System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving an input from a user; means for performing an analysis based on the received input; means for applying a generative model that generates prediction information using an analysis result; and means for providing the generated prediction information to the user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In conventional fortune-telling services, users had to meet with fortune-tellers face-to-face and were restricted by time and location, making it difficult for them to receive a fortune easily. Furthermore, the skills and interpretations of each fortune-teller varied, often resulting in inconsistent results. This made it difficult for users to easily obtain reliable fortune-telling results. The present invention aims to solve these problems and provide a system that allows users to obtain consistent fortune-telling results regardless of time or location. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for accepting input from a user, a means for performing analysis based on the accepted input, a means for applying a generative model that uses the analysis results to generate predictive information, and a means for providing the generated predictive information to the user. In particular, the system includes a means for analyzing image data, which analyzes palm lines or tarot card images and extracts their features. The generative model is based on a machine learning algorithm, which improves the consistency and accuracy of the fortune-telling results. Furthermore, the system provides a means for allowing the user to select the type of fortune-telling and a means for displaying the fortune-telling results in text format, thereby realizing a system that is easily accessible and usable by the user.

[0006] "User" means an individual who uses the System or Services.

[0007] "Input" refers to the data or information a user provides to a system.

[0008] "Image data" refers to digital images containing visual information such as palm lines and tarot cards that are necessary for fortune telling.

[0009] "Analysis" refers to data processing and feature extraction performed on input data.

[0010] A "generative model" refers to a mathematical model that uses machine learning algorithms to predict fortune-telling results.

[0011] "Predictive information" refers to the fortune-telling results and advice derived by the generative model.

[0012] A "machine learning algorithm" refers to a computational method that uses data to train a model and make predictions based on new data.

[0013] "Type of reading" refers to the specific method of reading a user can choose from, such as palmistry or tarot card reading.

[0014] "Text format" refers to data provided as text information.

[0015] "Palmistry features" refers to specific visual indicators used for divination, such as lines or patterns on the palm.

[0016] "Tarot card placement data" refers to information regarding the position and order of the cards used in tarot readings.

[0017] "API request" refers to data transmission from a terminal to a server via an application programming interface.

[0018] "API response" refers to the return of data from a server to a terminal via an application programming interface. [Brief explanation of the drawings]

[0019] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0020] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0021] First, the terms used in the following description will be explained.

[0022] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0023] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0024] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0025] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0026] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0030] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0031] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0032] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0033] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0034] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0037] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0038] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0039] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0040] The present invention relates to a system including an input means for a user to request a fortune telling, an analysis means for analyzing the received input, a generative model that generates predictive information using the analysis results, and a means for providing the generated predictive information to the user.

[0041] This system consists of a user's device (e.g., a smartphone or PC) and a server. The device provides the user interface and accepts the desired fortune-telling content and necessary data (e.g., palm reading images and tarot card placement data). The device then creates an API request to send the accepted data to the server.

[0042] The server analyzes the received API request and performs the necessary data processing based on the user's input. Specifically, image recognition technology is used to extract palmistry features and input these features into a generative model. The generative model is based on a machine learning algorithm and generates predictive information by referencing past data and statistical information. For example, if the lifeline on the palm is long, the resulting fortune-telling result will indicate good health.

[0043] The generated prediction information is sent from the server to the device as an API response. The device displays the received prediction information to the user, providing consistent fortune-telling results. The user can check the displayed results, request further fortune-telling, or try different fortune-telling methods.

[0044] Example 1: Palmistry

[0045] The user selects palm reading on their device and uploads a photo of their palm. This photo is sent to the server as an API request. The server analyzes the image and extracts palm features such as life lines and fate lines. The extracted feature data is input into a generative model, which generates a fortune-telling result. For example, it generates prediction information such as "Your life line is very long, so you have good health." This information is sent back to the device as an API response and displayed to the user.

[0046] Example 2: Tarot reading

[0047] The user selects tarot reading using their device and inputs the card placement data. This placement data is sent to the server as an API request. The server analyzes the tarot card placement and generates a fortune-telling result based on that placement using a generative model. For example, it generates prediction information such as "Since the current card is 'The Tower,' now is a time for change." This information is also sent back to the device as an API response and displayed to the user.

[0048] In this way, our system applies appropriate analysis and generative models depending on the type of fortune-telling requested by the user, providing fast and accurate fortune-telling results. Users can easily receive consistent and reliable fortune-telling results regardless of time or place.

[0049] The processing flow will be explained below.

[0050] Step 1:

[0051] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[0052] Step 2:

[0053] The user uploads a photo of their palm to the device and presses the "Perform fortune telling" button.

[0054] Step 3:

[0055] The device receives input from the user and composes palm image data and a fortune-telling request (e.g., "palm reading") as an API request.

[0056] Step 4:

[0057] The device sends the configured API request to the server.

[0058] Step 5:

[0059] The server receives an API request from the terminal and analyzes the request content to identify the fortune-telling method (palm reading) selected by the user and the image data provided.

[0060] Step 6:

[0061] The server invokes an image processing module to analyze the palm image, specifically applying image recognition algorithms to extract key palm features (e.g., life line, fate line, etc.).

[0062] Step 7:

[0063] The server inputs the extracted palm line feature data into a generative AI model, which is trained using machine learning algorithms and generates fortune-telling results based on this data.

[0064] Step 8:

[0065] The server formats the generated fortune-telling result in text format and composes it as an API response.

[0066] Step 9:

[0067] The server sends the constructed API response to the device.

[0068] Step 10:

[0069] The terminal receives the API response from the server and analyzes the response data.

[0070] Step 11:

[0071] The device then displays the analyzed fortune-telling results on the user interface, such as "Your lifeline is very long, so you have good health."

[0072] Step 12:

[0073] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0074] In this way, a series of processes that allows the user to easily obtain fortune-telling results is completed.

[0075] Example 1

[0076] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0077] In conventional fortune-telling systems, when users request a fortune, they must manually input and analyze data, which takes time and effort. There are also issues with the reliability and consistency of the results. This makes it difficult for users to easily obtain quick, accurate fortune-telling results.

[0078] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0079] In this invention, the server includes means for accepting input from a user, means for transmitting the accepted input to the server, means for analyzing data based on the received input, means for applying a generative AI model that generates predictive information using the analysis results, and means for providing the generated predictive information to the user, thereby enabling the user to easily request a fortune telling and obtain a quick and accurate result.

[0080] "User" refers to an individual or organization that uses this system.

[0081] "Means for accepting input" refers to devices or software that provide an interface for users to input or upload data for fortune-telling purposes.

[0082] "Means for sending input to a server" refers to a device or software with a communication function for sending data entered by a user to a server.

[0083] "Means for analyzing data" refers to software or algorithms that the server uses to process the data received from the user and extract the necessary information.

[0084] A "generative AI model that generates predictive information using analysis results" is an artificial intelligence model that generates fortune-telling results and predictive information based on analyzed data.

[0085] "Means for generating predictive information" refers to software or algorithms that use a generative AI model to output specific fortune-telling results or predictive information from the analysis results.

[0086] "Means for providing generated predictive information to users" refers to devices or software equipped with an interface and communication functions for conveying the information output by the generative AI model to users.

[0087] "Means for analyzing image data" refers to software or algorithms that use image recognition technology to process image data provided by users and extract necessary features.

[0088] A "generative AI model that uses prompts based on machine learning algorithms" is an artificial intelligence model that uses machine learning technology to generate appropriate responses or predictions for specific inputs.

[0089] The present invention relates to a system for users to request fortune-telling. This system is configured using a user's terminal (for example, a smartphone or PC) and a server.

[0090] The user uses the device to select the type of fortune-telling (palm reading, tarot card reading, etc.) and input or upload the necessary data. For example, for palm reading, the user can take and upload a photo of their palm. For tarot reading, the user can input the card arrangement data.

[0091] The device receives the data entered by the user, converts it into an appropriate format (e.g., JSON format) as an API request, and sends it to the server. This transmission uses Internet communication.

[0092] The server analyzes the received API request and checks the data content. In the case of palmistry, the server uses image recognition technology (e.g., OpenCV) to extract palm features (such as life lines and fate lines). This extracted feature data is input into a generative AI model (e.g., GPT-4).

[0093] The generative AI model uses machine learning algorithms to generate fortune-telling results and predictions by referencing past data and statistical information. For example, in the case of palmistry, by entering a prompt such as "Please analyze a palm with a long, clear life line. What does that mean?", the generative model will generate a result such as "Your life line is very long, so you have good health."

[0094] In the case of tarot readings, the AI ​​model is given a prompt based on the placement data of the tarot cards: "The current card is the Tower, and the future card is the Sun. Please generate a fortune-telling result based on these placements." In this case, it generates prediction information such as, "Because the current card is the Tower, now is a time of change."

[0095] The generated prediction information is sent from the server to the device as an API response. The device analyzes the received API response and displays the fortune-telling results in a format that is easy for the user to understand.

[0096] The user can check the displayed fortune-telling results and request a more detailed fortune-telling or a new fortune-telling if necessary. This system provides an environment where users can receive fortune-telling easily, quickly, and accurately.

[0097] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0098] Step 1:

[0099] The user selects the type of fortune-telling they want and inputs or uploads the necessary data: for palm reading, they take a photo of their palm, and for tarot reading, they input the card layout data. Then, the user confirms their fortune-telling request.

[0100] Input: Type of fortune telling and related data (palm reading photo or tarot card placement data)

[0101] Output: User selections and input data

[0102] Step 2:

[0103] The terminal receives the data entered by the user and sends it to the server as an API request, where the data is converted into an appropriate format (e.g., JSON).

[0104] Input: User-selected and entered data

[0105] Output: API request to the server

[0106] Step 3:

[0107] The server analyzes the received API request and checks the data content. In the case of palmistry, it analyzes a photo of the palm using image recognition technology to extract features. In the case of tarot readings, it analyzes the card placement data.

[0108] Input: API request sent from the device

[0109] Output: Palm reading data or tarot card layout data

[0110] Step 4:

[0111] The server inputs the extracted feature data and placement data into the generative AI model, generates prompt sentences, and inputs them into the model to generate prediction information.

[0112] Input: Palm reading data or tarot card placement data, prompt text

[0113] Output: Predictions from the generative AI model

[0114] Step 5:

[0115] The server receives the generated prediction information and sends it to the device as an API response, which is then formatted appropriately.

[0116] Input: Prediction information from a generative AI model

[0117] Output: API response to the device

[0118] Step 6:

[0119] The device analyzes the API response received from the server and displays the fortune-telling results in a format that is easy for the user to understand. The user can then check the displayed results and request a more detailed fortune-telling or a new fortune-telling.

[0120] Input: API response from the server

[0121] Output: Display fortune-telling results to the user

[0122] These steps allow users to easily obtain quick and accurate fortune-telling results.

[0123] (Application example 1)

[0124] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0125] Conventional fortune-telling systems often took a long time for users to receive their fortune-telling results, and they often lacked consistency and reliability. Face-to-face fortune-telling also had limitations on location and time, making it difficult for many users to use. Another issue was the lack of established technology for accurately analyzing image data from palmistry and tarot cards.

[0126] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0127] In this invention, the server includes means for processing input data for providing fortune-telling results using image recognition technology, means for inputting prompt sentences based on specific categories into a generative AI model, and means for providing consistent and reliable fortune-telling results online, thereby enabling users to quickly obtain consistent and reliable fortune-telling results regardless of location or time.

[0128] "User" refers to any individual or organization that uses the fortune-telling service.

[0129] "Means for accepting input" refers to the interface or function that allows users to input the information they want to know and the necessary data.

[0130] "Analysis tools" refers to the techniques and algorithms used to process data received from users and extract meaningful information.

[0131] "Means for applying generative models" refers to the function of applying machine learning models or AI to generate fortune-telling prediction information based on analyzed data.

[0132] "Means for providing predictive information" refers to the interface and functions for communicating the generated fortune-telling results to users.

[0133] "Image recognition technology" refers to the technology used to analyze image data and extract features. Specifically, it is used to extract palm lines and other features.

[0134] "Prompt" means a text-formatted instruction given to a generative AI model, including instructions based on a specific category.

[0135] "Consistent and reliable fortune-telling results" refers to fortune-telling results that always provide the same results for the same input and that have the reliability to be accepted by many people.

[0136] "Online delivery means" refers to the technologies and functions used to provide services to users via the Internet.

[0137] This invention relates to an online fortune-telling system that can be used by users. This system is composed of a user terminal and a server, and is capable of quickly and consistently providing fortune-telling results such as palm reading and tarot card reading.

[0138] The server includes a means for processing input data using image recognition technology to provide fortune-telling results. Specifically, it receives palm reading photos and tarot card layout data provided by users, analyzes those images, and extracts features. Deep learning frameworks such as TensorFlow and Keras are used for this analysis.

[0139] Next, there is a way to input prompt sentences based on specific categories into the generative AI model. For example, in the case of palm reading, the server generates prompt sentences of the following form based on features extracted from a palm image:

[0140] It analyzes the palm image provided by the user and generates a fortune-telling result based on the following palm characteristics:

[0141] If the lifeline is long, you have good health.

[0142] If your fate line is clear, you have good luck in your career.

[0143] ...

[0144] Based on your palm reading, please provide your reading in the following format:

[0145] "Your lifeline is {length}. Your health is {fortune_level}."

[0146] Image data URL: {img_url}

[0147] This prompt is input into a generative model using deep learning, such as GPT (Generative Pretrained Transformer), to generate a specific fortune-telling result.

[0148] The generated fortune-telling results are sent from the server to the user's device and displayed to the user via an interface. This process uses API requests and responses. The front-end portion is built using cross-platform development frameworks such as React Native, and users can upload photos of their palms and view fortune-telling results through the app.

[0149] As a concrete example, consider the case where a user selects palm reading and takes and uploads a photo of their palm with their smartphone. This photo is sent to the server as an API request. The server analyzes the photo using image recognition technology to extract the characteristics of the palm lines. The generative model then predicts the fortune-telling result, generating something like, "Your lifeline is very long, so you have good health." This result is sent back to the user's device as an API response and displayed through the app.

[0150] In this way, the present invention provides a system that allows users to quickly obtain highly reliable fortune-telling results regardless of location or time.

[0151] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0152] Step 1:

[0153] A user uses a device to access a fortune-telling application. The device displays a user interface and provides options for selecting categories, such as palmistry or tarot reading. The user selects the type of reading and uploads a photo of their palm. The input data is an image file of the palm.

[0154] Step 2:

[0155] The device receives the palm print photo uploaded by the user and sends it to the server as an API request. Specifically, the image file is sent to the server as form data via an HTTP POST request. At this stage, the input is the palm print image data, and the output is the API request sent to the server.

[0156] Step 3:

[0157] The server analyzes the received palm image data. As a first step, it uses image recognition technology to extract palm features. Specifically, it uses deep learning frameworks such as TensorFlow and Keras to identify palm features such as life lines and fate lines. The results of this analysis become the input data for the next step. The output of the analysis is the extracted palm feature data.

[0158] Step 4:

[0159] The server generates a prompt sentence based on the extracted feature data. For example, it creates a sentence to input to the generative AI model to prompt the generation of a fortune-telling result, such as "Your lifeline is long and you have good health." The input to this prompt sentence is the extracted palm feature data, and the output is the prompt sentence to input to the generative AI model.

[0160] Step 5:

[0161] The server generates fortune-telling results using a generative AI model. A specific prompt is input into the model, which predicts and generates fortune-telling results based on past data and statistical information. The input at this stage is the prompt, and the output is the generated fortune-telling result text.

[0162] Step 6:

[0163] The generated fortune-telling result is sent from the server to the device as an API response. Specifically, it is sent as an HTTP response and the result is encoded in JSON format. The input of this step is the generated fortune-telling result text, and the output is the API response sent to the device.

[0164] Step 7:

[0165] The terminal interprets the received fortune-telling results and displays them through a user interface. The user can then review the displayed fortune-telling results and request further fortune-telling or try other fortune-telling methods. The input at this stage is the text fortune-telling results received from the server, and the output is the result displayed to the user.

[0166] This series of processing steps allows users to obtain quick, consistent, and reliable fortune-telling results regardless of location or time.

[0167] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0168] This invention relates to a system that uses a generative model that accepts and analyzes input from a user to generate predictive information, and provides that predictive information to the user. This system also combines an emotion engine that recognizes the user's emotions, and provides fortune-telling results and predictive information according to the user's emotions.

[0169] System Configuration

[0170] This system is composed of a terminal (for example, a smartphone or PC), a server, and an emotion engine. The following is a specific embodiment of the system.

[0171] The device provides a user interface and accepts the desired fortune-telling content and necessary data (for example, palm reading images or tarot card placement data). It also monitors the user's input and facial expressions to collect emotional data, which becomes the basis for the emotion engine to analyze the user's emotions.

[0172] The server receives and analyzes the data sent from the device. Specifically, it analyzes palm reading and tarot card data and extracts its characteristics. The emotion engine analyzes the user's emotions based on this data and provides emotional information. This emotional information is input into a generative model and used to generate fortune-telling results and prediction information.

[0173] Generative models are based on machine learning algorithms and generate predictions based on historical data and statistical information. These predictions are tailored to the user's emotions and presented in an appropriate format. For example, if the user is feeling anxious, the predictions can be presented in a more gentle way.

[0174] Example 1: Palmistry and Emotion Recognition

[0175] 1. The user selects palm reading on the device and uploads a photo of their palm. At the same time, facial expression data of the user is collected via the camera.

