eliminating unnecessary spaces. Next, the server tokenizes the text, preparing it for analysis.

[0398] Step 3:

[0399] The server applies natural language processing techniques to perform sentiment analysis on text data. The server categorizes the content of posts into positive, negative, and neutral sentiment categories. Furthermore, topic modeling is used to extract the themes of the posts and identify the user's interests.

[0400] Step 4:

[0401] The server uses a generative model to compare the user's analysis results with other data. The server matches them against occupation lists and known patterns to identify occupations and activities similar to the user.

[0402] Step 5:

[0403] The server compiles the analysis results and selects recommended occupations and activities for the user. Next, the server visually organizes the results and sends the data to the user's terminal in an easy-to-understand format.

[0404] Step 6:

[0405] Based on the data received by the device, the results are displayed to the user in the form of a dashboard or report. Based on these results, the user can deepen their self-understanding and consider a career path that suits them.

[0406] (Example 1)

[0407] 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."

[0408] In today's world, it is difficult for users to identify appropriate occupations and activities based on their own submitted data and find the career path that best suits them. Furthermore, analyzing submitted data and recommending occupations requires advanced technology, and there is a need for efficient methods to perform these tasks. In addition, security during the data collection process is essential for protecting personal information.

[0409] 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.

[0410] In this invention, the server includes means for collecting information posted from a user information exchange platform, means for analyzing the posted information using natural language processing techniques to identify emotions and themes, and means for suggesting appropriate occupations and activities from the analysis results using a generative model. This makes it possible for users to easily find occupations and activities that are best suited to them, thereby deepening their self-awareness.

[0411] An "information processing device" is a mechanical or electronic device that has the function of collecting, analyzing, and processing data.

[0412] An "information exchange platform" is an online platform used by users to post, share, and exchange information.

[0413] "Posted information" refers to all content, such as text, images, and videos, that users transmit through the information exchange platform.

[0414] "Natural language processing techniques" are technologies that use computers to analyze and understand human language, and are particularly used for detecting emotions and themes.

[0415] "Emotion and subject matter" refers to the emotional tone and main topic contained in the posted information.

[0416] A "generative model" is a machine learning model used to learn patterns from data and generate new information or suggestions.

[0417] "Appropriate occupation or activity" refers to the occupation or life activity that best suits the user, based on their posting patterns and analysis results.

[0418] "Personal confidentiality" refers to a state in which users' personal information is protected from being leaked to external parties.

[0419] This invention is an information processing system aimed at enabling users to make optimal choices regarding their careers and lifestyles based on their activities on an information exchange platform. This system mainly consists of three components: a terminal, a server, and a user, each playing a specific role.

[0420] The device plays the role of collecting information posted from the information exchange platform with the user's consent. This collection utilizes secure communication methods, such as the HTTPS protocol, to safely protect the information. This ensures the confidentiality of the user's personal information.

[0421] The server analyzes the information received from the terminal based on natural language processing (NLP) techniques. These techniques utilize libraries such as SpaCy and NLTK. Through this analysis, the server identifies the sentiment and theme of the posted information and inputs the data into a generative model based on this information.

[0422] The generative model uses pre-trained machine learning algorithms to suggest appropriate occupations and activities from user posts. By comparing posts from other users, the model provides recommendations that match the user's interests and skills. For example, a user who frequently posts technical content can be recommended technical occupations.

[0423] Ultimately, the recommendations are sent from the server to the user's device and displayed visually. Through the dashboard, users can gain insights into their aptitudes and potential. For example, a user might receive a prompt such as, "Which programming language should I learn to benefit my career?" This allows users to take concrete actions toward career development and lifestyle improvement.

[0424] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0425] Step 1:

[0426] The device collects information posted from the information exchange platform with the user's consent. The input consists of posts made by the user on the platform, and the output is stored on the device as raw data. At this stage, a secure protocol is used to ensure the security of the information.

[0427] Step 2:

[0428] The terminal transfers the collected posted data to the server. The input is the raw data stored on the terminal, and the output is the data sent to the server. This transfer involves specific actions to ensure data security by using the HTTPS protocol.

[0429] Step 3:

[0430] The server analyzes the received data using natural language processing techniques. Raw data is sent to the server as input, and sentiment and topic identification are performed on this data. After this analysis, data with the characteristics of the analyzed sentiment and topic is obtained as output. Specifically, sentiment analysis and keyword extraction are used.

[0431] Step 4:

[0432] The server inputs results from natural language processing techniques into an AI model that recommends suitable occupations and activities for the user. The input is the analysis results, which are compared with the model's training data to generate a list of appropriate occupations and activities as output. Specifically, the model compares and analyzes posting patterns and evaluates similarity.

[0433] Step 5:

[0434] The server sends the generated recommendation list to the terminal. The input is the recommendation list created on the server, and the output is the data sent to the terminal. Here again, a secure method is used for transferring information.

[0435] Step 6:

[0436] The device visually displays a list of recommendations received from the server to the user. The input is received data, and the output is visualized information on the user's dashboard. Based on this information, the user can consider specific carrier choices and lifestyle improvements.

[0437] (Application Example 1)

[0438] 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."

[0439] In recent years, many people have been using communication platforms to share their daily activities and opinions. However, there is a lack of effective means to analyze this information and provide personalized recommendations for suitable occupations, activities, and even financial assets. In particular, it is difficult to systematically analyze consumer behavior data and utilize it as useful investment information. Against this backdrop, there is a need to provide personalized recommendations tailored to individual needs using user behavior data.

[0440] 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.

[0441] In this invention, the server includes means for collecting digital information using an information processing device, means for identifying the sentiment and subject matter of the digital information using natural language processing technology, means for recommending occupations and activities suitable for the individual using a generative model, and means for analyzing the user's consumption history and generating financial asset suggestions. This enables precise analysis based on individual posts and consumption behavior, and makes it possible to suggest occupations, activities, and financial plans optimized for each user.

