System

Abstract

A system is provided.SOLUTION: A system comprising: an input unit configured to allow a user to post text and an image; a communication unit configured to transmit text and image data input by the input unit to a server; a generation unit configured to analyze the text data and the image data in the server and aggregate information; a generation unit configured to generate an explanatory note from the information aggregated by the generation unit; and a provision unit configured to provide the explanatory note to another 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] Current SNSs have the problem that the information users need is both vast and mixed with inaccurate information, making it difficult to quickly find the information they need. Obtaining accurate information in real time is particularly difficult during events and disasters. Therefore, there is a demand for a system that allows users to quickly and concisely obtain reliable information tailored to their own situation. [Means for solving the problem]

[0005] The present invention provides a system that includes an input means for users to post text and images and a communication means for transmitting the input text and image data to a server. The server analyzes the text data and image data, aggregates the information, and generates a description using a generation means. The generation means generates questions for the user to fill in missing information and includes a reanalysis means for receiving additional information from the user, thereby generating a final summary. This provides a system that allows users to obtain concise and reliable information in real time.

[0006] "User" means any person or entity that uses the System to post or retrieve information.

[0007] "Text" refers to character string information entered by a user and sent to the system.

[0008] "Image" refers to visual data entered by a user and sent to the system.

[0009] "Input means" refers to an interface through which a user inputs text and images into the system.

[0010] "Communication means" refers to the network and related technologies for transmitting data entered by the input means to the server.

[0011] "Server" refers to a computer that receives, analyzes, and stores data sent by users.

[0012] "Analysis" refers to the process of semantically understanding input text and image data and extracting important information.

[0013] "Information aggregation generator" refers to a mechanism that executes the process of gathering and synthesizing useful information from the analyzed data.

[0014] "Explanation" refers to a concise sentence generated based on the aggregated information.

[0015] The "means for providing" refers to an interface for displaying the generated explanation to other users.

[0016] The "question generation means" refers to a mechanism that generates a question to supplement the collected information when the collected information is insufficient, and sends the question to the user.

[0017] The "re-analysis means" refers to the process of receiving additional information from the user and re-analyzing it to generate the final summary sentence. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The program processing will be explained in natural language below, along with specific examples.

[0040] Program processing

[0041] 1. Collecting posts

[0042] Users use their devices to post text and images about events and disasters to a social networking-style application.

[0043] The terminal transmits the text and image data entered by the user to the server.

[0044] The server stores the received post data in a database.

[0045] 2. Data collection and analysis

[0046] The server preprocesses the received text and image data and sends it to the generation AI.

[0047] The generative AI analyzes text data to extract important keywords and phrases, and also analyzes image data and associates it with the text data.

[0048] The generative AI integrates the analysis results and generates a comprehensive explanation.

[0049] 3. Question generation

[0050] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[0051] The server sends the generated question to the user.

[0052] 4. Obtaining additional information

[0053] The user enters additional text or images in response to the received question and submits it.

[0054] The terminal transmits the user's answer to the server.

[0055] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[0056] 5. Provision of Information

[0057] The generation AI generates the final complete description.

[0058] The server makes this description accessible to other users.

[0059] Users can view the server-provided description and, if desired, view the original post.

[0060] Specific examples

[0061] 1. Collecting posts

[0062] User: Posts to the application the text "I'm at a big music festival today. Stage A is especially crowded!" along with an image showing how crowded the stage is.

[0063] Terminal: Sends posted text and images to the server.

[0064] Server: Stores the submission in a database and sends the text and images for analysis.

[0065] 2. Data collection and analysis

[0066] Generative AI: Extracts keywords from text such as "big music festival," "stage A," and "crowded," and recognizes crowded situations from images.

[0067] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[0068] 3. Question generation

[0069] Generative AI: Determines that more specific information is lacking and generates questions such as "What is the name of the main artist?"

[0070] Server: Sends the question to the user.

[0071] 4. Obtaining additional information

[0072] User: Enters answer "The main artist is Band X" and submits.

[0073] Terminal: Sends the answer to the server.

[0074] Server: Sends additional information to the generating AI for reanalysis.

[0075] 5. Provision of Information

[0076] Generative AI: Generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[0077] Server: Provides the final description for other users to see.

[0078] Users: can view the provided description and, if desired, the original post.

[0079] In this way, the system can efficiently provide users with the real-time, accurate information they desire.

[0080] The processing flow will be explained below.

[0081] Step 1:

[0082] Users use their own devices to input text and images into a social networking-style application and post.

[0083] Step 2:

[0084] The terminal transmits the posted text and image data to the server.

[0085] Step 3:

[0086] The server stores the received post data in a database.

[0087] Step 4:

[0088] The server preprocesses the stored text and image data and sends it to the generation AI.