[0176] 2. The device sends the palm image data and facial expression data to the server.

[0177] 3. The server extracts features from the palm image and inputs them into the generative model. At the same time, the emotion engine analyzes the user's emotions using facial expression data.

[0178] 4. The emotion engine detects the user's emotional state (e.g., "anxiety") and provides that information to the generative model.

[0179] 5. The generative model generates fortune-telling results based on the palmistry characteristics and the user's emotions, outputting content such as, "Your lifeline is very long and you have good health. You may be feeling anxious at the moment, but things will improve in the future."

[0180] 6. The server sends the generated fortune-telling result to the terminal.

[0181] 7. The device displays the received fortune-telling results to the user, who can then confirm the results and select the next action.

[0182] Example 2: Tarot reading and emotion recognition

[0183] 1. The user selects tarot reading and inputs the card placement data. In addition, facial expression data is collected by camera.

[0184] 2. The device sends the position data and facial expression data to the server.

[0185] 3. The server analyzes the placement data and extracts its features. At the same time, the emotion engine analyzes emotions based on the facial expression data.

[0186] 4. The emotion engine detects the user's emotions (e.g., "joy") and provides that information to the generative model.

[0187] 5. The generative model generates fortune-telling results based on the placement of the tarot cards and the user’s emotions, for example, “Since the current card is ‘The Sun,’ a very positive fortune is predicted. Your mood also seems to be lifted, and you feel confident about the future.”

[0188] 6. The server sends the generated results to the terminal.

[0189] 7. The device displays the results to the user and allows them to choose their next action.

[0190] In this way, by combining this system with an emotion engine, it is possible to provide fortune-telling results that correspond to the user's emotions, realizing a more personalized experience.

[0191] The processing flow will be explained below.

[0192] Step 1:

[0193] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[0194] Step 2:

[0195] Users use the device's camera to take a photo of their palm and simultaneously collect facial expression data.

[0196] Step 3:

[0197] The device sends palm image data and facial expression data to the server as an API request.

[0198] Step 4:

[0199] The server receives the API request sent from the terminal.

[0200] Step 5:

[0201] The server passes the palm image data to an image processing module, which extracts palm features (life line, fate line, etc.).

[0202] Step 6:

[0203] The server passes the facial expression data to an emotion engine to analyze the user's emotional state. For example, it uses facial expression recognition technology to detect whether the user is in an "anxious" state.

[0204] Step 7:

[0205] The server inputs the extracted palm feature data and analyzed emotional information into a generative AI model.

[0206] Step 8:

[0207] The generative AI model generates fortune-telling results based on palmistry feature data and emotional information, such as, "Your lifeline is very long, and you have good health. You may be feeling anxious at present, but things will improve in the future."

[0208] Step 9:

[0209] The server sends the generated fortune-telling result to the terminal as an API response.

[0210] Step 10:

[0211] The terminal receives the API response from the server and analyzes the response data.

[0212] Step 11:

[0213] The device then displays the analyzed fortune-telling results on the user interface, for example in a gentle tone.

[0214] Step 12:

[0215] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0216] Example 2: Tarot reading and emotion recognition

[0217] Step 1:

[0218] The user selects tarot reading on the terminal and enters the card placement data.

[0219] Step 2:

[0220] Users use the device's camera to collect facial expression data.

[0221] Step 3:

[0222] The device sends the tarot card placement data and facial expression data to the server as an API request.

[0223] Step 4:

[0224] The server receives the API request sent from the terminal.

[0225] Step 5:

[0226] The server analyzes the tarot card arrangement data and extracts its characteristics.

[0227] Step 6:

[0228] The server passes the facial expression data to an emotion engine to analyze the user's emotions. For example, it uses facial expression recognition technology to detect whether the user is in a "happy" state.

[0229] Step 7:

[0230] The server inputs the extracted tarot card feature data and analyzed emotional information into the generative AI model.

[0231] Step 8:

[0232] The generative AI model generates fortune-telling results based on the tarot card placement feature data and emotional information, such as, "Because the current card is the 'Sun,' a very positive fortune is predicted. Your mood seems to be lifted, and you feel confident about the future."

[0233] Step 9:

[0234] The server sends the generated fortune-telling result to the terminal as an API response.

[0235] Step 10:

[0236] The terminal receives the API response from the server and analyzes the response data.

[0237] Step 11:

[0238] The device then displays the analyzed fortune-telling results on the user interface, for example, in a positive tone that matches the user's emotions.

[0239] Step 12:

[0240] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0241] Example 2

[0242] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0243] Conventional prediction systems were unable to take the user's emotional state into account when providing predictive information based on user input data. This made it difficult to provide flexible predictions that reflected the user's current emotions, resulting in poor acceptability of the prediction results.

[0244] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information based on the analysis result and the emotional state of the user, and means for providing the generated predictive information to the user. This makes it possible to provide appropriate predictive information according to the user's emotions.

[0245] "User" refers to the person who operates the system and inputs data.

[0246] "Input" refers to data or information provided by a user to a system.

[0247] "Analysis" refers to the process of extracting features and meaning from input data.

[0248] "Emotional state" refers to a user's current emotional state or psychological condition.

[0249] A "generative model" refers to an algorithm or system that generates predictive information from input data and analysis results.

[0250] "Predictive information" refers to future outlooks and fortune-telling results generated based on analyzed data.

[0251] "Providing" refers to displaying the generated forecast information to the user.

[0252] "Server" refers to a computer system that receives data, analyzes it, applies generative models, and provides prediction information.

[0253] "Terminal" refers to a device (e.g., a smartphone or PC) that a user operates and uses to provide input data.

[0254] "Image data" refers to photo and video data provided by users.

[0255] A "machine learning algorithm" refers to a computational method for training a model based on data and making predictions and classifications.

[0256] This invention relates to a system that accepts and analyzes input data from a user, evaluates the user's emotional state using an emotion recognition engine, and generates and provides predictive information based on that information. This system consists of a terminal (such as a smartphone or PC), a server, and an emotion recognition engine.

[0257] Overview of program processing

[0258] This system performs the following processes:

[0259] 1. Accepting user input

[0260] Users use the application on their device to select palm reading or tarot card reading, and input a photo of their palm and tarot card placement data, while facial expression data is collected via the camera.

[0261] 2. Data transmission

[0262] The device sends the data entered by the user to a server using an internet connection.

[0263] 3. Server-side data analysis

[0264] The server analyzes the received data. For palm reading image data, image analysis software (e.g., OpenCV) is used to extract features, and for tarot card placement data, a proprietary algorithm is used.

[0265] 4. Emotion analysis

[0266] An emotion recognition engine analyzes facial expression data to assess the user's emotional state, using deep learning models (e.g., Emotion Recognition API).

[0267] 5. Generating Predictive Information Using Generative Models

[0268] The generative model generates predictions based on emotion information and palm reading or tarot data. This generative model uses machine learning algorithms (e.g., TensorFlow). The predictions are adjusted according to the user's emotions.

[0269] 6. Sending and displaying results

[0270] The server transmits the generated forecast information to the terminal, which displays the information to the user.

[0271] Hardware and software used

[0272] Devices: Smartphones, PCs, webcams

[0273] Server: High-performance processor, large storage capacity

[0274] Image analysis software: OpenCV

[0275] Emotion Recognition Engine: Emotion Recognition API

[0276] Machine learning framework: TensorFlow

[0277] Specific examples

[0278] Example 1: Palmistry

[0279] 1. The user selects palm reading through the app, takes a photo of their palm and uploads it, while facial expression data is also collected.

[0280] 2. The device sends the palm image and facial expression data to the server.

[0281] 3. The server analyzes the palm image using OpenCV and evaluates the emotion using an emotion recognition engine.

[0282] 4. The generative model generates the fortune-telling results, creating a message such as, "Your lifeline is very long and you have good health. You may be feeling anxious now, but things will improve in the future."

[0283] 5. The server sends the results to the terminal, which displays them to the user.

[0284] Prompt Sentence Examples

[0285] "Upload an image of your palm and we'll give you a fortune reading based on that image. The reading will be adjusted according to your current emotional state."

[0286] Example 2: Tarot reading

[0287] 1. The user selects tarot reading and inputs the card placement data. Facial expression data is also collected at the same time.

[0288] 2. The device sends the position data and facial expression data to the server.

[0289] 3. The server analyzes the placement data and evaluates the emotion using an emotion recognition engine.

[0290] 4. The generative model generates the fortune-telling result, creating a message such as, "Since your current card is the Sun, a very positive fortune is predicted. Your spirits seem to be lifted and you feel confident about the future."

[0291] 5. The server sends the results to the terminal, which displays them to the user.

[0292] Prompt Sentence Examples

[0293] "Enter your tarot card placement data. We will predict your fortune based on that placement. The results will be adjusted according to your current emotions."

[0294] In this way, the present invention provides appropriate predictive information according to the user's emotions, realizing a more personalized experience.

[0295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0296] Step 1:

[0297] The user opens the application on the device and selects the type of fortune-telling (palm reading or tarot card reading). Then, for palm reading, the user takes a photo of their palm, and for tarot reading, the user inputs the card arrangement data. Furthermore, facial expression data is automatically collected via the camera. The user's palm image, tarot card arrangement data, and facial expression data are then input.

[0298] Input: Palm reading image or tarot card placement data, and facial expression data

[0299] Output: A set of palm reading images or tarot card layout data and facial expression data

[0300] Specific behavior:

[0301] The user opens the app.

[0302] Choose palm reading or tarot reading (through UI).

[0303] For palm reading, open the camera and take a photo of your palm.

[0304] For tarot, the card placement is entered manually.

[0305] To collect facial expression data, the camera is activated and a picture of the user's facial expression is taken.

[0306] Step 2:

[0307] The terminal transmits the palm reading image, tarot card placement data, and facial expression data collected from the user to the server. This transmission is performed via internet communication. The data is sent in a single packet.

[0308] Input: A set of palm reading images or tarot card layout data and facial expression data

[0309] Output: Palm reading image or tarot card placement data and facial expression data sent to the server

[0310] Specific behavior:

[0311] The collected data is organized into packets.

[0312] Send an HTTP POST request to the server's URL over your internet connection.

[0313] Step 3:

[0314] The server receives the data sent from the device and analyzes each data. For palm reading images, image analysis software (e.g., OpenCV) is used, and for tarot card placement data, a proprietary algorithm is used to extract features. For facial expression data, an emotion recognition engine is used to analyze emotions.

[0315] Input: Palm reading image or tarot card placement data, and facial expression data

[0316] Output: Palmistry feature data, Tarot feature data, and emotional state data

[0317] Specific behavior:

[0318] The server receives the data packets and passes them to a module for analysis.

[0319] The palm image is analyzed using OpenCV to extract palm line features.

[0320] Analyze tarot placement data and extract card characteristics.

[0321] An emotion recognition engine is used to analyze facial expression data and detect emotional states (e.g., "anxiety" or "joy").

[0322] Step 4:

[0323] The server inputs the emotional information obtained from the emotion engine and the analyzed palm reading and tarot data into a generative model. The generative model uses a machine learning framework (e.g., TensorFlow) to generate fortune-telling results based on past data and statistical information. Furthermore, the generated results are adjusted according to the user's emotional state.

[0324] Input: Palmistry feature data, Tarot feature data, and emotional state data

[0325] Output: Predictive information adjusted based on emotions

[0326] Specific behavior:

[0327] Emotion information and palm or tarot data are input into the generative model.

[0328] Use TensorFlow to generate prediction information.

[0329] Tailor predictive information to the user's emotional state.

[0330] Step 5:

[0331] The server sends the fortune-telling results generated by the generative model to the device. This is done via internet communication again. The data is converted into a format that is easy for the device to understand (e.g., JSON format) and then sent.

[0332] Input: Emotionally adjusted prediction information

[0333] Output: Fortune telling results sent to the device

[0334] Specific behavior:

[0335] The generated fortune-telling results are collected into a packet.

[0336] Send it to your device via your internet connection.

[0337] Step 6:

[0338] The terminal displays the fortune-telling results received from the server to the user. The user can check the results and select the next action. The fortune-telling results are displayed in a format suitable for the user's terminal.

[0339] Input: Fortune telling result sent from the server

[0340] Output: Fortune telling result displayed to the user

[0341] Specific behavior:

[0342] Analyze the data received from the server and reflect the results in the display UI.

[0343] The user sees the results on the device screen.

[0344] (Application example 2)

[0345] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0346] Current predictive information systems have difficulty providing personalized information based on the user's emotions. Furthermore, rather than simply analyzing data, it is necessary to provide more accurate counseling and fortune-telling results by providing feedback based on emotions.

[0347] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information using the analysis results, means for analyzing emotions based on the generated predictive information, means for generating predictive information based on the analyzed emotional information, and means for providing the generated predictive information to the user. This makes it possible to provide personalized predictive information based on the user's emotions.

[0348] "User" refers to a person who uses the system.

[0349] "Input" refers to the data or information that a user provides to a system.

[0350] "Analysis" refers to the process of extracting information from input data and drawing specific conclusions or predictions.

[0351] A "generative model" refers to a computational model for generating predictive information using a machine learning algorithm.

[0352] "Predictive information" refers to information about future events or trends that is generated based on analytical results.

[0353] "Emotion analysis" refers to the process of determining a user's emotional state from facial expression data and other inputs.

[0354] "Emotional information" refers to data about a user's emotional state obtained through emotion analysis.

[0355] "Personalization" refers to tailoring information to each individual user's specific needs and feelings.

[0356] "Image data" refers to visual information provided in the form of still images or video.

[0357] A "machine learning algorithm" refers to a computational method that learns patterns from data and makes predictions or decisions based on them.

[0358] The system for realizing this invention is composed of the following program: This program analyzes data entered by a user, uses a machine learning algorithm to generate predictive information based on emotion information, and provides it to the user.

[0359] Hardware used

[0360] Device: Smartphone, tablet, or computer

[0361] Display devices: smart glasses, head-mounted displays

[0362] Analysis server: A high-performance calculation server (e.g., an EC2 instance on Amazon Web Services (AWS))

[0363] Software used

[0364] Facial expression recognition library: OpenCV

[0365] Sentiment analysis engine: Microsoft Azure Cognitive Services

[0366] Machine learning libraries: TensorFlow, PyTorch

[0367] Database: MongoDB, MySQL

[0368] Program processing flow

[0369] 1. The user uses the device to input the data they wish to receive for fortune telling or counseling. The input data includes the user's text information and image data required for fortune telling.

[0370] 2. The device uses the user's camera to collect facial expression data in real time, which is then used for later analysis.

[0371] 3. The analysis server receives the input data and facial expression data sent from the device. The facial expression data is analyzed using OpenCV to extract the emotional state.

[0372] 4. Microsoft Azure Cognitive Services, an emotion analysis engine, quantitatively evaluates the emotional state based on the extracted facial expression data and generates emotional information.

[0373] 5. Use a machine learning library (TensorFlow or PyTorch) to generate predictions based on the sentiment and user-supplied data, referencing historical data and statistical information to obtain more accurate results.

[0374] 6. The generated forecast information is provided to the user via the terminal.

[0375] Specific use cases

[0376] Consider a case where a user selects a relaxation menu at a relaxation salon. The user selects palm reading on their device and uploads a photo of their palm. At this time, the smart glasses also collect the user's facial expression data in real time. The server analyzes the palm image and simultaneously performs emotion analysis using the facial expression data. Using the generative model, the server generates a result such as, "Your lifeline is very long and you have good health luck. You may be feeling anxious at present, but things will improve in the future," and displays this result to the user.

[0377] Prompt Sentence Examples

[0378] Below is an example of a prompt for this system:

[0379] Customer facial expression data: {facial expression data}

[0380] Customer emotions: Anxiety, tension

[0381] Past counseling data: {Past data}

[0382] What I want: I want to relax

[0383] --Generative Model Prompt--

[0384] Generate personalized relaxation menus and counseling content based on the customer's emotional state.

[0385] In this way, the system combines highly accurate emotion analysis with predictive information to provide users with personalized information.

[0386] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0387] Step 1:

[0388] The device accepts input from the user regarding their desired fortune-telling or counseling. Specifically, the user uploads text information or image data (e.g., a photo of their palm) to the device. The input data is stored in a local database for subsequent analysis.

[0389] Step 2:

[0390] The device collects the user's facial expression data in real time. It divides the video data captured by the camera into frames and uses the OpenCV library to perform facial recognition and extract feature points. It analyzes the facial feature points and generates numerical data of the facial expression data.

[0391] Step 3:

[0392] The device sends the collected input data and facial expression data to the analysis server. The transmitted data is sent to the server's analysis engine via an API. The input data includes the user's text information, image data, and facial expression data.

[0393] Step 4:

[0394] The server receives the data sent from the device and first analyzes the image data. Specifically, the server uses an image recognition algorithm to extract the palm's characteristic points and convert them into numerical data. For image recognition, a deep learning model (e.g., VGG16 or ResNet) is used.

[0395] Step 5:

[0396] The server uses an emotion analysis engine (Microsoft Azure Cognitive Services) to analyze the facial expression data and identify the user's emotional state. Based on the facial expression data received as input, it determines the type of emotion (e.g., joy, anxiety, sadness) and outputs the emotional information as numerical data.

[0397] Step 6:

[0398] The server runs a generative model using a machine learning library (TensorFlow or PyTorch). Based on the palm reading data and emotion information received as input, the generative model generates predictions. The predictions (e.g., fortune-telling results or counseling advice) are generated by the generative AI model.