[0442] An "information processing device" is a computer system used to collect and analyze digital information.

[0443] A "communication platform" is a foundation for exchanging information and messages online, which users use on a daily basis.

[0444] "Digital information" refers to all electronic data that users generate or collect on online platforms.

[0445] "Natural language processing technology" is a technology that enables computers to understand and process natural human language.

[0446] A "generative model" is a type of algorithm that learns patterns from vast amounts of data and generates new recommendations.

[0447] "User consumption history" refers to records of purchases and expenses made by a user.

[0448] "Financial asset recommendations" refer to investment and asset management recommendations based on the user's individual financial situation and actions.

[0449] This invention is a system that proposes the most suitable occupation and financial assets to a user through the collection and analysis of digital information. The server collects digital information from a communication platform with the user's consent and identifies its sentiment and subject matter using natural language processing technology. The terminal transmits the collected digital information to the server, which uses a generative model to create suggestions based on the analysis results. This makes it possible to analyze the user's consumption history and propose appropriate financial assets.

[0450] The server operates a system for collecting and processing data using programming languages ​​such as Python. Natural language processing techniques utilize NLP libraries and APIs. The generative model uses a neural network model that learns from large datasets and generates new recommendations. The final recommendations are displayed on the user's device using visualization tools.

[0451] For example, if a user has recently purchased many technology-related products, we might suggest a stock fund related to technology companies. In this way, detailed suggestions based on individual behavioral data become possible. An example of a prompt message is shown below.

[0452] "This user has recently purchased many technology-related products. Based on this trend, what investment products would you recommend? Please consider the generated answer and take market trends into account."

[0453] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0454] Step 1:

[0455] The device collects digital information from the communication platform with the user's consent. This information includes posts and purchase history that reflect the user's daily activities and consumption behavior. Because the collected information is difficult to analyze directly, it is converted into an appropriate format and sent to the server. The input is user posts and purchase history, and the output is a data format that can be transferred to the server.

[0456] Step 2:

[0457] The server receives digital information transmitted from the terminal and performs analysis using natural language processing (NLP) techniques. Specifically, it extracts sentiment and themes from text using an NLP library and organizes them as structured data. The input is the digital information received from the terminal, and the output is the sentiment and theme information as a result of the analysis. This result is then prepared for transmission to a generative model.

[0458] Step 3:

[0459] The server inputs the analysis results into a generative model and initiates a process to recommend suitable occupations and financial assets for the individual. The generative model is a neural network that searches for user-like profiles from pre-trained data and generates optimal suggestions. The input is the analysis results of natural language processing, and the output is recommended information on occupations and assets.

[0460] Step 4:

[0461] The server visualizes the generated suggestions and sends them to the terminal. The user can then view the suggested occupations and financial assets suitable for them through a visual dashboard. The terminal receives this information and displays it to the user in an intuitive and easy-to-understand manner. The input is the recommendations from the generative model, and the output is the visualized information.

[0462] Step 5:

[0463] Users review the information presented on their devices and make decisions regarding their careers and investments. User feedback may be used to further improve the system. Input is the visualized information from the device, and output is the user's actions and feedback.

[0464] 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.

[0465] This invention is a system that combines an emotion engine that recognizes user emotions, thereby comprehensively analyzing user-generated data from communication platforms and using the results to recommend suitable occupations and activities to users.

[0466] The device collects posted data from the user's communication platform. Based on the user's consent, it can include not only text data but also audio and image data. This allows for the creation of richer datasets. The collected data is securely transmitted to the server.

[0467] The server analyzes the received data using natural language processing technology. In addition to conventional text analysis, it utilizes an emotion engine to analyze the emotions and nuances hidden within posts. This emotion engine detects not only the user's short-term emotional state but also their long-term emotional patterns, and generates analysis results that take both into account.

[0468] The analysis results are input into a generative model on the server and compared with known data related to specific occupations or activities. This generative model has been trained on classified occupational data and can recommend suitable occupations and activities to users based on their similarity to the posted data.

[0469] Based on the analysis, if suitable occupations or activities are recommended for the user, the server visualizes this information and sends it back to the terminal. The terminal displays the analysis results to the user using graphs, charts, etc., allowing the user to easily understand their own characteristics and potential.

[0470] For example, if a user frequently shares emotionally rich technical experiences or posts images and audio, the sentiment engine analyzes this to identify creative personality traits in the technical field. Based on this, a generative model recommends engineering and design jobs to the user, and the device displays this in a dashboard format.

[0471] This system allows users to understand their inner emotional characteristics through their own posts and better comprehend their career and activity options.

[0472] The following describes the processing flow.

[0473] Step 1:

[0474] The device accesses the user's communication platform account and collects posted data, including text, audio, and images, via an API. The collected data is sent to the server via a secure protocol.

[0475] Step 2:

[0476] The server cleanses and preprocesses the data it receives. This includes removing special characters and tokenizing text data, converting audio data to text using speech recognition technology, and extracting specific features from image data using an image recognition engine.

[0477] Step 3:

[0478] The server uses natural language processing techniques to perform sentiment analysis on text data. Next, it uses a sentiment engine to integrate and analyze all data (text, audio, and images) to identify short-term and long-term sentiment patterns.

[0479] Step 4:

[0480] The server applies a generative model and compares the aforementioned sentiment analysis results with other categorized occupational data. This allows it to evaluate the similarity to the user's occupation and activities and identify their suitability.

[0481] Step 5:

[0482] The server generates occupation and activity recommendations based on the analysis results and prepares visualization data to send to the terminal. The visualization data includes a description of the user's characteristics and recommended occupations and suggestions.

[0483] Step 6:

[0484] The device displays the received visualization data to the user as a dashboard or report. This allows the user to gain a detailed understanding of their emotional characteristics and the resulting career aptitudes.

[0485] (Example 2)

[0486] 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."

[0487] Finding suitable occupations and activities based on one's emotional state and interests is a challenging task. Traditional methods have limited emotional data collection and analysis capabilities, sometimes failing to provide optimal recommendations to users. Protecting data privacy is also a critical issue.