[0089] Step 5:

[0090] The generative AI analyzes the received text data and extracts important keywords and phrases.

[0091] Step 6:

[0092] The generative AI analyzes image data and associates it with text data (e.g., "A large crowd is gathering").

[0093] Step 7:

[0094] The generative AI integrates the analysis results and generates an initial description.

[0095] Step 8:

[0096] The generation AI determines whether there are any deficiencies in the generated description.

[0097] Step 9:

[0098] Generative AI generates questions to fill in missing information (e.g., "Please tell me specific location and stage information").

[0099] Step 10:

[0100] The server sends the generated question to the original posting user.

[0101] Step 11:

[0102] The user enters additional information (text or images) in response to the question and submits the answer.

[0103] Step 12:

[0104] The terminal transmits the user's response data to the server.

[0105] Step 13:

[0106] The server then sends the additional information back to the generation AI for reanalysis.

[0107] Step 14:

[0108] The generation AI generates the final description based on the additional information.

[0109] Step 15:

[0110] The server displays the final description in the application's UI for other users to access.

[0111] Step 16:

[0112] The user sees the final description provided by the server and, if desired, the original post.

[0113] Example 1

[0114] 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."

[0115] Existing SNS-style information gathering and provision systems have difficulty effectively analyzing text and image data posted by users and providing appropriate information to other users. In particular, they lack the ability to perform detailed analysis of posted content, supplement missing information, or incorporate additional information, making it difficult to provide accurate information in real time.

[0116] 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.

[0117] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for preprocessing and analyzing the text data and image data in the server, a generation means for generating an explanatory text from the information analyzed by the generation means, a provision means for providing the explanatory text to other users, a reanalysis means for receiving additional information from users and reanalyzing it to generate a final summary, and a storage means for saving the text and image data input by users in a database. This makes it possible to effectively analyze the information posted by users and obtain additional information as needed, thereby providing accurate information to other users in real time.

[0118] "Input means" is an interface through which users contribute text and images to the system.

[0119] The "communication means" is a function for transmitting text and image data posted by the user via the input means to the server.

[0120] The "generation means" is a function for preprocessing and analyzing text data and image data received by the server.

[0121] The "providing means" is a function for disclosing and providing the description generated by the generating means to other users.

[0122] The "re-analysis means" is a function that receives additional information from the user and re-analyzes the data to generate the final summary.

[0123] The "storage means" is a function for storing the text and image data entered by the user in a database.

[0124] The "question generation means" is a function for generating a question for the user to supplement the missing information and sending the question to the user.

[0125] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The purpose of this system is to enable users to collect information about events and disasters in real time and provide accurate and detailed information to other users. A specific embodiment of this system is described below.

[0126] System configuration

[0127] The system includes an input means for users to post text and images, a communication means, a generation means, a provision means, a reanalysis means, and a storage means. These means are primarily implemented using servers, terminals, and generative AI models (e.g., OpenAI's GPT-4).

[0128] Hardware and software used

[0129] User device: A device such as a smartphone, tablet, or PC.

[0130] Server: High-performance cloud server (e.g. AWS, Google Cloud Platform).

[0131] Generative AI models: Models that perform advanced natural language processing and image analysis, such as OpenAI's GPT-4.

[0132] Explanation of program processing

[0133] Collecting Posts

[0134] Users use their devices to post text and images about events and disasters to a social networking-style application.

[0135] The terminal transmits the text and image data entered by the user to the server.

[0136] The server stores the received post data in a database.

[0137] Data aggregation and analysis

[0138] The server preprocesses the received text and image data and sends it to the generative AI model, which includes string cleansing, removing unnecessary tags, and adjusting image resolution.

[0139] The generative AI model extracts important keywords and phrases from text data and also analyzes image data and associates it with the text data.

[0140] The generative AI integrates the analysis results and generates a comprehensive explanation.

[0141] question generation

[0142] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[0143] The server sends the generated question to the user.

[0144] Obtaining additional information

[0145] The user enters additional text or images in response to the received question and submits it.

[0146] The terminal transmits the user's answer to the server.

[0147] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[0148] Providing information

[0149] The generation AI generates the final complete description.

[0150] The server makes this description accessible to other users.

[0151] Users can view the server-provided description and, if desired, view the original post.

[0152] Specific examples

[0153] 1. A user uses their smartphone to post the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing how crowded the stage is.

[0154] 2. The device sends the posted text and images to the server.

[0155] 3. The server stores the post in a database and sends the text and images for analysis.

[0156] 4. The generative AI model extracts keywords from the text, such as "big music festival," "stage A," and "crowded," and recognizes the crowded situation from the image.

[0157] 5. The AI ​​generates the initial description: "Stage A at the music festival is currently very crowded."

[0158] 6. The generative AI determines that more specific information is lacking and generates questions such as, "What is the name of the main artist?"