[0399] Step 7:

[0400] The server sends the generated forecast information to the device using the REST API in JSON format. The device then displays the received forecast information to the user.

[0401] Step 8:

[0402] The device provides users with predictive information and allows them to select their next action based on that information, for example, by providing an interactive UI for users to select a relaxation menu or request further counseling.

[0403] In this way, through the processing steps, personalized prediction information according to the user's emotions is provided.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0405] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0407] [Second embodiment]

[0408] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0409] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0410] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0412] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0414] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0415] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0416] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0419] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0420] The present invention relates to a system including an input means for a user to request a fortune telling, an analysis means for analyzing the received input, a generative model that generates predictive information using the analysis results, and a means for providing the generated predictive information to the user.

[0421] This system consists of a user's device (e.g., a smartphone or PC) and a server. The device provides the user interface and accepts the desired fortune-telling content and necessary data (e.g., palm reading images and tarot card placement data). The device then creates an API request to send the accepted data to the server.

[0422] The server analyzes the received API request and performs the necessary data processing based on the user's input. Specifically, image recognition technology is used to extract palmistry features and input these features into a generative model. The generative model is based on a machine learning algorithm and generates predictive information by referencing past data and statistical information. For example, if the lifeline on the palm is long, the resulting fortune-telling result will indicate good health.

[0423] The generated prediction information is sent from the server to the device as an API response. The device displays the received prediction information to the user, providing consistent fortune-telling results. The user can check the displayed results, request further fortune-telling, or try different fortune-telling methods.

[0424] Example 1: Palmistry

[0425] The user selects palm reading on their device and uploads a photo of their palm. This photo is sent to the server as an API request. The server analyzes the image and extracts palm features such as life lines and fate lines. The extracted feature data is input into a generative model, which generates a fortune-telling result. For example, it generates prediction information such as "Your life line is very long, so you have good health." This information is sent back to the device as an API response and displayed to the user.

[0426] Example 2: Tarot reading

[0427] The user selects tarot reading using their device and inputs the card placement data. This placement data is sent to the server as an API request. The server analyzes the tarot card placement and generates a fortune-telling result based on that placement using a generative model. For example, it generates prediction information such as "Since the current card is 'The Tower,' now is a time for change." This information is also sent back to the device as an API response and displayed to the user.

[0428] In this way, our system applies appropriate analysis and generative models depending on the type of fortune-telling requested by the user, providing fast and accurate fortune-telling results. Users can easily receive consistent and reliable fortune-telling results regardless of time or place.

[0429] The processing flow will be explained below.

[0430] Step 1:

[0431] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[0432] Step 2:

[0433] The user uploads a photo of their palm to the device and presses the "Perform fortune telling" button.

[0434] Step 3:

[0435] The device receives input from the user and composes palm image data and a fortune-telling request (e.g., "palm reading") as an API request.

[0436] Step 4:

[0437] The device sends the configured API request to the server.

[0438] Step 5:

[0439] The server receives an API request from the terminal and analyzes the request content to identify the fortune-telling method (palm reading) selected by the user and the image data provided.

[0440] Step 6:

[0441] The server invokes an image processing module to analyze the palm image, specifically applying image recognition algorithms to extract key palm features (e.g., life line, fate line, etc.).

[0442] Step 7:

[0443] The server inputs the extracted palm line feature data into a generative AI model, which is trained using machine learning algorithms and generates fortune-telling results based on this data.

[0444] Step 8:

[0445] The server formats the generated fortune-telling result in text format and composes it as an API response.

[0446] Step 9:

[0447] The server sends the constructed API response to the device.

[0448] Step 10:

[0449] The terminal receives the API response from the server and analyzes the response data.

[0450] Step 11:

[0451] The device then displays the analyzed fortune-telling results on the user interface, such as "Your lifeline is very long, so you have good health."

[0452] Step 12:

[0453] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0454] In this way, a series of processes that allows the user to easily obtain fortune-telling results is completed.

[0455] Example 1

[0456] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0457] In conventional fortune-telling systems, when users request a fortune, they must manually input and analyze data, which takes time and effort. There are also issues with the reliability and consistency of the results. This makes it difficult for users to easily obtain quick, accurate fortune-telling results.

[0458] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0459] In this invention, the server includes means for accepting input from a user, means for transmitting the accepted input to the server, means for analyzing data based on the received input, means for applying a generative AI model that generates predictive information using the analysis results, and means for providing the generated predictive information to the user, thereby enabling the user to easily request a fortune telling and obtain a quick and accurate result.

[0460] "User" refers to an individual or organization that uses this system.

[0461] "Means for accepting input" refers to devices or software that provide an interface for users to input or upload data for fortune-telling purposes.

[0462] "Means for sending input to a server" refers to a device or software with a communication function for sending data entered by a user to a server.

[0463] "Means for analyzing data" refers to software or algorithms that the server uses to process the data received from the user and extract the necessary information.

[0464] A "generative AI model that generates predictive information using analysis results" is an artificial intelligence model that generates fortune-telling results and predictive information based on analyzed data.

[0465] "Means for generating predictive information" refers to software or algorithms that use a generative AI model to output specific fortune-telling results or predictive information from the analysis results.

[0466] "Means for providing generated predictive information to users" refers to devices or software equipped with an interface and communication functions for conveying the information output by the generative AI model to users.

[0467] "Means for analyzing image data" refers to software or algorithms that use image recognition technology to process image data provided by users and extract necessary features.

[0468] A "generative AI model that uses prompts based on machine learning algorithms" is an artificial intelligence model that uses machine learning technology to generate appropriate responses or predictions for specific inputs.

[0469] The present invention relates to a system for users to request fortune-telling. This system is configured using a user's terminal (for example, a smartphone or PC) and a server.

[0470] The user uses the device to select the type of fortune-telling (palm reading, tarot card reading, etc.) and input or upload the necessary data. For example, for palm reading, the user can take and upload a photo of their palm. For tarot reading, the user can input the card arrangement data.

[0471] The device receives the data entered by the user, converts it into an appropriate format (e.g., JSON format) as an API request, and sends it to the server. This transmission uses Internet communication.

[0472] The server analyzes the received API request and checks the data content. In the case of palmistry, the server uses image recognition technology (e.g., OpenCV) to extract palm features (such as life lines and fate lines). This extracted feature data is input into a generative AI model (e.g., GPT-4).

[0473] The generative AI model uses machine learning algorithms to generate fortune-telling results and predictions by referencing past data and statistical information. For example, in the case of palmistry, by entering a prompt such as "Please analyze a palm with a long, clear life line. What does that mean?", the generative model will generate a result such as "Your life line is very long, so you have good health."

[0474] In the case of tarot readings, the AI ​​model is given a prompt based on the placement data of the tarot cards: "The current card is the Tower, and the future card is the Sun. Please generate a fortune-telling result based on these placements." In this case, it generates prediction information such as, "Because the current card is the Tower, now is a time of change."

[0475] The generated prediction information is sent from the server to the device as an API response. The device analyzes the received API response and displays the fortune-telling results in a format that is easy for the user to understand.

[0476] The user can check the displayed fortune-telling results and request a more detailed fortune-telling or a new fortune-telling if necessary. This system provides an environment where users can receive fortune-telling easily, quickly, and accurately.

[0477] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0478] Step 1:

[0479] The user selects the type of fortune-telling they want and inputs or uploads the necessary data: for palm reading, they take a photo of their palm, and for tarot reading, they input the card layout data. Then, the user confirms their fortune-telling request.

[0480] Input: Type of fortune telling and related data (palm reading photo or tarot card placement data)

[0481] Output: User selections and input data

[0482] Step 2:

[0483] The terminal receives the data entered by the user and sends it to the server as an API request, where the data is converted into an appropriate format (e.g., JSON).

[0484] Input: User-selected and entered data

[0485] Output: API request to the server

[0486] Step 3:

[0487] The server analyzes the received API request and checks the data content. In the case of palmistry, it analyzes a photo of the palm using image recognition technology to extract features. In the case of tarot readings, it analyzes the card placement data.

[0488] Input: API request sent from the device

[0489] Output: Palm reading data or tarot card layout data

[0490] Step 4:

[0491] The server inputs the extracted feature data and placement data into the generative AI model, generates prompt sentences, and inputs them into the model to generate prediction information.

[0492] Input: Palm reading data or tarot card placement data, prompt text

[0493] Output: Predictions from the generative AI model

[0494] Step 5:

[0495] The server receives the generated prediction information and sends it to the device as an API response, which is then formatted appropriately.

[0496] Input: Prediction information from a generative AI model

[0497] Output: API response to the device

[0498] Step 6:

[0499] The device analyzes the API response received from the server and displays the fortune-telling results in a format that is easy for the user to understand. The user can then check the displayed results and request a more detailed fortune-telling or a new fortune-telling.

[0500] Input: API response from the server

[0501] Output: Display fortune-telling results to the user

[0502] These steps allow users to easily obtain quick and accurate fortune-telling results.

[0503] (Application example 1)

[0504] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0505] Conventional fortune-telling systems often took a long time for users to receive their fortune-telling results, and they often lacked consistency and reliability. Face-to-face fortune-telling also had limitations on location and time, making it difficult for many users to use. Another issue was the lack of established technology for accurately analyzing image data from palmistry and tarot cards.

[0506] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0507] In this invention, the server includes means for processing input data for providing fortune-telling results using image recognition technology, means for inputting prompt sentences based on specific categories into a generative AI model, and means for providing consistent and reliable fortune-telling results online, thereby enabling users to quickly obtain consistent and reliable fortune-telling results regardless of location or time.

[0508] "User" refers to any individual or organization that uses the fortune-telling service.

[0509] "Means for accepting input" refers to the interface or function that allows users to input the information they want to know and the necessary data.

[0510] "Analysis tools" refers to the techniques and algorithms used to process data received from users and extract meaningful information.

[0511] "Means for applying generative models" refers to the function of applying machine learning models or AI to generate fortune-telling prediction information based on analyzed data.

[0512] "Means for providing predictive information" refers to the interface and functions for communicating the generated fortune-telling results to users.

[0513] "Image recognition technology" refers to the technology used to analyze image data and extract features. Specifically, it is used to extract palm lines and other features.

[0514] "Prompt" means a text-formatted instruction given to a generative AI model, including instructions based on a specific category.

[0515] "Consistent and reliable fortune-telling results" refers to fortune-telling results that always provide the same results for the same input and that have the reliability to be accepted by many people.

[0516] "Online delivery means" refers to the technologies and functions used to provide services to users via the Internet.

[0517] This invention relates to an online fortune-telling system that can be used by users. This system is composed of a user terminal and a server, and is capable of quickly and consistently providing fortune-telling results such as palm reading and tarot card reading.

[0518] The server includes a means for processing input data using image recognition technology to provide fortune-telling results. Specifically, it receives palm reading photos and tarot card layout data provided by users, analyzes those images, and extracts features. Deep learning frameworks such as TensorFlow and Keras are used for this analysis.

[0519] Next, there is a way to input prompt sentences based on specific categories into the generative AI model. For example, in the case of palm reading, the server generates prompt sentences of the following form based on features extracted from a palm image:

[0520] It analyzes the palm image provided by the user and generates a fortune-telling result based on the following palm characteristics:

[0521] If the lifeline is long, you have good health.

[0522] If your fate line is clear, you have good luck in your career.

[0523] ...

[0524] Based on your palm reading, please provide your reading in the following format:

[0525] "Your lifeline is {length}. Your health is {fortune_level}."

[0526] Image data URL: {img_url}

[0527] This prompt is input into a generative model using deep learning, such as GPT (Generative Pretrained Transformer), to generate a specific fortune-telling result.

[0528] The generated fortune-telling results are sent from the server to the user's device and displayed to the user via an interface. This process uses API requests and responses. The front-end portion is built using cross-platform development frameworks such as React Native, and users can upload photos of their palms and view fortune-telling results through the app.

[0529] As a concrete example, consider the case where a user selects palm reading and takes and uploads a photo of their palm with their smartphone. This photo is sent to the server as an API request. The server analyzes the photo using image recognition technology to extract the characteristics of the palm lines. The generative model then predicts the fortune-telling result, generating something like, "Your lifeline is very long, so you have good health." This result is sent back to the user's device as an API response and displayed through the app.

[0530] In this way, the present invention provides a system that allows users to quickly obtain highly reliable fortune-telling results regardless of location or time.

[0531] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0532] Step 1:

[0533] A user uses a device to access a fortune-telling application. The device displays a user interface and provides options for selecting categories, such as palmistry or tarot reading. The user selects the type of reading and uploads a photo of their palm. The input data is an image file of the palm.

[0534] Step 2:

[0535] The device receives the palm print photo uploaded by the user and sends it to the server as an API request. Specifically, the image file is sent to the server as form data via an HTTP POST request. At this stage, the input is the palm print image data, and the output is the API request sent to the server.

[0536] Step 3:

[0537] The server analyzes the received palm image data. As a first step, it uses image recognition technology to extract palm features. Specifically, it uses deep learning frameworks such as TensorFlow and Keras to identify palm features such as life lines and fate lines. The results of this analysis become the input data for the next step. The output of the analysis is the extracted palm feature data.

[0538] Step 4:

[0539] The server generates a prompt sentence based on the extracted feature data. For example, it creates a sentence to input to the generative AI model to prompt the generation of a fortune-telling result, such as "Your lifeline is long and you have good health." The input to this prompt sentence is the extracted palm feature data, and the output is the prompt sentence to input to the generative AI model.

[0540] Step 5:

[0541] The server generates fortune-telling results using a generative AI model. A specific prompt is input into the model, which predicts and generates fortune-telling results based on past data and statistical information. The input at this stage is the prompt, and the output is the generated fortune-telling result text.

[0542] Step 6:

[0543] The generated fortune-telling result is sent from the server to the device as an API response. Specifically, it is sent as an HTTP response and the result is encoded in JSON format. The input of this step is the generated fortune-telling result text, and the output is the API response sent to the device.

[0544] Step 7:

[0545] The terminal interprets the received fortune-telling results and displays them through a user interface. The user can then review the displayed fortune-telling results and request further fortune-telling or try other fortune-telling methods. The input at this stage is the text fortune-telling results received from the server, and the output is the result displayed to the user.

[0546] This series of processing steps allows users to obtain quick, consistent, and reliable fortune-telling results regardless of location or time.

[0547] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0548] This invention relates to a system that uses a generative model that accepts and analyzes input from a user to generate predictive information, and provides that predictive information to the user. This system also combines an emotion engine that recognizes the user's emotions, and provides fortune-telling results and predictive information according to the user's emotions.

[0549] System Configuration

[0550] This system is composed of a terminal (for example, a smartphone or PC), a server, and an emotion engine. The following is a specific embodiment of the system.

[0551] The device provides a user interface and accepts the desired fortune-telling content and necessary data (for example, palm reading images or tarot card placement data). It also monitors the user's input and facial expressions to collect emotional data, which becomes the basis for the emotion engine to analyze the user's emotions.

[0552] The server receives and analyzes the data sent from the device. Specifically, it analyzes palm reading and tarot card data and extracts its characteristics. The emotion engine analyzes the user's emotions based on this data and provides emotional information. This emotional information is input into a generative model and used to generate fortune-telling results and prediction information.

[0553] Generative models are based on machine learning algorithms and generate predictions based on historical data and statistical information. These predictions are tailored to the user's emotions and presented in an appropriate format. For example, if the user is feeling anxious, the predictions can be presented in a more gentle way.

[0554] Example 1: Palmistry and Emotion Recognition

[0555] 1. The user selects palm reading on the device and uploads a photo of their palm. At the same time, facial expression data of the user is collected via the camera.

[0556] 2. The device sends the palm image data and facial expression data to the server.

[0557] 3. The server extracts features from the palm image and inputs them into the generative model. At the same time, the emotion engine analyzes the user's emotions using facial expression data.

[0558] 4. The emotion engine detects the user's emotional state (e.g., "anxiety") and provides that information to the generative model.

[0559] 5. The generative model generates fortune-telling results based on the palmistry characteristics and the user's emotions, outputting content such as, "Your lifeline is very long and you have good health. You may be feeling anxious at the moment, but things will improve in the future."

[0560] 6. The server sends the generated fortune-telling result to the terminal.

[0561] 7. The device displays the received fortune-telling results to the user, who can then confirm the results and select the next action.

[0562] Example 2: Tarot reading and emotion recognition

[0563] 1. The user selects tarot reading and inputs the card placement data. In addition, facial expression data is collected by camera.

[0564] 2. The device sends the position data and facial expression data to the server.

[0565] 3. The server analyzes the placement data and extracts its features. At the same time, the emotion engine analyzes emotions based on the facial expression data.

[0566] 4. The emotion engine detects the user's emotions (e.g., "joy") and provides that information to the generative model.

[0567] 5. The generative model generates fortune-telling results based on the placement of the tarot cards and the user’s emotions, for example, “Since the current card is ‘The Sun,’ a very positive fortune is predicted. Your mood also seems to be lifted, and you feel confident about the future.”

[0568] 6. The server sends the generated results to the terminal.

[0569] 7. The device displays the results to the user and allows them to choose their next action.

[0570] In this way, by combining this system with an emotion engine, it is possible to provide fortune-telling results that correspond to the user's emotions, realizing a more personalized experience.

[0571] The processing flow will be explained below.

[0572] Step 1:

[0573] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[0574] Step 2:

[0575] Users use the device's camera to take a photo of their palm and simultaneously collect facial expression data.