[0488] 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.

[0489] In this invention, the server includes means for collecting digital information from the user's digital communication infrastructure, means for analyzing the digital information using language analysis technology to extract emotional states and themes, means for recommending suitable occupations and activities to the user based on the analysis results using a generative AI model, and means for securely transmitting the digital information while protecting privacy. This enables users to find more appropriate occupations and activities based on their posts and emotional data.

[0490] A "digital communication infrastructure" is a system that enables the exchange of information between users via the internet and communication terminals.

[0491] "Digital information" refers to all data that users post to communication platforms, including text, audio, and images, expressed in digital format.

[0492] "Language analysis technology" is a technique that uses natural language processing to analyze text and audio data, and to analyze the meaning and emotions contained within them.

[0493] "Emotional state" refers to the emotions and moods of users at any given time, inferred from their posted data.

[0494] A "generative AI model" refers to an artificial intelligence algorithm that generates new data or makes recommendations based on a training dataset.

[0495] "Transmitting while protecting privacy" refers to a process that ensures data is securely transferred to the server without being leaked externally.

[0496] "Analyzing similarity" is the process of finding similarities between different datasets and evaluating their relationships.

[0497] "Other digital information categorized by occupation" refers to a collection of digital data organized based on an already categorized occupation directory.

[0498] This invention is a system that analyzes digital information collected from a user's digital communication infrastructure and recommends the most suitable occupation or activity for that user. This system is implemented using terminals and servers.

[0499] The device first collects various digital information, such as text, audio, and images, posted to the communication platform, with the user's consent. This process is carried out using dedicated data collection software, and the collected data is protected by encryption technology and transmitted to the server via a secure connection.

[0500] The server analyzes the received digital information using natural language processing techniques. This analysis process includes a text analysis engine and speech / image processing algorithms, and in particular, uses a generative AI model to derive emotional states and themes. The emotion engine detects short-term and long-term emotional patterns and generates detailed analysis results based on them.

[0501] The generative AI model receives the analysis results as input data and compares them with classification data related to occupations that it has already learned. This model is designed to suggest suitable occupations and activities for users and analyzes the similarity of information with high accuracy.

[0502] For example, if a user makes posts that are rich in emotion related to technology, the emotion engine analyzes them and identifies creative personality traits in that field. Based on this, the generative AI model can recommend engineering or design jobs.

[0503] A concrete example of a prompt might be the instruction, "Analyze tech-related posts that evoke rich emotions and recommend related professions."

[0504] This system allows users to understand their inner characteristics through their own posts and sentiment data, and to discover new possibilities for their careers and activities.

[0505] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0506] Step 1:

[0507] The terminal collects digital information in text, audio, and image formats from the user's digital communication infrastructure. The user must consent to this data collection. Input is user-submitted data, and output is a collected dataset. The terminal operates by launching a data collection program and targeting the necessary information.

[0508] Step 2:

[0509] The terminal encrypts the collected digital information and sends it to the server using a secure communication protocol. The input is the collected dataset, and the output is the encrypted transmission data. This operation ensures that the data is securely transferred to the server without being leaked externally.

[0510] Step 3:

[0511] The server begins analyzing the received digital information using a natural language processing engine. It decrypts encrypted data as input and analyzes text, audio, and image data. The output provides analysis results regarding emotions and themes. Specifically, the engine extracts keywords and emotion indicators from the data.

[0512] Step 4:

[0513] The server inputs the analyzed data into a generating AI model. This model evaluates the similarity of the analysis results to existing occupational data. The input is the analysis results of sentiment and themes, and the output is a list of recommended occupations and activities. The server's operation includes matching with existing databases and model training.

[0514] Step 5:

[0515] The server visualizes the generated occupation and activity recommendations and sends them to the terminal along with prompt messages. The input is recommendation data from the model, and the output is visualized recommendation information. Specifically, it generates graphs and charts.

[0516] Step 6:

[0517] The device displays the received visualization information to the user. The input is the visualized recommendation results, and the output is visual feedback to the user. The device displays graphs and charts on its screen, allowing the user to deepen their understanding of their own characteristics and recommended carriers.

[0518] (Application Example 2)

[0519] 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."

[0520] In today's information network environment, it is difficult for users to find the optimal products and activities that match their emotional state, and traditional recommendation systems have the challenge of not being able to provide personalized recommendations that reflect these emotional changes. Furthermore, from a privacy perspective, there is a need to provide effective recommendations while ensuring the security of user data.

[0521] 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.

[0522] In this invention, the server includes means for collecting data from a user's communication platform using an information processing device, means for analyzing the data using natural language processing technology to identify the sentiment and topic of the data, and means for recommending products or activities suitable for the user based on the analysis results using a generative model. This enables instantaneous analysis of the user's sentiment, highly accurate recommendations of products and activities that respond to changes, and effectively promotes the user's willingness to purchase.

[0523] An "information processing device" is a device used to collect and analyze data from a user's communication platform.

[0524] "Data" refers to information posted by users on a communication platform, including text, audio, and images.

[0525] "Natural language processing technology" is a technique that uses computers to analyze human language and extract specific meanings and emotions.

[0526] A "generative model" is a model that generates new information based on input data, and is used to recommend products and activities that are suitable for the user based on the analysis results.

[0527] "Emotions" refer to the mental state analyzed from users' posts and actions, and they influence users' preferences and purchasing behavior.

[0528] A "topic" refers to a theme or subject identified based on user-submitted data.

[0529] "Recommending a product or activity" means presenting highly relevant products or activities based on the user's emotional state and preferences.

[0530] "Visual display" refers to displaying analyzed data and recommended information on the screen using graphs, charts, and other visual aids.

[0531] "Security" refers to technical measures taken to prevent unauthorized access to and leakage of data, and to protect user privacy.