[0576] Step 3:

[0577] The device sends palm image data and facial expression data to the server as an API request.

[0578] Step 4:

[0579] The server receives the API request sent from the terminal.

[0580] Step 5:

[0581] The server passes the palm image data to an image processing module, which extracts palm features (life line, fate line, etc.).

[0582] Step 6:

[0583] The server passes the facial expression data to an emotion engine to analyze the user's emotional state. For example, it uses facial expression recognition technology to detect whether the user is in an "anxious" state.

[0584] Step 7:

[0585] The server inputs the extracted palm feature data and analyzed emotional information into a generative AI model.

[0586] Step 8:

[0587] The generative AI model generates fortune-telling results based on palmistry feature data and emotional information, such as, "Your lifeline is very long, and you have good health. You may be feeling anxious at present, but things will improve in the future."

[0588] Step 9:

[0589] The server sends the generated fortune-telling result to the terminal as an API response.

[0590] Step 10:

[0591] The terminal receives the API response from the server and analyzes the response data.

[0592] Step 11:

[0593] The device then displays the analyzed fortune-telling results on the user interface, for example in a gentle tone.

[0594] Step 12:

[0595] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0596] Example 2: Tarot reading and emotion recognition

[0597] Step 1:

[0598] The user selects tarot reading on the terminal and enters the card placement data.

[0599] Step 2:

[0600] Users use the device's camera to collect facial expression data.

[0601] Step 3:

[0602] The device sends the tarot card placement data and facial expression data to the server as an API request.

[0603] Step 4:

[0604] The server receives the API request sent from the terminal.

[0605] Step 5:

[0606] The server analyzes the tarot card arrangement data and extracts its characteristics.

[0607] Step 6:

[0608] The server passes the facial expression data to an emotion engine to analyze the user's emotions. For example, it uses facial expression recognition technology to detect whether the user is in a "happy" state.

[0609] Step 7:

[0610] The server inputs the extracted tarot card feature data and analyzed emotional information into the generative AI model.

[0611] Step 8:

[0612] The generative AI model generates fortune-telling results based on the tarot card placement feature data and emotional information, such as, "Because the current card is the 'Sun,' a very positive fortune is predicted. Your mood seems to be lifted, and you feel confident about the future."

[0613] Step 9:

[0614] The server sends the generated fortune-telling result to the terminal as an API response.

[0615] Step 10:

[0616] The terminal receives the API response from the server and analyzes the response data.

[0617] Step 11:

[0618] The device then displays the analyzed fortune-telling results on the user interface, for example, in a positive tone that matches the user's emotions.

[0619] Step 12:

[0620] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0621] Example 2

[0622] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0623] Conventional prediction systems were unable to take the user's emotional state into account when providing predictive information based on user input data. This made it difficult to provide flexible predictions that reflected the user's current emotions, resulting in poor acceptability of the prediction results.

[0624] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information based on the analysis result and the emotional state of the user, and means for providing the generated predictive information to the user. This makes it possible to provide appropriate predictive information according to the user's emotions.

[0625] "User" refers to the person who operates the system and inputs data.

[0626] "Input" refers to data or information provided by a user to a system.

[0627] "Analysis" refers to the process of extracting features and meaning from input data.

[0628] "Emotional state" refers to a user's current emotional state or psychological condition.

[0629] A "generative model" refers to an algorithm or system that generates predictive information from input data and analysis results.

[0630] "Predictive information" refers to future outlooks and fortune-telling results generated based on analyzed data.

[0631] "Providing" refers to displaying the generated forecast information to the user.

[0632] "Server" refers to a computer system that receives data, analyzes it, applies generative models, and provides prediction information.

[0633] "Terminal" refers to a device (e.g., a smartphone or PC) that a user operates and uses to provide input data.

[0634] "Image data" refers to photo and video data provided by users.

[0635] A "machine learning algorithm" refers to a computational method for training a model based on data and making predictions and classifications.

[0636] This invention relates to a system that accepts and analyzes input data from a user, evaluates the user's emotional state using an emotion recognition engine, and generates and provides predictive information based on that information. This system consists of a terminal (such as a smartphone or PC), a server, and an emotion recognition engine.

[0637] Overview of program processing

[0638] This system performs the following processes:

[0639] 1. Accepting user input

[0640] Users use the application on their device to select palm reading or tarot card reading, and input a photo of their palm and tarot card placement data, while facial expression data is collected via the camera.

[0641] 2. Data transmission

[0642] The device sends the data entered by the user to a server using an internet connection.

[0643] 3. Server-side data analysis

[0644] The server analyzes the received data. For palm reading image data, image analysis software (e.g., OpenCV) is used to extract features, and for tarot card placement data, a proprietary algorithm is used.

[0645] 4. Emotion analysis

[0646] An emotion recognition engine analyzes facial expression data to assess the user's emotional state, using deep learning models (e.g., Emotion Recognition API).

[0647] 5. Generating Predictive Information Using Generative Models

[0648] The generative model generates predictions based on emotion information and palm reading or tarot data. This generative model uses machine learning algorithms (e.g., TensorFlow). The predictions are adjusted according to the user's emotions.

[0649] 6. Sending and displaying results

[0650] The server transmits the generated forecast information to the terminal, which displays the information to the user.

[0651] Hardware and software used

[0652] Devices: Smartphones, PCs, webcams

[0653] Server: High-performance processor, large storage capacity

[0654] Image analysis software: OpenCV

[0655] Emotion Recognition Engine: Emotion Recognition API

[0656] Machine learning framework: TensorFlow

[0657] Specific examples

[0658] Example 1: Palmistry

[0659] 1. The user selects palm reading through the app, takes a photo of their palm and uploads it, while facial expression data is also collected.

[0660] 2. The device sends the palm image and facial expression data to the server.

[0661] 3. The server analyzes the palm image using OpenCV and evaluates the emotion using an emotion recognition engine.

[0662] 4. The generative model generates the fortune-telling results, creating a message such as, "Your lifeline is very long and you have good health. You may be feeling anxious now, but things will improve in the future."

[0663] 5. The server sends the results to the terminal, which displays them to the user.

[0664] Prompt Sentence Examples

[0665] "Upload an image of your palm and we'll give you a fortune reading based on that image. The reading will be adjusted according to your current emotional state."

[0666] Example 2: Tarot reading

[0667] 1. The user selects tarot reading and inputs the card placement data. Facial expression data is also collected at the same time.

[0668] 2. The device sends the position data and facial expression data to the server.

[0669] 3. The server analyzes the placement data and evaluates the emotion using an emotion recognition engine.

[0670] 4. The generative model generates the fortune-telling result, creating a message such as, "Since your current card is the Sun, a very positive fortune is predicted. Your spirits seem to be lifted and you feel confident about the future."

[0671] 5. The server sends the results to the terminal, which displays them to the user.

[0672] Prompt Sentence Examples

[0673] "Enter your tarot card placement data. We will predict your fortune based on that placement. The results will be adjusted according to your current emotions."

[0674] In this way, the present invention provides appropriate predictive information according to the user's emotions, realizing a more personalized experience.

[0675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0676] Step 1:

[0677] The user opens the application on the device and selects the type of fortune-telling (palm reading or tarot card reading). Then, for palm reading, the user takes a photo of their palm, and for tarot reading, the user inputs the card arrangement data. Furthermore, facial expression data is automatically collected via the camera. The user's palm image, tarot card arrangement data, and facial expression data are then input.

[0678] Input: Palm reading image or tarot card placement data, and facial expression data

[0679] Output: A set of palm reading images or tarot card layout data and facial expression data

[0680] Specific behavior:

[0681] The user opens the app.

[0682] Choose palm reading or tarot reading (through UI).

[0683] For palm reading, open the camera and take a photo of your palm.

[0684] For tarot, the card placement is entered manually.

[0685] To collect facial expression data, the camera is activated and a picture of the user's facial expression is taken.

[0686] Step 2:

[0687] The terminal transmits the palm reading image, tarot card placement data, and facial expression data collected from the user to the server. This transmission is performed via internet communication. The data is sent in a single packet.

[0688] Input: A set of palm reading images or tarot card layout data and facial expression data

[0689] Output: Palm reading image or tarot card placement data and facial expression data sent to the server

[0690] Specific behavior:

[0691] The collected data is organized into packets.

[0692] Send an HTTP POST request to the server's URL over your internet connection.

[0693] Step 3:

[0694] The server receives the data sent from the device and analyzes each data. For palm reading images, image analysis software (e.g., OpenCV) is used, and for tarot card placement data, a proprietary algorithm is used to extract features. For facial expression data, an emotion recognition engine is used to analyze emotions.

[0695] Input: Palm reading image or tarot card placement data, and facial expression data

[0696] Output: Palmistry feature data, Tarot feature data, and emotional state data

[0697] Specific behavior:

[0698] The server receives the data packets and passes them to a module for analysis.

[0699] The palm image is analyzed using OpenCV to extract palm line features.

[0700] Analyze tarot placement data and extract card characteristics.

[0701] An emotion recognition engine is used to analyze facial expression data and detect emotional states (e.g., "anxiety" or "joy").

[0702] Step 4:

[0703] The server inputs the emotional information obtained from the emotion engine and the analyzed palm reading and tarot data into a generative model. The generative model uses a machine learning framework (e.g., TensorFlow) to generate fortune-telling results based on past data and statistical information. Furthermore, the generated results are adjusted according to the user's emotional state.

[0704] Input: Palmistry feature data, Tarot feature data, and emotional state data

[0705] Output: Predictive information adjusted based on emotions

[0706] Specific behavior:

[0707] Emotion information and palm or tarot data are input into the generative model.

[0708] Use TensorFlow to generate prediction information.

[0709] Tailor predictive information to the user's emotional state.

[0710] Step 5:

[0711] The server sends the fortune-telling results generated by the generative model to the device. This is done via internet communication again. The data is converted into a format that is easy for the device to understand (e.g., JSON format) and then sent.

[0712] Input: Emotionally adjusted prediction information

[0713] Output: Fortune telling results sent to the device

[0714] Specific behavior:

[0715] The generated fortune-telling results are collected into a packet.

[0716] Send it to your device via your internet connection.

[0717] Step 6:

[0718] The terminal displays the fortune-telling results received from the server to the user. The user can check the results and select the next action. The fortune-telling results are displayed in a format suitable for the user's terminal.

[0719] Input: Fortune telling result sent from the server

[0720] Output: Fortune telling result displayed to the user

[0721] Specific behavior:

[0722] Analyze the data received from the server and reflect the results in the display UI.

[0723] The user sees the results on the device screen.

[0724] (Application example 2)

[0725] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0726] Current predictive information systems have difficulty providing personalized information based on the user's emotions. Furthermore, rather than simply analyzing data, it is necessary to provide more accurate counseling and fortune-telling results by providing feedback based on emotions.

[0727] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information using the analysis results, means for analyzing emotions based on the generated predictive information, means for generating predictive information based on the analyzed emotional information, and means for providing the generated predictive information to the user. This makes it possible to provide personalized predictive information based on the user's emotions.

[0728] "User" refers to a person who uses the system.

[0729] "Input" refers to the data or information that a user provides to a system.

[0730] "Analysis" refers to the process of extracting information from input data and drawing specific conclusions or predictions.

[0731] A "generative model" refers to a computational model for generating predictive information using a machine learning algorithm.

[0732] "Predictive information" refers to information about future events or trends that is generated based on analytical results.

[0733] "Emotion analysis" refers to the process of determining a user's emotional state from facial expression data and other inputs.

[0734] "Emotional information" refers to data about a user's emotional state obtained through emotion analysis.

[0735] "Personalization" refers to tailoring information to each individual user's specific needs and feelings.

[0736] "Image data" refers to visual information provided in the form of still images or video.

[0737] A "machine learning algorithm" refers to a computational method that learns patterns from data and makes predictions or decisions based on them.

[0738] The system for realizing this invention is composed of the following program: This program analyzes data entered by a user, uses a machine learning algorithm to generate predictive information based on emotion information, and provides it to the user.

[0739] Hardware used

[0740] Device: Smartphone, tablet, or computer

[0741] Display devices: smart glasses, head-mounted displays

[0742] Analysis server: A high-performance calculation server (e.g., an EC2 instance on Amazon Web Services (AWS))

[0743] Software used

[0744] Facial expression recognition library: OpenCV

[0745] Sentiment analysis engine: Microsoft Azure Cognitive Services

[0746] Machine learning libraries: TensorFlow, PyTorch

[0747] Database: MongoDB, MySQL

[0748] Program processing flow

[0749] 1. The user uses the device to input the data they wish to receive for fortune telling or counseling. The input data includes the user's text information and image data required for fortune telling.

[0750] 2. The device uses the user's camera to collect facial expression data in real time, which is then used for later analysis.

[0751] 3. The analysis server receives the input data and facial expression data sent from the device. The facial expression data is analyzed using OpenCV to extract the emotional state.

[0752] 4. Microsoft Azure Cognitive Services, an emotion analysis engine, quantitatively evaluates the emotional state based on the extracted facial expression data and generates emotional information.

[0753] 5. Use a machine learning library (TensorFlow or PyTorch) to generate predictions based on the sentiment and user-supplied data, referencing historical data and statistical information to obtain more accurate results.

[0754] 6. The generated forecast information is provided to the user via the terminal.

[0755] Specific use cases

[0756] Consider a case where a user selects a relaxation menu at a relaxation salon. The user selects palm reading on their device and uploads a photo of their palm. At this time, the smart glasses also collect the user's facial expression data in real time. The server analyzes the palm image and simultaneously performs emotion analysis using the facial expression data. Using the generative model, the server generates a result such as, "Your lifeline is very long and you have good health luck. You may be feeling anxious at present, but things will improve in the future," and displays this result to the user.

[0757] Prompt Sentence Examples

[0758] Below is an example of a prompt for this system:

[0759] Customer facial expression data: {facial expression data}

[0760] Customer emotions: Anxiety, tension

[0761] Past counseling data: {Past data}

[0762] What I want: I want to relax

[0763] --Generative Model Prompt--

[0764] Generate personalized relaxation menus and counseling content based on the customer's emotional state.

[0765] In this way, the system combines highly accurate emotion analysis with predictive information to provide users with personalized information.

[0766] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0767] Step 1:

[0768] The device accepts input from the user regarding their desired fortune-telling or counseling. Specifically, the user uploads text information or image data (e.g., a photo of their palm) to the device. The input data is stored in a local database for subsequent analysis.

[0769] Step 2:

[0770] The device collects the user's facial expression data in real time. It divides the video data captured by the camera into frames and uses the OpenCV library to perform facial recognition and extract feature points. It analyzes the facial feature points and generates numerical data of the facial expression data.

[0771] Step 3:

[0772] The device sends the collected input data and facial expression data to the analysis server. The transmitted data is sent to the server's analysis engine via an API. The input data includes the user's text information, image data, and facial expression data.

[0773] Step 4:

[0774] The server receives the data sent from the device and first analyzes the image data. Specifically, the server uses an image recognition algorithm to extract the palm's characteristic points and convert them into numerical data. For image recognition, a deep learning model (e.g., VGG16 or ResNet) is used.

[0775] Step 5:

[0776] The server uses an emotion analysis engine (Microsoft Azure Cognitive Services) to analyze the facial expression data and identify the user's emotional state. Based on the facial expression data received as input, it determines the type of emotion (e.g., joy, anxiety, sadness) and outputs the emotional information as numerical data.

[0777] Step 6:

[0778] The server runs a generative model using a machine learning library (TensorFlow or PyTorch). Based on the palm reading data and emotion information received as input, the generative model generates predictions. The predictions (e.g., fortune-telling results or counseling advice) are generated by the generative AI model.

[0779] Step 7:

[0780] The server sends the generated forecast information to the device using the REST API in JSON format. The device then displays the received forecast information to the user.

[0781] Step 8:

[0782] The device provides users with predictive information and allows them to select their next action based on that information, for example, by providing an interactive UI for users to select a relaxation menu or request further counseling.

[0783] In this way, through the processing steps, personalized prediction information according to the user's emotions is provided.

[0784] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0785] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0786] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0787] [Third embodiment]

[0788] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0789] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0790] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0791] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0792] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0793] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0794] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0795] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0796] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0797] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0798] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0799] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0800] The present invention relates to a system including an input means for a user to request a fortune telling, an analysis means for analyzing the received input, a generative model that generates predictive information using the analysis results, and a means for providing the generated predictive information to the user.

[0801] This system consists of a user's device (e.g., a smartphone or PC) and a server. The device provides the user interface and accepts the desired fortune-telling content and necessary data (e.g., palm reading images and tarot card placement data). The device then creates an API request to send the accepted data to the server.

[0802] The server analyzes the received API request and performs the necessary data processing based on the user's input. Specifically, image recognition technology is used to extract palmistry features and input these features into a generative model. The generative model is based on a machine learning algorithm and generates predictive information by referencing past data and statistical information. For example, if the lifeline on the palm is long, the resulting fortune-telling result will indicate good health.

[0803] The generated prediction information is sent from the server to the device as an API response. The device displays the received prediction information to the user, providing consistent fortune-telling results. The user can check the displayed results, request further fortune-telling, or try different fortune-telling methods.

[0804] Example 1: Palmistry

[0805] The user selects palm reading on their device and uploads a photo of their palm. This photo is sent to the server as an API request. The server analyzes the image and extracts palm features such as life lines and fate lines. The extracted feature data is input into a generative model, which generates a fortune-telling result. For example, it generates prediction information such as "Your life line is very long, so you have good health." This information is sent back to the device as an API response and displayed to the user.