[0532] The system implementing this invention first collects data from the user's communication platform using an information processing device. The data includes text, audio, and image data, which are collected with the user's consent and transmitted to the server while ensuring security and protecting privacy. The server analyzes this data using natural language processing technology to identify the user's emotions and topics of conversation. Specifically, it uses Python and natural language processing libraries such as NLTK and spaCy to analyze the text.

[0533] By utilizing generative models, the server recommends products or activities suitable for the user based on these analysis results. These generative models employ machine learning libraries such as TensorFlow and PyTorch, comparing product classification data with the user's analyzed sentiment patterns to provide optimal recommendations based on similarity.

[0534] The server then visually displays these recommendations on the terminal to encourage the user's purchase. The terminal displays the analysis and recommendation results in the form of graphs and charts, allowing the user to easily understand the suggested products and activities.

[0535] For example, if a user posts "I want something fun today," the system can analyze this emotion and suggest entertainment-related products that match the user's interests. Another example of a prompt might be: "Build a system that analyzes the emotions of users based on their posts and recommends the most suitable products based on those emotions. Suggest relaxing products if the user is stressed, and celebratory products if they are happy."

[0536] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0537] Step 1:

[0538] The server collects data from the user's communication platform. It takes user-submitted text, audio, and image data as input and stores it securely. The server then converts this data into a format for analysis, preparing it for the next step.

[0539] Step 2:

[0540] The server analyzes the collected data using natural language processing techniques. The input is the data formatted in Step 1. The server uses Python and natural language processing libraries (NLTK and spaCy) to tokenize the text data and perform sentiment analysis. The output is the sentiment and topic extracted from the text.

[0541] Step 3:

[0542] The server uses a generative AI model to recommend products or activities based on the analysis results. The input is sentiment and topic information obtained in step 2. The server uses a generative model based on TensorFlow or PyTorch to calculate the similarity between the product database and the sentiment information. The output is a list of products suitable for the user.

[0543] Step 4:

[0544] The server visually displays recommended product information on the terminal. The input is the product list obtained in step 3. The server generates a graph or chart and sends it to the terminal via API for display on the screen in a format that is easy for the user to understand. The output is the product recommendations displayed on the user's screen.

[0545] Step 5:

[0546] The user reviews the information displayed on the device and considers the recommended products and activities. The input is the product information displayed on the device. The user performs purchase or search actions as needed and makes their own decisions based on the system's recommendations. The output is the next action based on the user's actions.

[0547] 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.

[0548] 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.

[0549] 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.

[0550] [Fourth Embodiment]

[0551] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0552] 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.

[0553] 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).

[0554] 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.

[0555] 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.

[0556] 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).

[0557] 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.

[0558] 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.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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".

[0564] This invention is a system that acquires posted data from users' communication platforms, analyzes it, and recommends suitable occupations and activities for the users. This system mainly consists of three main entities: terminals, servers, and users.

[0565] The device collects posted data from the communication platform based on user consent. The collected data is sent to a server and analyzed using natural language processing technology. Natural language processing technology is used to identify the sentiment and topic of the posts.

[0566] The server inputs the analysis results obtained from this process into a generative model, which compares the user's posted data with other datasets. The generative model learns the characteristics of various occupations and activities and identifies other users and occupations with similar posting patterns. Based on these comparison results, suitable occupations and activities for the user are identified.

[0567] The analysis results are sent from the server to the terminal and displayed visually to the user. This allows users to easily understand their own personality traits and aptitudes, and make decisions regarding their career and lifestyle.

[0568] As a concrete example, consider a user who frequently shares technology-related articles on social media and posts detailed descriptions of their own projects. In this case, natural language processing techniques are used to extract the technical orientation and creative thinking tendencies from the posts. The generative model can then recommend professions such as software developer or project manager, given these characteristics. This result is visually displayed on a dashboard, allowing the user to gain insights into their own aptitudes and potential.

[0569] This invention provides users with concrete tools to analyze their own posting patterns and deepen their self-understanding. This enables users to find the optimal career path for themselves and obtain information to achieve more fulfilling activities.

[0570] The following describes the processing flow.

[0571] Step 1:

[0572] The device accesses the user's communication platform account and collects posted data via an API. This data includes post content, posting date and time, hashtags, and the number of reactions. The device securely transmits this data to the server.

[0573] Step 2:

[0574] The server preprocesses the data it receives. Specifically, the server cleanses the text data, removing special characters and emojis, and eliminating unnecessary spaces. Next, the server tokenizes the text, preparing it for analysis.

[0575] Step 3:

[0576] The server applies natural language processing techniques to perform sentiment analysis on text data. The server classifies the content of posts into positive, negative, and neutral sentiment categories. Furthermore, topic modeling is used to extract the themes of the posts and identify the users' interests.

[0577] Step 4:

[0578] The server uses a generative model to compare the user's analysis results with other data. The server matches them against occupational lists and known patterns to identify occupations and activities similar to the user.

[0579] Step 5:

[0580] The server compiles the analysis results and selects recommended occupations and activities for the user. Next, the server visually organizes the results and sends the data to the user's terminal in an easy-to-understand format.

[0581] Step 6:

[0582] Based on the data received by the device, the results are displayed to the user in the form of a dashboard or report. Based on these results, the user can deepen their self-understanding and consider a career path that suits them.

[0583] (Example 1)

[0584] 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".

[0585] In today's world, it is difficult for users to identify appropriate occupations and activities based on their own submitted data and find the career path that best suits them. Furthermore, analyzing submitted data and recommending occupations requires advanced technology, and there is a need for efficient methods to perform these tasks. In addition, security during the data collection process is essential for protecting personal information.

[0586] 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.

[0587] In this invention, the server includes means for collecting information posted from a user information exchange platform, means for analyzing the posted information using natural language processing techniques to identify emotions and themes, and means for suggesting appropriate occupations and activities from the analysis results using a generative model. This makes it possible for users to easily find occupations and activities that are best suited to them, thereby deepening their self-awareness.