[0806] Example 2: Tarot reading

[0807] The user selects tarot reading using their device and inputs the card placement data. This placement data is sent to the server as an API request. The server analyzes the tarot card placement and generates a fortune-telling result based on that placement using a generative model. For example, it generates prediction information such as "Since the current card is 'The Tower,' now is a time for change." This information is also sent back to the device as an API response and displayed to the user.

[0808] In this way, our system applies appropriate analysis and generative models depending on the type of fortune-telling requested by the user, providing fast and accurate fortune-telling results. Users can easily receive consistent and reliable fortune-telling results regardless of time or place.

[0809] The processing flow will be explained below.

[0810] Step 1:

[0811] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[0812] Step 2:

[0813] The user uploads a photo of their palm to the device and presses the "Perform fortune telling" button.

[0814] Step 3:

[0815] The device receives input from the user and composes palm image data and a fortune-telling request (e.g., "palm reading") as an API request.

[0816] Step 4:

[0817] The device sends the configured API request to the server.

[0818] Step 5:

[0819] The server receives an API request from the terminal and analyzes the request content to identify the fortune-telling method (palm reading) selected by the user and the image data provided.

[0820] Step 6:

[0821] The server invokes an image processing module to analyze the palm image, specifically applying image recognition algorithms to extract key palm features (e.g., life line, fate line, etc.).

[0822] Step 7:

[0823] The server inputs the extracted palm line feature data into a generative AI model, which is trained using machine learning algorithms and generates fortune-telling results based on this data.

[0824] Step 8:

[0825] The server formats the generated fortune-telling result in text format and composes it as an API response.

[0826] Step 9:

[0827] The server sends the constructed API response to the device.

[0828] Step 10:

[0829] The terminal receives the API response from the server and analyzes the response data.

[0830] Step 11:

[0831] The device then displays the analyzed fortune-telling results on the user interface, such as "Your lifeline is very long, so you have good health."

[0832] Step 12:

[0833] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0834] In this way, a series of processes that allows the user to easily obtain fortune-telling results is completed.

[0835] Example 1

[0836] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0837] In conventional fortune-telling systems, when users request a fortune, they must manually input and analyze data, which takes time and effort. There are also issues with the reliability and consistency of the results. This makes it difficult for users to easily obtain quick, accurate fortune-telling results.

[0838] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0839] In this invention, the server includes means for accepting input from a user, means for transmitting the accepted input to the server, means for analyzing data based on the received input, means for applying a generative AI model that generates predictive information using the analysis results, and means for providing the generated predictive information to the user, thereby enabling the user to easily request a fortune telling and obtain a quick and accurate result.

[0840] "User" refers to an individual or organization that uses this system.

[0841] "Means for accepting input" refers to devices or software that provide an interface for users to input or upload data for fortune-telling purposes.

[0842] "Means for sending input to a server" refers to a device or software with a communication function for sending data entered by a user to a server.

[0843] "Means for analyzing data" refers to software or algorithms that the server uses to process the data received from the user and extract the necessary information.

[0844] A "generative AI model that generates predictive information using analysis results" is an artificial intelligence model that generates fortune-telling results and predictive information based on analyzed data.

[0845] "Means for generating predictive information" refers to software or algorithms that use a generative AI model to output specific fortune-telling results or predictive information from the analysis results.

[0846] "Means for providing generated predictive information to users" refers to devices or software equipped with an interface and communication functions for conveying the information output by the generative AI model to users.

[0847] "Means for analyzing image data" refers to software or algorithms that use image recognition technology to process image data provided by users and extract necessary features.

[0848] A "generative AI model that uses prompts based on machine learning algorithms" is an artificial intelligence model that uses machine learning technology to generate appropriate responses or predictions for specific inputs.

[0849] The present invention relates to a system for users to request fortune-telling. This system is configured using a user's terminal (for example, a smartphone or PC) and a server.

[0850] The user uses the device to select the type of fortune-telling (palm reading, tarot card reading, etc.) and input or upload the necessary data. For example, for palm reading, the user can take and upload a photo of their palm. For tarot reading, the user can input the card arrangement data.

[0851] The device receives the data entered by the user, converts it into an appropriate format (e.g., JSON format) as an API request, and sends it to the server. This transmission uses Internet communication.

[0852] The server analyzes the received API request and checks the data content. In the case of palmistry, the server uses image recognition technology (e.g., OpenCV) to extract palm features (such as life lines and fate lines). This extracted feature data is input into a generative AI model (e.g., GPT-4).

[0853] The generative AI model uses machine learning algorithms to generate fortune-telling results and predictions by referencing past data and statistical information. For example, in the case of palmistry, by entering a prompt such as "Please analyze a palm with a long, clear life line. What does that mean?", the generative model will generate a result such as "Your life line is very long, so you have good health."

[0854] In the case of tarot readings, the AI ​​model is given a prompt based on the placement data of the tarot cards: "The current card is the Tower, and the future card is the Sun. Please generate a fortune-telling result based on these placements." In this case, it generates prediction information such as, "Because the current card is the Tower, now is a time of change."

[0855] The generated prediction information is sent from the server to the device as an API response. The device analyzes the received API response and displays the fortune-telling results in a format that is easy for the user to understand.

[0856] The user can check the displayed fortune-telling results and request a more detailed fortune-telling or a new fortune-telling if necessary. This system provides an environment where users can receive fortune-telling easily, quickly, and accurately.

[0857] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0858] Step 1:

[0859] The user selects the type of fortune-telling they want and inputs or uploads the necessary data: for palm reading, they take a photo of their palm, and for tarot reading, they input the card layout data. Then, the user confirms their fortune-telling request.

[0860] Input: Type of fortune telling and related data (palm reading photo or tarot card placement data)

[0861] Output: User selections and input data

[0862] Step 2:

[0863] The terminal receives the data entered by the user and sends it to the server as an API request, where the data is converted into an appropriate format (e.g., JSON).

[0864] Input: User-selected and entered data

[0865] Output: API request to the server

[0866] Step 3:

[0867] The server analyzes the received API request and checks the data content. In the case of palmistry, it analyzes a photo of the palm using image recognition technology to extract features. In the case of tarot readings, it analyzes the card placement data.

[0868] Input: API request sent from the device

[0869] Output: Palm reading data or tarot card layout data

[0870] Step 4:

[0871] The server inputs the extracted feature data and placement data into the generative AI model, generates prompt sentences, and inputs them into the model to generate prediction information.

[0872] Input: Palm reading data or tarot card placement data, prompt text

[0873] Output: Predictions from the generative AI model

[0874] Step 5:

[0875] The server receives the generated prediction information and sends it to the device as an API response, which is then formatted appropriately.

[0876] Input: Prediction information from a generative AI model

[0877] Output: API response to the device

[0878] Step 6:

[0879] The device analyzes the API response received from the server and displays the fortune-telling results in a format that is easy for the user to understand. The user can then check the displayed results and request a more detailed fortune-telling or a new fortune-telling.

[0880] Input: API response from the server

[0881] Output: Display fortune-telling results to the user

[0882] These steps allow users to easily obtain quick and accurate fortune-telling results.

[0883] (Application example 1)

[0884] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0885] Conventional fortune-telling systems often took a long time for users to receive their fortune-telling results, and they often lacked consistency and reliability. Face-to-face fortune-telling also had limitations on location and time, making it difficult for many users to use. Another issue was the lack of established technology for accurately analyzing image data from palmistry and tarot cards.

[0886] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0887] In this invention, the server includes means for processing input data for providing fortune-telling results using image recognition technology, means for inputting prompt sentences based on specific categories into a generative AI model, and means for providing consistent and reliable fortune-telling results online, thereby enabling users to quickly obtain consistent and reliable fortune-telling results regardless of location or time.

[0888] "User" refers to any individual or organization that uses the fortune-telling service.

[0889] "Means for accepting input" refers to the interface or function that allows users to input the information they want to know and the necessary data.

[0890] "Analysis tools" refers to the techniques and algorithms used to process data received from users and extract meaningful information.

[0891] "Means for applying generative models" refers to the function of applying machine learning models or AI to generate fortune-telling prediction information based on analyzed data.

[0892] "Means for providing predictive information" refers to the interface and functions for communicating the generated fortune-telling results to users.

[0893] "Image recognition technology" refers to the technology used to analyze image data and extract features. Specifically, it is used to extract palm lines and other features.

[0894] "Prompt" means a text-formatted instruction given to a generative AI model, including instructions based on a specific category.

[0895] "Consistent and reliable fortune-telling results" refers to fortune-telling results that always provide the same results for the same input and that have the reliability to be accepted by many people.

[0896] "Online delivery means" refers to the technologies and functions used to provide services to users via the Internet.

[0897] This invention relates to an online fortune-telling system that can be used by users. This system is composed of a user terminal and a server, and is capable of quickly and consistently providing fortune-telling results such as palm reading and tarot card reading.

[0898] The server includes a means for processing input data using image recognition technology to provide fortune-telling results. Specifically, it receives palm reading photos and tarot card layout data provided by users, analyzes those images, and extracts features. Deep learning frameworks such as TensorFlow and Keras are used for this analysis.

[0899] Next, there is a way to input prompt sentences based on specific categories into the generative AI model. For example, in the case of palm reading, the server generates prompt sentences of the following form based on features extracted from a palm image:

[0900] It analyzes the palm image provided by the user and generates a fortune-telling result based on the following palm characteristics:

[0901] If the lifeline is long, you have good health.

[0902] If your fate line is clear, you have good luck in your career.

[0903] ...

[0904] Based on your palm reading, please provide your reading in the following format:

[0905] "Your lifeline is {length}. Your health is {fortune_level}."

[0906] Image data URL: {img_url}

[0907] This prompt is input into a generative model using deep learning, such as GPT (Generative Pretrained Transformer), to generate a specific fortune-telling result.

[0908] The generated fortune-telling results are sent from the server to the user's device and displayed to the user via an interface. This process uses API requests and responses. The front-end portion is built using cross-platform development frameworks such as React Native, and users can upload photos of their palms and view fortune-telling results through the app.

[0909] As a concrete example, consider the case where a user selects palm reading and takes and uploads a photo of their palm with their smartphone. This photo is sent to the server as an API request. The server analyzes the photo using image recognition technology to extract the characteristics of the palm lines. The generative model then predicts the fortune-telling result, generating something like, "Your lifeline is very long, so you have good health." This result is sent back to the user's device as an API response and displayed through the app.

[0910] In this way, the present invention provides a system that allows users to quickly obtain highly reliable fortune-telling results regardless of location or time.

[0911] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0912] Step 1:

[0913] A user uses a device to access a fortune-telling application. The device displays a user interface and provides options for selecting categories, such as palmistry or tarot reading. The user selects the type of reading and uploads a photo of their palm. The input data is an image file of the palm.

[0914] Step 2:

[0915] The device receives the palm print photo uploaded by the user and sends it to the server as an API request. Specifically, the image file is sent to the server as form data via an HTTP POST request. At this stage, the input is the palm print image data, and the output is the API request sent to the server.

[0916] Step 3:

[0917] The server analyzes the received palm image data. As a first step, it uses image recognition technology to extract palm features. Specifically, it uses deep learning frameworks such as TensorFlow and Keras to identify palm features such as life lines and fate lines. The results of this analysis become the input data for the next step. The output of the analysis is the extracted palm feature data.

[0918] Step 4:

[0919] The server generates a prompt sentence based on the extracted feature data. For example, it creates a sentence to input to the generative AI model to prompt the generation of a fortune-telling result, such as "Your lifeline is long and you have good health." The input to this prompt sentence is the extracted palm feature data, and the output is the prompt sentence to input to the generative AI model.

[0920] Step 5:

[0921] The server generates fortune-telling results using a generative AI model. A specific prompt is input into the model, which predicts and generates fortune-telling results based on past data and statistical information. The input at this stage is the prompt, and the output is the generated fortune-telling result text.

[0922] Step 6:

[0923] The generated fortune-telling result is sent from the server to the device as an API response. Specifically, it is sent as an HTTP response and the result is encoded in JSON format. The input of this step is the generated fortune-telling result text, and the output is the API response sent to the device.

[0924] Step 7:

[0925] The terminal interprets the received fortune-telling results and displays them through a user interface. The user can then review the displayed fortune-telling results and request further fortune-telling or try other fortune-telling methods. The input at this stage is the text fortune-telling results received from the server, and the output is the result displayed to the user.

[0926] This series of processing steps allows users to obtain quick, consistent, and reliable fortune-telling results regardless of location or time.

[0927] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0928] This invention relates to a system that uses a generative model that accepts and analyzes input from a user to generate predictive information, and provides that predictive information to the user. This system also combines an emotion engine that recognizes the user's emotions, and provides fortune-telling results and predictive information according to the user's emotions.

[0929] System Configuration

[0930] This system is composed of a terminal (for example, a smartphone or PC), a server, and an emotion engine. The following is a specific embodiment of the system.

[0931] The device provides a user interface and accepts the desired fortune-telling content and necessary data (for example, palm reading images or tarot card placement data). It also monitors the user's input and facial expressions to collect emotional data, which becomes the basis for the emotion engine to analyze the user's emotions.

[0932] The server receives and analyzes the data sent from the device. Specifically, it analyzes palm reading and tarot card data and extracts its characteristics. The emotion engine analyzes the user's emotions based on this data and provides emotional information. This emotional information is input into a generative model and used to generate fortune-telling results and prediction information.

[0933] Generative models are based on machine learning algorithms and generate predictions based on historical data and statistical information. These predictions are tailored to the user's emotions and presented in an appropriate format. For example, if the user is feeling anxious, the predictions can be presented in a more gentle way.

[0934] Example 1: Palmistry and Emotion Recognition

[0935] 1. The user selects palm reading on the device and uploads a photo of their palm. At the same time, facial expression data of the user is collected via the camera.

[0936] 2. The device sends the palm image data and facial expression data to the server.

[0937] 3. The server extracts features from the palm image and inputs them into the generative model. At the same time, the emotion engine analyzes the user's emotions using facial expression data.

[0938] 4. The emotion engine detects the user's emotional state (e.g., "anxiety") and provides that information to the generative model.

[0939] 5. The generative model generates fortune-telling results based on the palmistry characteristics and the user's emotions, outputting content such as, "Your lifeline is very long and you have good health. You may be feeling anxious at the moment, but things will improve in the future."

[0940] 6. The server sends the generated fortune-telling result to the terminal.

[0941] 7. The device displays the received fortune-telling results to the user, who can then confirm the results and select the next action.

[0942] Example 2: Tarot reading and emotion recognition

[0943] 1. The user selects tarot reading and inputs the card placement data. In addition, facial expression data is collected by camera.

[0944] 2. The device sends the position data and facial expression data to the server.

[0945] 3. The server analyzes the placement data and extracts its features. At the same time, the emotion engine analyzes emotions based on the facial expression data.

[0946] 4. The emotion engine detects the user's emotions (e.g., "joy") and provides that information to the generative model.

[0947] 5. The generative model generates fortune-telling results based on the placement of the tarot cards and the user’s emotions, for example, “Since the current card is ‘The Sun,’ a very positive fortune is predicted. Your mood also seems to be lifted, and you feel confident about the future.”

[0948] 6. The server sends the generated results to the terminal.

[0949] 7. The device displays the results to the user and allows them to choose their next action.

[0950] In this way, by combining this system with an emotion engine, it is possible to provide fortune-telling results that correspond to the user's emotions, realizing a more personalized experience.

[0951] The processing flow will be explained below.

[0952] Step 1:

[0953] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[0954] Step 2:

[0955] Users use the device's camera to take a photo of their palm and simultaneously collect facial expression data.

[0956] Step 3:

[0957] The device sends palm image data and facial expression data to the server as an API request.

[0958] Step 4:

[0959] The server receives the API request sent from the terminal.

[0960] Step 5:

[0961] The server passes the palm image data to an image processing module, which extracts palm features (life line, fate line, etc.).

[0962] Step 6:

[0963] The server passes the facial expression data to an emotion engine to analyze the user's emotional state. For example, it uses facial expression recognition technology to detect whether the user is in an "anxious" state.

[0964] Step 7:

[0965] The server inputs the extracted palm feature data and analyzed emotional information into a generative AI model.

[0966] Step 8:

[0967] The generative AI model generates fortune-telling results based on palmistry feature data and emotional information, such as, "Your lifeline is very long, and you have good health. You may be feeling anxious at present, but things will improve in the future."

[0968] Step 9:

[0969] The server sends the generated fortune-telling result to the terminal as an API response.

[0970] Step 10:

[0971] The terminal receives the API response from the server and analyzes the response data.

[0972] Step 11:

[0973] The device then displays the analyzed fortune-telling results on the user interface, for example in a gentle tone.

[0974] Step 12:

[0975] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[0976] Example 2: Tarot reading and emotion recognition

[0977] Step 1:

[0978] The user selects tarot reading on the terminal and enters the card placement data.

[0979] Step 2:

[0980] Users use the device's camera to collect facial expression data.

[0981] Step 3:

[0982] The device sends the tarot card placement data and facial expression data to the server as an API request.

[0983] Step 4:

[0984] The server receives the API request sent from the terminal.

[0985] Step 5:

[0986] The server analyzes the tarot card arrangement data and extracts its characteristics.