[0588] An "information processing device" is a mechanical or electronic device that has the function of collecting, analyzing, and processing data.

[0589] An "information exchange platform" is an online platform used by users to post, share, and exchange information.

[0590] "Posted information" refers to all content, such as text, images, and videos, that users transmit through the information exchange platform.

[0591] "Natural language processing techniques" are technologies that use computers to analyze and understand human language, and are particularly used for detecting emotions and themes.

[0592] "Emotion and subject matter" refers to the emotional tone and main topic contained in the posted information.

[0593] A "generative model" is a machine learning model used to learn patterns from data and generate new information or suggestions.

[0594] "Appropriate occupation or activity" refers to the occupation or life activity that best suits the user, based on their posting patterns and analysis results.

[0595] "Personal confidentiality" refers to a state in which users' personal information is protected from being leaked to external parties.

[0596] This invention is an information processing system aimed at enabling users to make optimal choices regarding their careers and lifestyles based on their activities on an information exchange platform. This system mainly consists of three components: a terminal, a server, and a user, each playing a specific role.

[0597] The device plays the role of collecting information posted from the information exchange platform with the user's consent. This collection utilizes secure communication methods, such as the HTTPS protocol, to safely protect the information. This ensures the confidentiality of the user's personal information.

[0598] The server analyzes the information received from the terminal based on natural language processing (NLP) techniques. These techniques utilize libraries such as SpaCy and NLTK. Through this analysis, the server identifies the sentiment and theme of the posted information and inputs the data into a generative model based on this information.

[0599] The generative model uses pre-trained machine learning algorithms to suggest appropriate occupations and activities from user posts. By comparing posts from other users, the model provides recommendations that match the user's interests and skills. For example, a user who frequently posts technical content can be recommended technical occupations.

[0600] Ultimately, the recommendations are sent from the server to the user's device and displayed visually. Through the dashboard, users can gain insights into their aptitudes and potential. For example, a user might receive a prompt such as, "Which programming language should I learn to benefit my career?" This allows users to take concrete actions toward career development and lifestyle improvement.

[0601] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0602] Step 1:

[0603] The device collects information posted from the information exchange platform with the user's consent. The input consists of posts made by the user on the platform, and the output is stored on the device as raw data. At this stage, a secure protocol is used to ensure the security of the information.

[0604] Step 2:

[0605] The terminal transfers the collected posted data to the server. The input is the raw data stored on the terminal, and the output is the data sent to the server. This transfer involves specific actions to ensure data security by using the HTTPS protocol.

[0606] Step 3:

[0607] The server analyzes the received data using natural language processing techniques. Raw data is sent to the server as input, and sentiment and topic identification are performed on this data. After this analysis, data with the characteristics of the analyzed sentiment and topic is obtained as output. Specifically, sentiment analysis and keyword extraction are used.

[0608] Step 4:

[0609] The server inputs results from natural language processing techniques into an AI model that recommends suitable occupations and activities for the user. The input is the analysis results, which are compared with the model's training data to generate a list of appropriate occupations and activities as output. Specifically, the model compares and analyzes posting patterns and evaluates similarity.

[0610] Step 5:

[0611] The server sends the generated recommendation list to the terminal. The input is the recommendation list created on the server, and the output is the data sent to the terminal. Here again, a secure method is used for transferring information.

[0612] Step 6:

[0613] The device visually displays a list of recommendations received from the server to the user. The input is received data, and the output is visualized information on the user's dashboard. Based on this information, the user can consider specific carrier choices and lifestyle improvements.

[0614] (Application Example 1)

[0615] 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".

[0616] In recent years, many people have been using communication platforms to share their daily activities and opinions. However, there is a lack of effective means to analyze this information and provide personalized recommendations for suitable occupations, activities, and even financial assets. In particular, it is difficult to systematically analyze consumer behavior data and utilize it as useful investment information. Against this backdrop, there is a need to provide personalized recommendations tailored to individual needs using user behavior data.

[0617] 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.

[0618] In this invention, the server includes means for collecting digital information using an information processing device, means for identifying the sentiment and subject matter of the digital information using natural language processing technology, means for recommending occupations and activities suitable for the individual using a generative model, and means for analyzing the user's consumption history and generating financial asset suggestions. This enables precise analysis based on individual posts and consumption behavior, and makes it possible to suggest occupations, activities, and financial plans optimized for each user.

[0619] An "information processing device" is a computer system used to collect and analyze digital information.

[0620] A "communication platform" is a foundation for exchanging information and messages online, which users use on a daily basis.

[0621] "Digital information" refers to all electronic data that users generate or collect on online platforms.

[0622] "Natural language processing technology" is a technology that enables computers to understand and process natural human language.

[0623] A "generative model" is a type of algorithm that learns patterns from vast amounts of data and generates new recommendations.

[0624] "User consumption history" refers to records of purchases and expenses made by a user.

[0625] "Financial asset recommendations" refer to investment and asset management recommendations based on the user's individual financial situation and actions.

[0626] This invention is a system that proposes the most suitable occupation and financial assets to a user through the collection and analysis of digital information. The server collects digital information from a communication platform with the user's consent and identifies its sentiment and subject matter using natural language processing technology. The terminal transmits the collected digital information to the server, which uses a generative model to create suggestions based on the analysis results. This makes it possible to analyze the user's consumption history and propose appropriate financial assets.

[0627] The server operates a system for collecting and processing data using programming languages ​​such as Python. Natural language processing techniques utilize NLP libraries and APIs. The generative model uses a neural network model that learns from large datasets and generates new recommendations. The final recommendations are displayed on the user's device using visualization tools.

[0628] For example, if a user has recently purchased many technology-related products, we might suggest a stock fund related to technology companies. In this way, detailed suggestions based on individual behavioral data become possible. An example of a prompt message is shown below.

[0629] "This user has recently purchased many technology-related products. Based on this trend, what investment products would you recommend? Please consider the generated answer and take market trends into account."