[0987] Step 6:

[0988] The server passes the facial expression data to an emotion engine to analyze the user's emotions. For example, it uses facial expression recognition technology to detect whether the user is in a "happy" state.

[0989] Step 7:

[0990] The server inputs the extracted tarot card feature data and analyzed emotional information into the generative AI model.

[0991] Step 8:

[0992] The generative AI model generates fortune-telling results based on the tarot card placement feature data and emotional information, such as, "Because the current card is the 'Sun,' a very positive fortune is predicted. Your mood seems to be lifted, and you feel confident about the future."

[0993] Step 9:

[0994] The server sends the generated fortune-telling result to the terminal as an API response.

[0995] Step 10:

[0996] The terminal receives the API response from the server and analyzes the response data.

[0997] Step 11:

[0998] The device then displays the analyzed fortune-telling results on the user interface, for example, in a positive tone that matches the user's emotions.

[0999] Step 12:

[1000] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[1001] Example 2

[1002] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1003] Conventional prediction systems were unable to take the user's emotional state into account when providing predictive information based on user input data. This made it difficult to provide flexible predictions that reflected the user's current emotions, resulting in poor acceptability of the prediction results.

[1004] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information based on the analysis result and the emotional state of the user, and means for providing the generated predictive information to the user. This makes it possible to provide appropriate predictive information according to the user's emotions.

[1005] "User" refers to the person who operates the system and inputs data.

[1006] "Input" refers to data or information provided by a user to a system.

[1007] "Analysis" refers to the process of extracting features and meaning from input data.

[1008] "Emotional state" refers to a user's current emotional state or psychological condition.

[1009] A "generative model" refers to an algorithm or system that generates predictive information from input data and analysis results.

[1010] "Predictive information" refers to future outlooks and fortune-telling results generated based on analyzed data.

[1011] "Providing" refers to displaying the generated forecast information to the user.

[1012] "Server" refers to a computer system that receives data, analyzes it, applies generative models, and provides prediction information.

[1013] "Terminal" refers to a device (e.g., a smartphone or PC) that a user operates and uses to provide input data.

[1014] "Image data" refers to photo and video data provided by users.

[1015] A "machine learning algorithm" refers to a computational method for training a model based on data and making predictions and classifications.

[1016] This invention relates to a system that accepts and analyzes input data from a user, evaluates the user's emotional state using an emotion recognition engine, and generates and provides predictive information based on that information. This system consists of a terminal (such as a smartphone or PC), a server, and an emotion recognition engine.

[1017] Overview of program processing

[1018] This system performs the following processes:

[1019] 1. Accepting user input

[1020] Users use the application on their device to select palm reading or tarot card reading, and input a photo of their palm and tarot card placement data, while facial expression data is collected via the camera.

[1021] 2. Data transmission

[1022] The device sends the data entered by the user to a server using an internet connection.

[1023] 3. Server-side data analysis

[1024] The server analyzes the received data. For palm reading image data, image analysis software (e.g., OpenCV) is used to extract features, and for tarot card placement data, a proprietary algorithm is used.

[1025] 4. Emotion analysis

[1026] An emotion recognition engine analyzes facial expression data to assess the user's emotional state, using deep learning models (e.g., Emotion Recognition API).

[1027] 5. Generating Predictive Information Using Generative Models

[1028] The generative model generates predictions based on emotion information and palm reading or tarot data. This generative model uses machine learning algorithms (e.g., TensorFlow). The predictions are adjusted according to the user's emotions.

[1029] 6. Sending and displaying results

[1030] The server transmits the generated forecast information to the terminal, which displays the information to the user.

[1031] Hardware and software used

[1032] Devices: Smartphones, PCs, webcams

[1033] Server: High-performance processor, large storage capacity

[1034] Image analysis software: OpenCV

[1035] Emotion Recognition Engine: Emotion Recognition API

[1036] Machine learning framework: TensorFlow

[1037] Specific examples

[1038] Example 1: Palmistry

[1039] 1. The user selects palm reading through the app, takes a photo of their palm and uploads it, while facial expression data is also collected.

[1040] 2. The device sends the palm image and facial expression data to the server.

[1041] 3. The server analyzes the palm image using OpenCV and evaluates the emotion using an emotion recognition engine.

[1042] 4. The generative model generates the fortune-telling results, creating a message such as, "Your lifeline is very long and you have good health. You may be feeling anxious now, but things will improve in the future."

[1043] 5. The server sends the results to the terminal, which displays them to the user.

[1044] Prompt Sentence Examples

[1045] "Upload an image of your palm and we'll give you a fortune reading based on that image. The reading will be adjusted according to your current emotional state."

[1046] Example 2: Tarot reading

[1047] 1. The user selects tarot reading and inputs the card placement data. Facial expression data is also collected at the same time.

[1048] 2. The device sends the position data and facial expression data to the server.

[1049] 3. The server analyzes the placement data and evaluates the emotion using an emotion recognition engine.

[1050] 4. The generative model generates the fortune-telling result, creating a message such as, "Since your current card is the Sun, a very positive fortune is predicted. Your spirits seem to be lifted and you feel confident about the future."

[1051] 5. The server sends the results to the terminal, which displays them to the user.

[1052] Prompt Sentence Examples

[1053] "Enter your tarot card placement data. We will predict your fortune based on that placement. The results will be adjusted according to your current emotions."

[1054] In this way, the present invention provides appropriate predictive information according to the user's emotions, realizing a more personalized experience.

[1055] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1056] Step 1:

[1057] The user opens the application on the device and selects the type of fortune-telling (palm reading or tarot card reading). Then, for palm reading, the user takes a photo of their palm, and for tarot reading, the user inputs the card arrangement data. Furthermore, facial expression data is automatically collected via the camera. The user's palm image, tarot card arrangement data, and facial expression data are then input.

[1058] Input: Palm reading image or tarot card placement data, and facial expression data

[1059] Output: A set of palm reading images or tarot card layout data and facial expression data

[1060] Specific behavior:

[1061] The user opens the app.

[1062] Choose palm reading or tarot reading (through UI).

[1063] For palm reading, open the camera and take a photo of your palm.

[1064] For tarot, the card placement is entered manually.

[1065] To collect facial expression data, the camera is activated and a picture of the user's facial expression is taken.

[1066] Step 2:

[1067] The terminal transmits the palm reading image, tarot card placement data, and facial expression data collected from the user to the server. This transmission is performed via internet communication. The data is sent in a single packet.

[1068] Input: A set of palm reading images or tarot card layout data and facial expression data

[1069] Output: Palm reading image or tarot card placement data and facial expression data sent to the server

[1070] Specific behavior:

[1071] The collected data is organized into packets.

[1072] Send an HTTP POST request to the server's URL over your internet connection.

[1073] Step 3:

[1074] The server receives the data sent from the device and analyzes each data. For palm reading images, image analysis software (e.g., OpenCV) is used, and for tarot card placement data, a proprietary algorithm is used to extract features. For facial expression data, an emotion recognition engine is used to analyze emotions.

[1075] Input: Palm reading image or tarot card placement data, and facial expression data

[1076] Output: Palmistry feature data, Tarot feature data, and emotional state data

[1077] Specific behavior:

[1078] The server receives the data packets and passes them to a module for analysis.

[1079] The palm image is analyzed using OpenCV to extract palm line features.

[1080] Analyze tarot placement data and extract card characteristics.

[1081] An emotion recognition engine is used to analyze facial expression data and detect emotional states (e.g., "anxiety" or "joy").

[1082] Step 4:

[1083] The server inputs the emotional information obtained from the emotion engine and the analyzed palm reading and tarot data into a generative model. The generative model uses a machine learning framework (e.g., TensorFlow) to generate fortune-telling results based on past data and statistical information. Furthermore, the generated results are adjusted according to the user's emotional state.

[1084] Input: Palmistry feature data, Tarot feature data, and emotional state data

[1085] Output: Predictive information adjusted based on emotions

[1086] Specific behavior:

[1087] Emotion information and palm or tarot data are input into the generative model.

[1088] Use TensorFlow to generate prediction information.

[1089] Tailor predictive information to the user's emotional state.

[1090] Step 5:

[1091] The server sends the fortune-telling results generated by the generative model to the device. This is done via internet communication again. The data is converted into a format that is easy for the device to understand (e.g., JSON format) and then sent.

[1092] Input: Emotionally adjusted prediction information

[1093] Output: Fortune telling results sent to the device

[1094] Specific behavior:

[1095] The generated fortune-telling results are collected into a packet.

[1096] Send it to your device via your internet connection.

[1097] Step 6:

[1098] The terminal displays the fortune-telling results received from the server to the user. The user can check the results and select the next action. The fortune-telling results are displayed in a format suitable for the user's terminal.

[1099] Input: Fortune telling result sent from the server

[1100] Output: Fortune telling result displayed to the user

[1101] Specific behavior:

[1102] Analyze the data received from the server and reflect the results in the display UI.

[1103] The user sees the results on the device screen.

[1104] (Application example 2)

[1105] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1106] Current predictive information systems have difficulty providing personalized information based on the user's emotions. Furthermore, rather than simply analyzing data, it is necessary to provide more accurate counseling and fortune-telling results by providing feedback based on emotions.

[1107] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information using the analysis results, means for analyzing emotions based on the generated predictive information, means for generating predictive information based on the analyzed emotional information, and means for providing the generated predictive information to the user. This makes it possible to provide personalized predictive information based on the user's emotions.

[1108] "User" refers to a person who uses the system.

[1109] "Input" refers to the data or information that a user provides to a system.

[1110] "Analysis" refers to the process of extracting information from input data and drawing specific conclusions or predictions.

[1111] A "generative model" refers to a computational model for generating predictive information using a machine learning algorithm.

[1112] "Predictive information" refers to information about future events or trends that is generated based on analytical results.

[1113] "Emotion analysis" refers to the process of determining a user's emotional state from facial expression data and other inputs.

[1114] "Emotional information" refers to data about a user's emotional state obtained through emotion analysis.

[1115] "Personalization" refers to tailoring information to each individual user's specific needs and feelings.

[1116] "Image data" refers to visual information provided in the form of still images or video.

[1117] A "machine learning algorithm" refers to a computational method that learns patterns from data and makes predictions or decisions based on them.

[1118] The system for realizing this invention is composed of the following program: This program analyzes data entered by a user, uses a machine learning algorithm to generate predictive information based on emotion information, and provides it to the user.

[1119] Hardware used

[1120] Device: Smartphone, tablet, or computer

[1121] Display devices: smart glasses, head-mounted displays

[1122] Analysis server: A high-performance calculation server (e.g., an EC2 instance on Amazon Web Services (AWS))

[1123] Software used

[1124] Facial expression recognition library: OpenCV

[1125] Sentiment analysis engine: Microsoft Azure Cognitive Services

[1126] Machine learning libraries: TensorFlow, PyTorch

[1127] Database: MongoDB, MySQL

[1128] Program processing flow

[1129] 1. The user uses the device to input the data they wish to receive for fortune telling or counseling. The input data includes the user's text information and image data required for fortune telling.

[1130] 2. The device uses the user's camera to collect facial expression data in real time, which is then used for later analysis.

[1131] 3. The analysis server receives the input data and facial expression data sent from the device. The facial expression data is analyzed using OpenCV to extract the emotional state.

[1132] 4. Microsoft Azure Cognitive Services, an emotion analysis engine, quantitatively evaluates the emotional state based on the extracted facial expression data and generates emotional information.

[1133] 5. Use a machine learning library (TensorFlow or PyTorch) to generate predictions based on the sentiment and user-supplied data, referencing historical data and statistical information to obtain more accurate results.

[1134] 6. The generated forecast information is provided to the user via the terminal.

[1135] Specific use cases

[1136] Consider a case where a user selects a relaxation menu at a relaxation salon. The user selects palm reading on their device and uploads a photo of their palm. At this time, the smart glasses also collect the user's facial expression data in real time. The server analyzes the palm image and simultaneously performs emotion analysis using the facial expression data. Using the generative model, the server generates a result such as, "Your lifeline is very long and you have good health luck. You may be feeling anxious at present, but things will improve in the future," and displays this result to the user.

[1137] Prompt Sentence Examples

[1138] Below is an example of a prompt for this system:

[1139] Customer facial expression data: {facial expression data}

[1140] Customer emotions: Anxiety, tension

[1141] Past counseling data: {Past data}

[1142] What I want: I want to relax

[1143] --Generative Model Prompt--

[1144] Generate personalized relaxation menus and counseling content based on the customer's emotional state.

[1145] In this way, the system combines highly accurate emotion analysis with predictive information to provide users with personalized information.

[1146] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1147] Step 1:

[1148] The device accepts input from the user regarding their desired fortune-telling or counseling. Specifically, the user uploads text information or image data (e.g., a photo of their palm) to the device. The input data is stored in a local database for subsequent analysis.

[1149] Step 2:

[1150] The device collects the user's facial expression data in real time. It divides the video data captured by the camera into frames and uses the OpenCV library to perform facial recognition and extract feature points. It analyzes the facial feature points and generates numerical data of the facial expression data.

[1151] Step 3:

[1152] The device sends the collected input data and facial expression data to the analysis server. The transmitted data is sent to the server's analysis engine via an API. The input data includes the user's text information, image data, and facial expression data.

[1153] Step 4:

[1154] The server receives the data sent from the device and first analyzes the image data. Specifically, the server uses an image recognition algorithm to extract the palm's characteristic points and convert them into numerical data. For image recognition, a deep learning model (e.g., VGG16 or ResNet) is used.

[1155] Step 5:

[1156] The server uses an emotion analysis engine (Microsoft Azure Cognitive Services) to analyze the facial expression data and identify the user's emotional state. Based on the facial expression data received as input, it determines the type of emotion (e.g., joy, anxiety, sadness) and outputs the emotional information as numerical data.

[1157] Step 6:

[1158] The server runs a generative model using a machine learning library (TensorFlow or PyTorch). Based on the palm reading data and emotion information received as input, the generative model generates predictions. The predictions (e.g., fortune-telling results or counseling advice) are generated by the generative AI model.

[1159] Step 7:

[1160] The server sends the generated forecast information to the device using the REST API in JSON format. The device then displays the received forecast information to the user.

[1161] Step 8:

[1162] The device provides users with predictive information and allows them to select their next action based on that information, for example, by providing an interactive UI for users to select a relaxation menu or request further counseling.

[1163] In this way, through the processing steps, personalized prediction information according to the user's emotions is provided.

[1164] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1165] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1166] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1167] [Fourth embodiment]

[1168] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1169] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1170] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1171] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1172] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1173] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1174] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1175] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1176] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1177] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1178] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1179] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1180] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1181] The present invention relates to a system including an input means for a user to request a fortune telling, an analysis means for analyzing the received input, a generative model that generates predictive information using the analysis results, and a means for providing the generated predictive information to the user.

[1182] This system consists of a user's device (e.g., a smartphone or PC) and a server. The device provides the user interface and accepts the desired fortune-telling content and necessary data (e.g., palm reading images and tarot card placement data). The device then creates an API request to send the accepted data to the server.

[1183] The server analyzes the received API request and performs the necessary data processing based on the user's input. Specifically, image recognition technology is used to extract palmistry features and input these features into a generative model. The generative model is based on a machine learning algorithm and generates predictive information by referencing past data and statistical information. For example, if the lifeline on the palm is long, the resulting fortune-telling result will indicate good health.

[1184] The generated prediction information is sent from the server to the device as an API response. The device displays the received prediction information to the user, providing consistent fortune-telling results. The user can check the displayed results, request further fortune-telling, or try different fortune-telling methods.

[1185] Example 1: Palmistry

[1186] The user selects palm reading on their device and uploads a photo of their palm. This photo is sent to the server as an API request. The server analyzes the image and extracts palm features such as life lines and fate lines. The extracted feature data is input into a generative model, which generates a fortune-telling result. For example, it generates prediction information such as "Your life line is very long, so you have good health." This information is sent back to the device as an API response and displayed to the user.

[1187] Example 2: Tarot reading

[1188] The user selects tarot reading using their device and inputs the card placement data. This placement data is sent to the server as an API request. The server analyzes the tarot card placement and generates a fortune-telling result based on that placement using a generative model. For example, it generates prediction information such as "Since the current card is 'The Tower,' now is a time for change." This information is also sent back to the device as an API response and displayed to the user.

[1189] In this way, our system applies appropriate analysis and generative models depending on the type of fortune-telling requested by the user, providing fast and accurate fortune-telling results. Users can easily receive consistent and reliable fortune-telling results regardless of time or place.

[1190] The processing flow will be explained below.

[1191] Step 1:

[1192] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[1193] Step 2:

[1194] The user uploads a photo of their palm to the device and presses the "Perform fortune telling" button.

[1195] Step 3:

[1196] The device receives input from the user and composes palm image data and a fortune-telling request (e.g., "palm reading") as an API request.

[1197] Step 4:

[1198] The device sends the configured API request to the server.

[1199] Step 5:

[1200] The server receives an API request from the terminal and analyzes the request content to identify the fortune-telling method (palm reading) selected by the user and the image data provided.

[1201] Step 6:

[1202] The server invokes an image processing module to analyze the palm image, specifically applying image recognition algorithms to extract key palm features (e.g., life line, fate line, etc.).

[1203] Step 7:

[1204] The server inputs the extracted palm line feature data into a generative AI model, which is trained using machine learning algorithms and generates fortune-telling results based on this data.

[1205] Step 8:

[1206] The server formats the generated fortune-telling result in text format and composes it as an API response.