[0630] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0631] Step 1:

[0632] The device collects digital information from the communication platform with the user's consent. This information includes posts and purchase history that reflect the user's daily activities and consumption behavior. Because the collected information is difficult to analyze directly, it is converted into an appropriate format and sent to the server. The input is user posts and purchase history, and the output is a data format that can be transferred to the server.

[0633] Step 2:

[0634] The server receives digital information transmitted from the terminal and performs analysis using natural language processing (NLP) techniques. Specifically, it extracts sentiment and themes from text using an NLP library and organizes them as structured data. The input is the digital information received from the terminal, and the output is the sentiment and theme information as a result of the analysis. This result is then prepared for transmission to a generative model.

[0635] Step 3:

[0636] The server inputs the analysis results into a generative model and initiates a process to recommend suitable occupations and financial assets for the individual. The generative model is a neural network that searches for user-like profiles from pre-trained data and generates optimal suggestions. The input is the analysis results of natural language processing, and the output is recommended information on occupations and assets.

[0637] Step 4:

[0638] The server visualizes the generated suggestions and sends them to the terminal. The user can then view the suggested occupations and financial assets suitable for them through a visual dashboard. The terminal receives this information and displays it to the user in an intuitive and easy-to-understand manner. The input is the recommendations from the generative model, and the output is the visualized information.

[0639] Step 5:

[0640] Users review the information presented on their devices and make decisions regarding their careers and investments. User feedback may be used to further improve the system. Input is the visualized information from the device, and output is the user's actions and feedback.

[0641] 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.

[0642] This invention is a system that combines an emotion engine that recognizes user emotions, thereby comprehensively analyzing user-generated data from communication platforms and using the results to recommend suitable occupations and activities to users.

[0643] The device collects posted data from the user's communication platform. Based on the user's consent, it can include not only text data but also audio and image data. This allows for the creation of richer datasets. The collected data is securely transmitted to the server.

[0644] The server analyzes the received data using natural language processing technology. In addition to conventional text analysis, it utilizes an emotion engine to analyze the emotions and nuances hidden within posts. This emotion engine detects not only the user's short-term emotional state but also their long-term emotional patterns, and generates analysis results that take both into account.

[0645] The analysis results are input into a generative model on the server and compared with known data related to specific occupations or activities. This generative model has been trained on classified occupational data and can recommend suitable occupations and activities to users based on their similarity to the posted data.

[0646] Based on the analysis, if suitable occupations or activities are recommended for the user, the server visualizes this information and sends it back to the terminal. The terminal displays the analysis results to the user using graphs, charts, etc., allowing the user to easily understand their own characteristics and potential.

[0647] For example, if a user frequently shares emotionally rich technical experiences or posts images and audio, the sentiment engine analyzes this to identify creative personality traits in the technical field. Based on this, a generative model recommends engineering and design jobs to the user, and the device displays this in a dashboard format.

[0648] This system allows users to understand their inner emotional characteristics through their own posts and better comprehend their career and activity options.

[0649] The following describes the processing flow.

[0650] Step 1:

[0651] The device accesses the user's communication platform account and collects posted data, including text, audio, and images, via an API. The collected data is sent to the server via a secure protocol.

[0652] Step 2:

[0653] The server cleanses and preprocesses the data it receives. This includes removing special characters and tokenizing text data, converting audio data to text using speech recognition technology, and extracting specific features from image data using an image recognition engine.

[0654] Step 3:

[0655] The server uses natural language processing techniques to perform sentiment analysis on text data. Next, it uses a sentiment engine to integrate and analyze all data (text, audio, and images) to identify short-term and long-term sentiment patterns.

[0656] Step 4:

[0657] The server applies a generative model and compares the aforementioned sentiment analysis results with other categorized occupational data. This allows it to evaluate the similarity to the user's occupation and activities and identify their suitability.

[0658] Step 5:

[0659] The server generates occupation and activity recommendations based on the analysis results and prepares visualization data to send to the terminal. The visualization data includes a description of the user's characteristics and recommended occupations and suggestions.

[0660] Step 6:

[0661] The device displays the received visualization data to the user as a dashboard or report. This allows the user to gain a detailed understanding of their emotional characteristics and the resulting career aptitudes.

[0662] (Example 2)

[0663] 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".

[0664] Finding suitable occupations and activities based on one's emotional state and interests is a challenging task. Traditional methods have limited emotional data collection and analysis capabilities, sometimes failing to provide optimal recommendations to users. Protecting data privacy is also a critical issue.

[0665] 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.

[0666] In this invention, the server includes means for collecting digital information from the user's digital communication infrastructure, means for analyzing the digital information using language analysis technology to extract emotional states and themes, means for recommending suitable occupations and activities to the user based on the analysis results using a generative AI model, and means for securely transmitting the digital information while protecting privacy. This enables users to find more appropriate occupations and activities based on their posts and emotional data.

[0667] A "digital communication infrastructure" is a system that enables the exchange of information between users via the internet and communication terminals.

[0668] "Digital information" refers to all data that users post to communication platforms, including text, audio, and images, expressed in digital format.

[0669] "Language analysis technology" is a technique that uses natural language processing to analyze text and audio data, and to analyze the meaning and emotions contained within them.

[0670] "Emotional state" refers to the emotions and moods of users at any given time, inferred from their posted data.

[0671] A "generative AI model" refers to an artificial intelligence algorithm that generates new data or makes recommendations based on a training dataset.

[0672] "Transmitting while protecting privacy" refers to a process that ensures data is securely transferred to the server without being leaked externally.

[0673] "Analyzing similarity" is the process of finding similarities between different datasets and evaluating their relationships.

[0674] "Other digital information categorized by occupation" refers to a collection of digital data organized based on an already categorized occupation directory.

[0675] This invention is a system that analyzes digital information collected from a user's digital communication infrastructure and recommends the most suitable occupation or activity for that user. This system is implemented using terminals and servers.

[0676] The device first collects various digital information, such as text, audio, and images, posted to the communication platform, with the user's consent. This process is carried out using dedicated data collection software, and the collected data is protected by encryption technology and transmitted to the server via a secure connection.

[0677] The server analyzes the received digital information using natural language processing techniques. This analysis process includes a text analysis engine and speech / image processing algorithms, and in particular, uses a generative AI model to derive emotional states and themes. The emotion engine detects short-term and long-term emotional patterns and generates detailed analysis results based on them.

[0678] The generative AI model receives the analysis results as input data and compares them with classification data related to occupations that it has already learned. This model is designed to suggest suitable occupations and activities for users and analyzes the similarity of information with high accuracy.

[0679] For example, if a user makes posts that are rich in emotion related to technology, the emotion engine analyzes them and identifies creative personality traits in that field. Based on this, the generative AI model can recommend engineering or design jobs.

[0680] A concrete example of a prompt might be the instruction, "Analyze tech-related posts that evoke rich emotions and recommend related professions."

[0681] This system allows users to understand their inner characteristics through their own posts and sentiment data, and to discover new possibilities for their careers and activities.

[0682] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0683] Step 1:

[0684] The terminal collects digital information in text, audio, and image formats from the user's digital communication infrastructure. The user must consent to this data collection. Input is user-submitted data, and output is a collected dataset. The terminal operates by launching a data collection program and targeting the necessary information.

[0685] Step 2:

[0686] The terminal encrypts the collected digital information and sends it to the server using a secure communication protocol. The input is the collected dataset, and the output is the encrypted transmission data. This operation ensures that the data is securely transferred to the server without being leaked externally.

[0687] Step 3:

[0688] The server begins analyzing the received digital information using a natural language processing engine. It decrypts encrypted data as input and analyzes text, audio, and image data. The output provides analysis results regarding emotions and themes. Specifically, the engine extracts keywords and emotion indicators from the data.

[0689] Step 4:

[0690] The server inputs the analyzed data into a generating AI model. This model evaluates the similarity of the analysis results to existing occupational data. The input is the analysis results of sentiment and themes, and the output is a list of recommended occupations and activities. The server's operation includes matching with existing databases and model training.

[0691] Step 5:

[0692] The server visualizes the generated occupation and activity recommendations and sends them to the terminal along with prompt messages. The input is recommendation data from the model, and the output is visualized recommendation information. Specifically, it generates graphs and charts.

[0693] Step 6:

[0694] The device displays the received visualization information to the user. The input is the visualized recommendation results, and the output is visual feedback to the user. The device displays graphs and charts on its screen, allowing the user to deepen their understanding of their own characteristics and recommended carriers.

[0695] (Application Example 2)

[0696] 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".

[0697] In today's information network environment, it is difficult for users to find the optimal products and activities that match their emotional state, and traditional recommendation systems have the challenge of not being able to provide personalized recommendations that reflect these emotional changes. Furthermore, from a privacy perspective, there is a need to provide effective recommendations while ensuring the security of user data.

[0698] 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.

[0699] In this invention, the server includes means for collecting data from a user's communication platform using an information processing device, means for analyzing the data using natural language processing technology to identify the sentiment and topic of the data, and means for recommending products or activities suitable for the user based on the analysis results using a generative model. This enables instantaneous analysis of the user's sentiment, highly accurate recommendations of products and activities that respond to changes, and effectively promotes the user's willingness to purchase.

[0700] An "information processing device" is a device used to collect and analyze data from a user's communication platform.

[0701] "Data" refers to information posted by users on a communication platform, including text, audio, and images.

[0702] "Natural language processing technology" is a technique that uses computers to analyze human language and extract specific meanings and emotions.

[0703] A "generative model" is a model that generates new information based on input data, and is used to recommend products and activities that are suitable for the user based on the analysis results.

[0704] "Emotions" refer to the mental state analyzed from users' posts and actions, and they influence users' preferences and purchasing behavior.

[0705] A "topic" refers to a theme or subject identified based on user-submitted data.

[0706] "Recommending a product or activity" means presenting highly relevant products or activities based on the user's emotional state and preferences.

[0707] "Visual display" refers to displaying analyzed data and recommended information on the screen using graphs, charts, and other visual aids.

[0708] "Security" refers to technical measures taken to prevent unauthorized access to and leakage of data, and to protect user privacy.

[0709] The system implementing this invention first collects data from the user's communication platform using an information processing device. The data includes text, audio, and image data, which are collected with the user's consent and transmitted to the server while ensuring security and protecting privacy. The server analyzes this data using natural language processing technology to identify the user's emotions and topics of conversation. Specifically, it uses Python and natural language processing libraries such as NLTK and spaCy to analyze the text.

[0710] By utilizing generative models, the server recommends products or activities suitable for the user based on these analysis results. These generative models employ machine learning libraries such as TensorFlow and PyTorch, comparing product classification data with the user's analyzed sentiment patterns to provide optimal recommendations based on similarity.

[0711] The server then visually displays these recommendations on the terminal to encourage the user's purchase. The terminal displays the analysis and recommendation results in the form of graphs and charts, allowing the user to easily understand the suggested products and activities.

[0712] For example, if a user posts "I want something fun today," the system can analyze this emotion and suggest entertainment-related products that match the user's interests. Another example of a prompt might be: "Build a system that analyzes the emotions of users based on their posts and recommends the most suitable products based on those emotions. Suggest relaxing products if the user is stressed, and celebratory products if they are happy."

[0713] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0714] Step 1:

[0715] The server collects data from the user's communication platform. It takes user-submitted text, audio, and image data as input and stores it securely. The server then converts this data into a format for analysis, preparing it for the next step.

[0716] Step 2:

[0717] The server analyzes the collected data using natural language processing techniques. The input is the data formatted in Step 1. The server uses Python and natural language processing libraries (NLTK and spaCy) to tokenize the text data and perform sentiment analysis. The output is the sentiment and topic extracted from the text.