[1207] Step 9:

[1208] The server sends the constructed API response to the device.

[1209] Step 10:

[1210] The terminal receives the API response from the server and analyzes the response data.

[1211] Step 11:

[1212] The device then displays the analyzed fortune-telling results on the user interface, such as "Your lifeline is very long, so you have good health."

[1213] Step 12:

[1214] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[1215] In this way, a series of processes that allows the user to easily obtain fortune-telling results is completed.

[1216] Example 1

[1217] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1218] In conventional fortune-telling systems, when users request a fortune, they must manually input and analyze data, which takes time and effort. There are also issues with the reliability and consistency of the results. This makes it difficult for users to easily obtain quick, accurate fortune-telling results.

[1219] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1220] In this invention, the server includes means for accepting input from a user, means for transmitting the accepted input to the server, means for analyzing data based on the received input, means for applying a generative AI model that generates predictive information using the analysis results, and means for providing the generated predictive information to the user, thereby enabling the user to easily request a fortune telling and obtain a quick and accurate result.

[1221] "User" refers to an individual or organization that uses this system.

[1222] "Means for accepting input" refers to devices or software that provide an interface for users to input or upload data for fortune-telling purposes.

[1223] "Means for sending input to a server" refers to a device or software with a communication function for sending data entered by a user to a server.

[1224] "Means for analyzing data" refers to software or algorithms that the server uses to process the data received from the user and extract the necessary information.

[1225] A "generative AI model that generates predictive information using analysis results" is an artificial intelligence model that generates fortune-telling results and predictive information based on analyzed data.

[1226] "Means for generating predictive information" refers to software or algorithms that use a generative AI model to output specific fortune-telling results or predictive information from the analysis results.

[1227] "Means for providing generated predictive information to users" refers to devices or software equipped with an interface and communication functions for conveying the information output by the generative AI model to users.

[1228] "Means for analyzing image data" refers to software or algorithms that use image recognition technology to process image data provided by users and extract necessary features.

[1229] A "generative AI model that uses prompts based on machine learning algorithms" is an artificial intelligence model that uses machine learning technology to generate appropriate responses or predictions for specific inputs.

[1230] The present invention relates to a system for users to request fortune-telling. This system is configured using a user's terminal (for example, a smartphone or PC) and a server.

[1231] The user uses the device to select the type of fortune-telling (palm reading, tarot card reading, etc.) and input or upload the necessary data. For example, for palm reading, the user can take and upload a photo of their palm. For tarot reading, the user can input the card arrangement data.

[1232] The device receives the data entered by the user, converts it into an appropriate format (e.g., JSON format) as an API request, and sends it to the server. This transmission uses Internet communication.

[1233] The server analyzes the received API request and checks the data content. In the case of palmistry, the server uses image recognition technology (e.g., OpenCV) to extract palm features (such as life lines and fate lines). This extracted feature data is input into a generative AI model (e.g., GPT-4).

[1234] The generative AI model uses machine learning algorithms to generate fortune-telling results and predictions by referencing past data and statistical information. For example, in the case of palmistry, by entering a prompt such as "Please analyze a palm with a long, clear life line. What does that mean?", the generative model will generate a result such as "Your life line is very long, so you have good health."

[1235] In the case of tarot readings, the AI ​​model is given a prompt based on the placement data of the tarot cards: "The current card is the Tower, and the future card is the Sun. Please generate a fortune-telling result based on these placements." In this case, it generates prediction information such as, "Because the current card is the Tower, now is a time of change."

[1236] The generated prediction information is sent from the server to the device as an API response. The device analyzes the received API response and displays the fortune-telling results in a format that is easy for the user to understand.

[1237] The user can check the displayed fortune-telling results and request a more detailed fortune-telling or a new fortune-telling if necessary. This system provides an environment where users can receive fortune-telling easily, quickly, and accurately.

[1238] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1239] Step 1:

[1240] The user selects the type of fortune-telling they want and inputs or uploads the necessary data: for palm reading, they take a photo of their palm, and for tarot reading, they input the card layout data. Then, the user confirms their fortune-telling request.

[1241] Input: Type of fortune telling and related data (palm reading photo or tarot card placement data)

[1242] Output: User selections and input data

[1243] Step 2:

[1244] The terminal receives the data entered by the user and sends it to the server as an API request, where the data is converted into an appropriate format (e.g., JSON).

[1245] Input: User-selected and entered data

[1246] Output: API request to the server

[1247] Step 3:

[1248] The server analyzes the received API request and checks the data content. In the case of palmistry, it analyzes a photo of the palm using image recognition technology to extract features. In the case of tarot readings, it analyzes the card placement data.

[1249] Input: API request sent from the device

[1250] Output: Palm reading data or tarot card layout data

[1251] Step 4:

[1252] The server inputs the extracted feature data and placement data into the generative AI model, generates prompt sentences, and inputs them into the model to generate prediction information.

[1253] Input: Palm reading data or tarot card placement data, prompt text

[1254] Output: Predictions from the generative AI model

[1255] Step 5:

[1256] The server receives the generated prediction information and sends it to the device as an API response, which is then formatted appropriately.

[1257] Input: Prediction information from a generative AI model

[1258] Output: API response to the device

[1259] Step 6:

[1260] The device analyzes the API response received from the server and displays the fortune-telling results in a format that is easy for the user to understand. The user can then check the displayed results and request a more detailed fortune-telling or a new fortune-telling.

[1261] Input: API response from the server

[1262] Output: Display fortune-telling results to the user

[1263] These steps allow users to easily obtain quick and accurate fortune-telling results.

[1264] (Application example 1)

[1265] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1266] Conventional fortune-telling systems often took a long time for users to receive their fortune-telling results, and they often lacked consistency and reliability. Face-to-face fortune-telling also had limitations on location and time, making it difficult for many users to use. Another issue was the lack of established technology for accurately analyzing image data from palmistry and tarot cards.

[1267] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1268] In this invention, the server includes means for processing input data for providing fortune-telling results using image recognition technology, means for inputting prompt sentences based on specific categories into a generative AI model, and means for providing consistent and reliable fortune-telling results online, thereby enabling users to quickly obtain consistent and reliable fortune-telling results regardless of location or time.

[1269] "User" refers to any individual or organization that uses the fortune-telling service.

[1270] "Means for accepting input" refers to the interface or function that allows users to input the information they want to know and the necessary data.

[1271] "Analysis tools" refers to the techniques and algorithms used to process data received from users and extract meaningful information.

[1272] "Means for applying generative models" refers to the function of applying machine learning models or AI to generate fortune-telling prediction information based on analyzed data.

[1273] "Means for providing predictive information" refers to the interface and functions for communicating the generated fortune-telling results to users.

[1274] "Image recognition technology" refers to the technology used to analyze image data and extract features. Specifically, it is used to extract palm lines and other features.

[1275] "Prompt" means a text-formatted instruction given to a generative AI model, including instructions based on a specific category.

[1276] "Consistent and reliable fortune-telling results" refers to fortune-telling results that always provide the same results for the same input and that have the reliability to be accepted by many people.

[1277] "Online delivery means" refers to the technologies and functions used to provide services to users via the Internet.

[1278] This invention relates to an online fortune-telling system that can be used by users. This system is composed of a user terminal and a server, and is capable of quickly and consistently providing fortune-telling results such as palm reading and tarot card reading.

[1279] The server includes a means for processing input data using image recognition technology to provide fortune-telling results. Specifically, it receives palm reading photos and tarot card layout data provided by users, analyzes those images, and extracts features. Deep learning frameworks such as TensorFlow and Keras are used for this analysis.

[1280] Next, there is a way to input prompt sentences based on specific categories into the generative AI model. For example, in the case of palm reading, the server generates prompt sentences of the following form based on features extracted from a palm image:

[1281] It analyzes the palm image provided by the user and generates a fortune-telling result based on the following palm characteristics:

[1282] If the lifeline is long, you have good health.

[1283] If your fate line is clear, you have good luck in your career.

[1284] ...

[1285] Based on your palm reading, please provide your reading in the following format:

[1286] "Your lifeline is {length}. Your health is {fortune_level}."

[1287] Image data URL: {img_url}

[1288] This prompt is input into a generative model using deep learning, such as GPT (Generative Pretrained Transformer), to generate a specific fortune-telling result.

[1289] The generated fortune-telling results are sent from the server to the user's device and displayed to the user via an interface. This process uses API requests and responses. The front-end portion is built using cross-platform development frameworks such as React Native, and users can upload photos of their palms and view fortune-telling results through the app.

[1290] As a concrete example, consider the case where a user selects palm reading and takes and uploads a photo of their palm with their smartphone. This photo is sent to the server as an API request. The server analyzes the photo using image recognition technology to extract the characteristics of the palm lines. The generative model then predicts the fortune-telling result, generating something like, "Your lifeline is very long, so you have good health." This result is sent back to the user's device as an API response and displayed through the app.

[1291] In this way, the present invention provides a system that allows users to quickly obtain highly reliable fortune-telling results regardless of location or time.

[1292] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1293] Step 1:

[1294] A user uses a device to access a fortune-telling application. The device displays a user interface and provides options for selecting categories, such as palmistry or tarot reading. The user selects the type of reading and uploads a photo of their palm. The input data is an image file of the palm.

[1295] Step 2:

[1296] The device receives the palm print photo uploaded by the user and sends it to the server as an API request. Specifically, the image file is sent to the server as form data via an HTTP POST request. At this stage, the input is the palm print image data, and the output is the API request sent to the server.

[1297] Step 3:

[1298] The server analyzes the received palm image data. As a first step, it uses image recognition technology to extract palm features. Specifically, it uses deep learning frameworks such as TensorFlow and Keras to identify palm features such as life lines and fate lines. The results of this analysis become the input data for the next step. The output of the analysis is the extracted palm feature data.

[1299] Step 4:

[1300] The server generates a prompt sentence based on the extracted feature data. For example, it creates a sentence to input to the generative AI model to prompt the generation of a fortune-telling result, such as "Your lifeline is long and you have good health." The input to this prompt sentence is the extracted palm feature data, and the output is the prompt sentence to input to the generative AI model.

[1301] Step 5:

[1302] The server generates fortune-telling results using a generative AI model. A specific prompt is input into the model, which predicts and generates fortune-telling results based on past data and statistical information. The input at this stage is the prompt, and the output is the generated fortune-telling result text.

[1303] Step 6:

[1304] The generated fortune-telling result is sent from the server to the device as an API response. Specifically, it is sent as an HTTP response and the result is encoded in JSON format. The input of this step is the generated fortune-telling result text, and the output is the API response sent to the device.

[1305] Step 7:

[1306] The terminal interprets the received fortune-telling results and displays them through a user interface. The user can then review the displayed fortune-telling results and request further fortune-telling or try other fortune-telling methods. The input at this stage is the text fortune-telling results received from the server, and the output is the result displayed to the user.

[1307] This series of processing steps allows users to obtain quick, consistent, and reliable fortune-telling results regardless of location or time.

[1308] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1309] This invention relates to a system that uses a generative model that accepts and analyzes input from a user to generate predictive information, and provides that predictive information to the user. This system also combines an emotion engine that recognizes the user's emotions, and provides fortune-telling results and predictive information according to the user's emotions.

[1310] System Configuration

[1311] This system is composed of a terminal (for example, a smartphone or PC), a server, and an emotion engine. The following is a specific embodiment of the system.

[1312] The device provides a user interface and accepts the desired fortune-telling content and necessary data (for example, palm reading images or tarot card placement data). It also monitors the user's input and facial expressions to collect emotional data, which becomes the basis for the emotion engine to analyze the user's emotions.

[1313] The server receives and analyzes the data sent from the device. Specifically, it analyzes palm reading and tarot card data and extracts its characteristics. The emotion engine analyzes the user's emotions based on this data and provides emotional information. This emotional information is input into a generative model and used to generate fortune-telling results and prediction information.

[1314] Generative models are based on machine learning algorithms and generate predictions based on historical data and statistical information. These predictions are tailored to the user's emotions and presented in an appropriate format. For example, if the user is feeling anxious, the predictions can be presented in a more gentle way.

[1315] Example 1: Palmistry and Emotion Recognition

[1316] 1. The user selects palm reading on the device and uploads a photo of their palm. At the same time, facial expression data of the user is collected via the camera.

[1317] 2. The device sends the palm image data and facial expression data to the server.

[1318] 3. The server extracts features from the palm image and inputs them into the generative model. At the same time, the emotion engine analyzes the user's emotions using facial expression data.

[1319] 4. The emotion engine detects the user's emotional state (e.g., "anxiety") and provides that information to the generative model.

[1320] 5. The generative model generates fortune-telling results based on the palmistry characteristics and the user's emotions, outputting content such as, "Your lifeline is very long and you have good health. You may be feeling anxious at the moment, but things will improve in the future."

[1321] 6. The server sends the generated fortune-telling result to the terminal.

[1322] 7. The device displays the received fortune-telling results to the user, who can then confirm the results and select the next action.

[1323] Example 2: Tarot reading and emotion recognition

[1324] 1. The user selects tarot reading and inputs the card placement data. In addition, facial expression data is collected by camera.

[1325] 2. The device sends the position data and facial expression data to the server.

[1326] 3. The server analyzes the placement data and extracts its features. At the same time, the emotion engine analyzes emotions based on the facial expression data.

[1327] 4. The emotion engine detects the user's emotions (e.g., "joy") and provides that information to the generative model.

[1328] 5. The generative model generates fortune-telling results based on the placement of the tarot cards and the user’s emotions, for example, “Since the current card is ‘The Sun,’ a very positive fortune is predicted. Your mood also seems to be lifted, and you feel confident about the future.”

[1329] 6. The server sends the generated results to the terminal.

[1330] 7. The device displays the results to the user and allows them to choose their next action.

[1331] In this way, by combining this system with an emotion engine, it is possible to provide fortune-telling results that correspond to the user's emotions, realizing a more personalized experience.

[1332] The processing flow will be explained below.

[1333] Step 1:

[1334] The user launches the app on their device and selects the type of fortune-telling (for example, "palm reading").

[1335] Step 2:

[1336] Users use the device's camera to take a photo of their palm and simultaneously collect facial expression data.

[1337] Step 3:

[1338] The device sends palm image data and facial expression data to the server as an API request.

[1339] Step 4:

[1340] The server receives the API request sent from the terminal.

[1341] Step 5:

[1342] The server passes the palm image data to an image processing module, which extracts palm features (life line, fate line, etc.).

[1343] Step 6:

[1344] The server passes the facial expression data to an emotion engine to analyze the user's emotional state. For example, it uses facial expression recognition technology to detect whether the user is in an "anxious" state.

[1345] Step 7:

[1346] The server inputs the extracted palm feature data and analyzed emotional information into a generative AI model.

[1347] Step 8:

[1348] The generative AI model generates fortune-telling results based on palmistry feature data and emotional information, such as, "Your lifeline is very long, and you have good health. You may be feeling anxious at present, but things will improve in the future."

[1349] Step 9:

[1350] The server sends the generated fortune-telling result to the terminal as an API response.

[1351] Step 10:

[1352] The terminal receives the API response from the server and analyzes the response data.

[1353] Step 11:

[1354] The device then displays the analyzed fortune-telling results on the user interface, for example in a gentle tone.

[1355] Step 12:

[1356] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[1357] Example 2: Tarot reading and emotion recognition

[1358] Step 1:

[1359] The user selects tarot reading on the terminal and enters the card placement data.

[1360] Step 2:

[1361] Users use the device's camera to collect facial expression data.

[1362] Step 3:

[1363] The device sends the tarot card placement data and facial expression data to the server as an API request.

[1364] Step 4:

[1365] The server receives the API request sent from the terminal.

[1366] Step 5:

[1367] The server analyzes the tarot card arrangement data and extracts its characteristics.

[1368] Step 6:

[1369] The server passes the facial expression data to an emotion engine to analyze the user's emotions. For example, it uses facial expression recognition technology to detect whether the user is in a "happy" state.

[1370] Step 7:

[1371] The server inputs the extracted tarot card feature data and analyzed emotional information into the generative AI model.

[1372] Step 8:

[1373] The generative AI model generates fortune-telling results based on the tarot card placement feature data and emotional information, such as, "Because the current card is the 'Sun,' a very positive fortune is predicted. Your mood seems to be lifted, and you feel confident about the future."

[1374] Step 9:

[1375] The server sends the generated fortune-telling result to the terminal as an API response.

[1376] Step 10:

[1377] The terminal receives the API response from the server and analyzes the response data.

[1378] Step 11:

[1379] The device then displays the analyzed fortune-telling results on the user interface, for example, in a positive tone that matches the user's emotions.

[1380] Step 12:

[1381] Users can check the displayed fortune-telling results and select their next action, such as "save the results" or "try other fortune-telling methods."

[1382] Example 2

[1383] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1384] Conventional prediction systems were unable to take the user's emotional state into account when providing predictive information based on user input data. This made it difficult to provide flexible predictions that reflected the user's current emotions, resulting in poor acceptability of the prediction results.

[1385] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information based on the analysis result and the emotional state of the user, and means for providing the generated predictive information to the user. This makes it possible to provide appropriate predictive information according to the user's emotions.

[1386] "User" refers to the person who operates the system and inputs data.

[1387] "Input" refers to data or information provided by a user to a system.

[1388] "Analysis" refers to the process of extracting features and meaning from input data.

[1389] "Emotional state" refers to a user's current emotional state or psychological condition.

[1390] A "generative model" refers to an algorithm or system that generates predictive information from input data and analysis results.

[1391] "Predictive information" refers to future outlooks and fortune-telling results generated based on analyzed data.

[1392] "Providing" refers to displaying the generated forecast information to the user.

[1393] "Server" refers to a computer system that receives data, analyzes it, applies generative models, and provides prediction information.

[1394] "Terminal" refers to a device (e.g., a smartphone or PC) that a user operates and uses to provide input data.

[1395] "Image data" refers to photo and video data provided by users.

[1396] A "machine learning algorithm" refers to a computational method for training a model based on data and making predictions and classifications.

[1397] This invention relates to a system that accepts and analyzes input data from a user, evaluates the user's emotional state using an emotion recognition engine, and generates and provides predictive information based on that information. This system consists of a terminal (such as a smartphone or PC), a server, and an emotion recognition engine.

[1398] Overview of program processing

[1399] This system performs the following processes:

[1400] 1. Accepting user input

[1401] Users use the application on their device to select palm reading or tarot card reading, and input a photo of their palm and tarot card placement data, while facial expression data is collected via the camera.

[1402] 2. Data transmission

[1403] The device sends the data entered by the user to a server using an internet connection.

[1404] 3. Server-side data analysis

[1405] The server analyzes the received data. For palm reading image data, image analysis software (e.g., OpenCV) is used to extract features, and for tarot card placement data, a proprietary algorithm is used.

[1406] 4. Emotion analysis

[1407] An emotion recognition engine analyzes facial expression data to assess the user's emotional state, using deep learning models (e.g., Emotion Recognition API).

[1408] 5. Generating Predictive Information Using Generative Models

[1409] The generative model generates predictions based on emotion information and palm reading or tarot data. This generative model uses machine learning algorithms (e.g., TensorFlow). The predictions are adjusted according to the user's emotions.

[1410] 6. Sending and displaying results

[1411] The server transmits the generated forecast information to the terminal, which displays the information to the user.

[1412] Hardware and software used

[1413] Devices: Smartphones, PCs, webcams

[1414] Server: High-performance processor, large storage capacity

[1415] Image analysis software: OpenCV

[1416] Emotion Recognition Engine: Emotion Recognition API

[1417] Machine learning framework: TensorFlow

[1418] Specific examples

[1419] Example 1: Palmistry

[1420] 1. The user selects palm reading through the app, takes a photo of their palm and uploads it, while facial expression data is also collected.

[1421] 2. The device sends the palm image and facial expression data to the server.

[1422] 3. The server analyzes the palm image using OpenCV and evaluates the emotion using an emotion recognition engine.

[1423] 4. The generative model generates the fortune-telling results, creating a message such as, "Your lifeline is very long and you have good health. You may be feeling anxious now, but things will improve in the future."

[1424] 5. The server sends the results to the terminal, which displays them to the user.

[1425] Prompt Sentence Examples

[1426] "Upload an image of your palm and we'll give you a fortune reading based on that image. The reading will be adjusted according to your current emotional state."

[1427] Example 2: Tarot reading

[1428] 1. The user selects tarot reading and inputs the card placement data. Facial expression data is also collected at the same time.

[1429] 2. The device sends the position data and facial expression data to the server.

[1430] 3. The server analyzes the placement data and evaluates the emotion using an emotion recognition engine.

[1431] 4. The generative model generates the fortune-telling result, creating a message such as, "Since your current card is the Sun, a very positive fortune is predicted. Your spirits seem to be lifted and you feel confident about the future."

[1432] 5. The server sends the results to the terminal, which displays them to the user.

[1433] Prompt Sentence Examples

[1434] "Enter your tarot card placement data. We will predict your fortune based on that placement. The results will be adjusted according to your current emotions."

[1435] In this way, the present invention provides appropriate predictive information according to the user's emotions, realizing a more personalized experience.

[1436] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1437] Step 1:

[1438] The user opens the application on the device and selects the type of fortune-telling (palm reading or tarot card reading). Then, for palm reading, the user takes a photo of their palm, and for tarot reading, the user inputs the card arrangement data. Furthermore, facial expression data is automatically collected via the camera. The user's palm image, tarot card arrangement data, and facial expression data are then input.

[1439] Input: Palm reading image or tarot card placement data, and facial expression data

[1440] Output: A set of palm reading images or tarot card layout data and facial expression data

[1441] Specific behavior:

[1442] The user opens the app.

[1443] Choose palm reading or tarot reading (through UI).

[1444] For palm reading, open the camera and take a photo of your palm.

[1445] For tarot, the card placement is entered manually.

[1446] To collect facial expression data, the camera is activated and a picture of the user's facial expression is taken.

[1447] Step 2:

[1448] The terminal transmits the palm reading image, tarot card placement data, and facial expression data collected from the user to the server. This transmission is performed via internet communication. The data is sent in a single packet.

[1449] Input: A set of palm reading images or tarot card layout data and facial expression data

[1450] Output: Palm reading image or tarot card placement data and facial expression data sent to the server

[1451] Specific behavior:

[1452] The collected data is organized into packets.

[1453] Send an HTTP POST request to the server's URL over your internet connection.

[1454] Step 3:

[1455] The server receives the data sent from the device and analyzes each data. For palm reading images, image analysis software (e.g., OpenCV) is used, and for tarot card placement data, a proprietary algorithm is used to extract features. For facial expression data, an emotion recognition engine is used to analyze emotions.

[1456] Input: Palm reading image or tarot card placement data, and facial expression data

[1457] Output: Palmistry feature data, Tarot feature data, and emotional state data

[1458] Specific behavior:

[1459] The server receives the data packets and passes them to a module for analysis.

[1460] The palm image is analyzed using OpenCV to extract palm line features.

[1461] Analyze tarot placement data and extract card characteristics.

[1462] An emotion recognition engine is used to analyze facial expression data and detect emotional states (e.g., "anxiety" or "joy").

[1463] Step 4:

[1464] The server inputs the emotional information obtained from the emotion engine and the analyzed palm reading and tarot data into a generative model. The generative model uses a machine learning framework (e.g., TensorFlow) to generate fortune-telling results based on past data and statistical information. Furthermore, the generated results are adjusted according to the user's emotional state.

[1465] Input: Palmistry feature data, Tarot feature data, and emotional state data

[1466] Output: Predictive information adjusted based on emotions

[1467] Specific behavior:

[1468] Emotion information and palm or tarot data are input into the generative model.

[1469] Use TensorFlow to generate prediction information.

[1470] Tailor predictive information to the user's emotional state.

[1471] Step 5:

[1472] The server sends the fortune-telling results generated by the generative model to the device. This is done via internet communication again. The data is converted into a format that is easy for the device to understand (e.g., JSON format) and then sent.

[1473] Input: Emotionally adjusted prediction information

[1474] Output: Fortune telling results sent to the device

[1475] Specific behavior:

[1476] The generated fortune-telling results are collected into a packet.

[1477] Send it to your device via your internet connection.

[1478] Step 6:

[1479] The terminal displays the fortune-telling results received from the server to the user. The user can check the results and select the next action. The fortune-telling results are displayed in a format suitable for the user's terminal.

[1480] Input: Fortune telling result sent from the server

[1481] Output: Fortune telling result displayed to the user

[1482] Specific behavior:

[1483] Analyze the data received from the server and reflect the results in the display UI.

[1484] The user sees the results on the device screen.

[1485] (Application example 2)

[1486] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1487] Current predictive information systems have difficulty providing personalized information based on the user's emotions. Furthermore, rather than simply analyzing data, it is necessary to provide more accurate counseling and fortune-telling results by providing feedback based on emotions.

[1488] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for accepting input from a user, means for performing analysis based on the accepted input, means for applying a generative model that generates predictive information using the analysis results, means for analyzing emotions based on the generated predictive information, means for generating predictive information based on the analyzed emotional information, and means for providing the generated predictive information to the user. This makes it possible to provide personalized predictive information based on the user's emotions.

[1489] "User" refers to a person who uses the system.

[1490] "Input" refers to the data or information that a user provides to a system.

[1491] "Analysis" refers to the process of extracting information from input data and drawing specific conclusions or predictions.

[1492] A "generative model" refers to a computational model for generating predictive information using a machine learning algorithm.

[1493] "Predictive information" refers to information about future events or trends that is generated based on analytical results.

[1494] "Emotion analysis" refers to the process of determining a user's emotional state from facial expression data and other inputs.

[1495] "Emotional information" refers to data about a user's emotional state obtained through emotion analysis.

[1496] "Personalization" refers to tailoring information to each individual user's specific needs and feelings.

[1497] "Image data" refers to visual information provided in the form of still images or video.

[1498] A "machine learning algorithm" refers to a computational method that learns patterns from data and makes predictions or decisions based on them.

[1499] The system for realizing this invention is composed of the following program: This program analyzes data entered by a user, uses a machine learning algorithm to generate predictive information based on emotion information, and provides it to the user.

[1500] Hardware used

[1501] Device: Smartphone, tablet, or computer

[1502] Display devices: smart glasses, head-mounted displays

[1503] Analysis server: A high-performance calculation server (e.g., an EC2 instance on Amazon Web Services (AWS))

[1504] Software used

[1505] Facial expression recognition library: OpenCV

[1506] Sentiment analysis engine: Microsoft Azure Cognitive Services

[1507] Machine learning libraries: TensorFlow, PyTorch

[1508] Database: MongoDB, MySQL

[1509] Program processing flow

[1510] 1. The user uses the device to input the data they wish to receive for fortune telling or counseling. The input data includes the user's text information and image data required for fortune telling.

[1511] 2. The device uses the user's camera to collect facial expression data in real time, which is then used for later analysis.

[1512] 3. The analysis server receives the input data and facial expression data sent from the device. The facial expression data is analyzed using OpenCV to extract the emotional state.

[1513] 4. Microsoft Azure Cognitive Services, an emotion analysis engine, quantitatively evaluates the emotional state based on the extracted facial expression data and generates emotional information.

[1514] 5. Use a machine learning library (TensorFlow or PyTorch) to generate predictions based on the sentiment and user-supplied data, referencing historical data and statistical information to obtain more accurate results.

[1515] 6. The generated forecast information is provided to the user via the terminal.

[1516] Specific use cases

[1517] Consider a case where a user selects a relaxation menu at a relaxation salon. The user selects palm reading on their device and uploads a photo of their palm. At this time, the smart glasses also collect the user's facial expression data in real time. The server analyzes the palm image and simultaneously performs emotion analysis using the facial expression data. Using the generative model, the server generates a result such as, "Your lifeline is very long and you have good health luck. You may be feeling anxious at present, but things will improve in the future," and displays this result to the user.

[1518] Prompt Sentence Examples

[1519] Below is an example of a prompt for this system:

[1520] Customer facial expression data: {facial expression data}

[1521] Customer emotions: Anxiety, tension

[1522] Past counseling data: {Past data}

[1523] What I want: I want to relax

[1524] --Generative Model Prompt--

[1525] Generate personalized relaxation menus and counseling content based on the customer's emotional state.

[1526] In this way, the system combines highly accurate emotion analysis with predictive information to provide users with personalized information.

[1527] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1528] Step 1:

[1529] The device accepts input from the user regarding their desired fortune-telling or counseling. Specifically, the user uploads text information or image data (e.g., a photo of their palm) to the device. The input data is stored in a local database for subsequent analysis.

[1530] Step 2:

[1531] The device collects the user's facial expression data in real time. It divides the video data captured by the camera into frames and uses the OpenCV library to perform facial recognition and extract feature points. It analyzes the facial feature points and generates numerical data of the facial expression data.

[1532] Step 3:

[1533] The device sends the collected input data and facial expression data to the analysis server. The transmitted data is sent to the server's analysis engine via an API. The input data includes the user's text information, image data, and facial expression data.

[1534] Step 4:

[1535] The server receives the data sent from the device and first analyzes the image data. Specifically, the server uses an image recognition algorithm to extract the palm's characteristic points and convert them into numerical data. For image recognition, a deep learning model (e.g., VGG16 or ResNet) is used.

[1536] Step 5:

[1537] The server uses an emotion analysis engine (Microsoft Azure Cognitive Services) to analyze the facial expression data and identify the user's emotional state. Based on the facial expression data received as input, it determines the type of emotion (e.g., joy, anxiety, sadness) and outputs the emotional information as numerical data.

[1538] Step 6:

[1539] The server runs a generative model using a machine learning library (TensorFlow or PyTorch). Based on the palm reading data and emotion information received as input, the generative model generates predictions. The predictions (e.g., fortune-telling results or counseling advice) are generated by the generative AI model.

[1540] Step 7:

[1541] The server sends the generated forecast information to the device using the REST API in JSON format. The device then displays the received forecast information to the user.

[1542] Step 8:

[1543] The device provides users with predictive information and allows them to select their next action based on that information, for example, by providing an interactive UI for users to select a relaxation menu or request further counseling.

[1544] In this way, through the processing steps, personalized prediction information according to the user's emotions is provided.

[1545] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1546] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1547] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1548] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1549] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1550] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1551] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1552] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1553] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1554] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1555] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1556] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1557] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1558] 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.

[1559] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1560] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1561] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1562] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1563] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1564] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1565] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1566] The following is further disclosed regarding the above embodiment.

[1567] (Claim 1)

[1568] a means for accepting input from a user;

[1569] means for performing analysis based on the received input;

[1570] means for applying a generative model that uses the analysis results to generate predictive information;

[1571] a means for providing the generated forecast information to a user;

[1572] A system including:

[1573] (Claim 2)

[1574] 10. The system of claim 1, further comprising means for performing analysis of the image data.

[1575] (Claim 3)

[1576] The system of claim 1 , wherein the generative model is based on a machine learning algorithm.

[1577] (Claim 4)

[1578] 2. The system according to claim 1, further comprising means for allowing a user to select a type of fortune telling.

[1579] (Claim 5)

[1580] 10. The system of claim 1, further comprising means for displaying the forecast information in text format.

[1581] (Claim 6)

[1582] 3. The system of claim 2, further comprising means for analyzing palm line characteristics if the input is palm line image data.

[1583] (Claim 7)

[1584] The system of claim 1, further comprising means for performing analysis based on the arrangement of tarot cards when the input is arrangement data of tarot cards.

[1585] "Example 1"

[1586] (Claim 1)

[1587] a means for accepting input from a user;

[1588] means for transmitting the received input to a server;

[1589] means for performing analysis of the data based on the received input;

[1590] A means for applying a generative AI model that generates predictive information using the analysis results;

[1591] a means for providing the generated forecast information to a user;

[1592] A system including:

[1593] (Claim 2)

[1594] 10. The system of claim 1, further comprising means for performing analysis of the image data.

[1595] (Claim 3)

[1596] 2. The system of claim 1, wherein the generative AI model uses prompt sentences based on machine learning algorithms.

[1597] "Application Example 1"

[1598] (Claim 1)

[1599] a means for accepting input from a user;

[1600] means for performing analysis based on the received input;

[1601] means for applying a generative model that uses the analysis results to generate predictive information;

[1602] a means for providing the generated forecast information to a user;

[1603] A means for processing input data using image recognition technology to provide fortune-telling results;

[1604] a means for inputting prompt sentences based on a particular category into a generative AI model;

[1605] A means to provide consistent and reliable fortune-telling results online, and

[1606] A system including:

[1607] (Claim 2)

[1608] 10. The system of claim 1, further comprising means for performing analysis of the image data.

[1609] (Claim 3)

[1610] The system of claim 1 , wherein the generative model is based on a machine learning algorithm.

[1611] "Example 2: Combining Emotion Engines"

[1612] (Claim 1)

[1613] a means for accepting input from a user;

[1614] means for performing analysis based on the received input;

[1615] means for applying a generative model to generate predictive information based on the analysis results and the user's emotional state;

[1616] a means for providing the generated forecast information to a user;

[1617] A system including:

[1618] (Claim 2)

[1619] 10. The system of claim 1, further comprising means for performing an analysis of the image data and means for analyzing the user's emotions.

[1620] (Claim 3)

[1621] The system of claim 1 , wherein the generative model is based on a machine learning algorithm.

[1622] "Application example 2 when combining emotion engines"

[1623] (Claim 1)

[1624] a means for accepting input from a user;

[1625] means for performing analysis based on the received input;

[1626] means for applying a generative model that uses the analysis results to generate predictive information;

[1627] means for analyzing emotions based on the generated prediction information;

[1628] means for generating prediction information according to the analyzed emotion information;

[1629] a means for providing the generated forecast information to a user;

[1630] A system including:

[1631] (Claim 2)

[1632] 10. The system of claim 1, further comprising means for performing analysis of the image data.

[1633] (Claim 3)

[1634] The system of claim 1 , wherein the generative model is based on a machine learning algorithm and uses an external library for sentiment analysis. [Explanation of symbols]

[1635] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for accepting input from a user; means for performing analysis based on the received input; means for applying a generative model that uses the analysis results to generate predictive information; a means for providing the generated forecast information to a user; A system including:

2. 10. The system of claim 1, further comprising means for performing analysis of the image data.

3. The system of claim 1 , wherein the generative model is based on a machine learning algorithm.

4. 2. The system according to claim 1, further comprising means for allowing a user to select a type of fortune telling.

5. 10. The system of claim 1, further comprising means for displaying said forecast information in text form.

6. 3. The system of claim 2, further comprising means for analyzing palm line characteristics if the input is palm line image data.

7. The system of claim 1 further comprising means for performing analysis based on the arrangement of tarot cards when the input is arrangement data of tarot cards.

Images