[0718] Step 3:

[0719] The server uses a generative AI model to recommend products or activities based on the analysis results. The input is sentiment and topic information obtained in step 2. The server uses a generative model based on TensorFlow or PyTorch to calculate the similarity between the product database and the sentiment information. The output is a list of products suitable for the user.

[0720] Step 4:

[0721] The server visually displays recommended product information on the terminal. The input is the product list obtained in step 3. The server generates a graph or chart and sends it to the terminal via API for display on the screen in a format that is easy for the user to understand. The output is the product recommendations displayed on the user's screen.

[0722] Step 5:

[0723] The user reviews the information displayed on the device and considers the recommended products and activities. The input is the product information displayed on the device. The user performs purchase or search actions as needed and makes their own decisions based on the system's recommendations. The output is the next action based on the user's actions.

[0724] 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.

[0725] 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.

[0726] 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.

[0727] 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.

[0728] 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.

[0729] 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.

[0730] 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.

[0731] 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.

[0732] 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."

[0733] 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.

[0734] 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.

[0735] 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.

[0736] 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.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] 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.

[0744] 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.

[0745] The following is further disclosed regarding the embodiments described above.

[0746] (Claim 1)

[0747] The information processing device provides a means for collecting posted data from the user's communication platform,

[0748] The aforementioned posted data is analyzed using natural language processing technology to identify the sentiment and topic of the posts,

[0749] Using a generative model, a means of recommending suitable occupations and activities to users based on the analysis results,

[0750] A means of visually displaying the aforementioned recommendations and promoting self-understanding by the user,

[0751] A system that includes this.

[0752] (Claim 2)

[0753] The system according to claim 1, characterized in that the generative model compares user-submitted data with other submitted data classified by occupation and analyzes similarity.

[0754] (Claim 3)

[0755] The system according to claim 1, characterized in that the information processing device has a function to securely collect posted data with the user's consent and to protect privacy.

[0756] "Example 1"

[0757] (Claim 1)

[0758] The information processing device provides a means for collecting information posted from the user's information exchange platform,

[0759] The aforementioned posted information is analyzed using natural language processing techniques to identify emotions and themes, and

[0760] Using a generative model, a means to suggest suitable occupations and activities for users based on the analysis results,

[0761] A means of visually displaying the aforementioned suggestion and promoting self-awareness among users,

[0762] The aforementioned system includes means for inputting analysis results into a generation model and providing a function for analyzing the similarity between user-submitted data and other submitted data,

[0763] A system that includes this.

[0764] (Claim 2)

[0765] The system according to claim 1, characterized in that the generative model compares user-submitted data with other submitted data classified by occupation and analyzes similarity.

[0766] (Claim 3)

[0767] The system according to claim 1, characterized in that the information processing device has a function to securely collect posted data with the user's consent and protect the privacy of individuals.

[0768] "Application Example 1"

[0769] (Claim 1)

[0770] The information processing device provides a means for collecting digital information from the user's communication platform,

[0771] A means for analyzing the aforementioned digital information using natural language processing technology to identify the emotion and theme of the linguistic expression,

[0772] Using a generative model, a means of recommending suitable occupations and activities for individuals based on the analysis results,

[0773] The aforementioned recommendations are visually displayed and serve as a means to promote individual self-understanding.

[0774] A means of analyzing a user's consumption history and generating financial asset recommendations,

[0775] A system that includes this.

[0776] (Claim 2)

[0777] The system according to claim 1, characterized in that the generation model compares the user's digital information with other digital information classified by occupation and analyzes the similarity.

[0778] (Claim 3)

[0779] The system according to claim 1, characterized in that the information processing device securely collects digital information with the consent of an individual and has a function to protect personal information.

[0780] "Example 2 of combining an emotion engine"

[0781] (Claim 1)

[0782] Means for collecting digital information from the user's digital communication infrastructure,

[0783] A means for analyzing the aforementioned digital information using language analysis technology and extracting emotional states and themes,

[0784] Using a generative AI model, a means of recommending suitable occupations and activities to users based on the aforementioned analysis results,

[0785] A means of visualizing and displaying the aforementioned recommendations to promote user self-awareness,

[0786] A means of securely transmitting digital information while protecting privacy,

[0787] A system that includes this.

[0788] (Claim 2)

[0789] The system according to claim 1, characterized in that the generating AI model compares other digital information classified as occupation with the user's digital information and analyzes the similarity.

[0790] (Claim 3)

[0791] The system according to claim 1, characterized in that the information processing device has the function of collecting digital information, including multimedia information, with the consent of the user, and constructing a rich dataset.

[0792] "Application example 2 when combining with an emotional engine"

[0793] (Claim 1)

[0794] The information processing device provides a means for collecting data from the user's communication platform,

[0795] The aforementioned data is analyzed using natural language processing technology, and means are provided to identify the sentiment and topic of the data.

[0796] Using a generative model, a means of recommending products or activities suitable for the user based on the analysis results,

[0797] A means of visually displaying the aforementioned recommendations and promoting the user's desire to purchase,

[0798] A system that includes this.

[0799] (Claim 2)

[0800] The system according to claim 1, characterized in that the generation model compares user data with other data classified by product category and analyzes similarity.

[0801] (Claim 3)

[0802] The system according to claim 1, characterized in that the information processing device has a function to securely collect data with the user's consent and protect privacy. [Explanation of symbols]

[0803] 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. The information processing device provides a means for collecting posted data from the user's communication platform, The aforementioned posted data is analyzed using natural language processing technology to identify the sentiment and topic of the posts, Using a generative model, a means of recommending suitable occupations and activities to users based on the analysis results, A means of visually displaying the aforementioned recommendations and promoting self-understanding by the user, A system that includes this.

2. The system according to claim 1, characterized in that the generation model compares user-submitted data with other submitted data classified by occupation and analyzes the similarity.

3. The system according to claim 1, characterized in that the information processing device has a function to securely collect posted data with the user's consent and to protect privacy.

Images