[0159] 7. The server sends the question to the user.

[0160] 8. The user answers, "The main artist is Band X," and submits.

[0161] 9. The device sends the response to the server.

[0162] 10. The server sends additional information to the generation AI for reanalysis.

[0163] 11. The AI ​​generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[0164] 12. The server provides the final description for other users to see.

[0165] 13. Users can view the description provided and, if necessary, the original post.

[0166] Prompt Sentence Examples

[0167] "I'm at a big music festival. Stage A seems particularly busy. I need more information. Can you tell me the names of the main artists and how busy the other stages are?"

[0168] In this way, the present invention analyzes information provided by users in real time, supplements it with necessary additional information in a timely manner, and enables other users to receive accurate and detailed information.

[0169] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0170] Step 1:

[0171] A user uses their device to launch a social networking-style application and input text and images related to an event or disaster. For example, they can input text such as "I'm at a big music festival today. Stage A is particularly crowded and it's really tough!" along with an image showing the crowding situation on the stage. The input data is temporarily saved on the device and then sent to the server via a communication means by pressing the post button.

[0172] Step 2:

[0173] The terminal sends the text and image data entered by the user to the server. Specifically, the terminal divides the data into packets and transfers them to the server using the TCP / IP protocol. If the server confirms receipt, the terminal displays a notification of successful transmission to the user. At this stage, the input is the user's submitted data, and the output is a notification of successful transmission to the server.

[0174] Step 3:

[0175] The server saves the received text and image data in a database. Specifically, the server saves the text data as a string and the image data in binary format in storage. The saved data is placed in a queue for preprocessing, and the next process begins. The input in this step is the posted data received from the device, and the output is the data being saved to the database.

[0176] Step 4:

[0177] The server preprocesses the posted data stored in the database. Preprocessing includes removing unnecessary tags, normalizing text, adjusting image size, etc. This organizes the input data for the generative AI model. The input in this step is the posted data read from the database, and the output is the preprocessed data.

[0178] Step 5:

[0179] The server sends the preprocessed data to the generative AI model. Specifically, it uses an API to pass text data and image data to the generative AI. The generative AI model (e.g., OpenAI's GPT-4) extracts important keywords and phrases from the text data and also analyzes and associates them with the image data. The input in this step is the preprocessed data, and the output is the analysis results.

[0180] Step 6:

[0181] The generation AI integrates the analysis results and generates an initial description. Specifically, it creates a description such as "Stage A at the music festival is currently very crowded." The generated description is returned to the server and proceeds to the next step. The input in this step is the analysis data sent to the generation AI, and the output is the initial description.

[0182] Step 7:

[0183] If the generation AI determines that the description is incomplete, it generates a question to fill in the gaps. For example, it generates a question like, "What is the name of the main artist?" The generated question is returned to the server and is ready to be sent to the user. The input in this step is the initial description, and the output is the generated question.

[0184] Step 8:

[0185] The server sends the generated question to the user. Specifically, it sends the question to the user's device as a push notification or an in-app message. The input in this step is the generated question, and the output is a question notification to the user.

[0186] Step 9:

[0187] The user inputs additional text or image information in response to the received question and sends it to the server from their device. For example, they provide an answer such as "The main artist is Band X." The input in this step is the question from the server, and the output is the additional information from the user.

[0188] Step 10:

[0189] The terminal sends the additional information from the user to the server. This process is the same as in step 2, where additional text and image data are sent. The input in this step is the additional information, and the output is a notification of successful transmission to the server.

[0190] Step 11:

[0191] The server receives the additional information and sends it to the generative AI model for analysis again. The generative AI model takes the additional information into account to generate the final summary. For example, it creates a description such as "Band X is performing on Stage A at a music festival, and it's very crowded." The input in this step is the additional information, and the output is the final summary.

[0192] Step 12:

[0193] The server publishes the generated final description for other users to access. Specifically, it adds the description to a social networking application feed and updates it in real time. The input for this step is the final summary, and the output is the published description.

[0194] Step 13:

[0195] The user views the final description provided by the server and, if necessary, checks the original post. This allows the user to obtain accurate information in real time. The input in this step is the description from the server, and the output is the user's viewing result.

[0196] This is the specific flow of processing in the program for this system. At each step, the input data is processed appropriately, and ultimately a mechanism is established to provide the user with accurate and detailed information.

[0197] (Application example 1)

[0198] 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."

[0199] In today's world, there is a need to quickly and accurately obtain and share real-time information about events, disasters, and other events. However, conventional systems often take time to properly analyze and disseminate information posted by users, which impairs real-time reporting. Furthermore, inaccurate reports due to incomplete information can become a problem. The present invention aims to solve these problems and provide a system that provides accurate information in real time.

[0200] 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.

[0201] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data and aggregating information in the server, a generation means for generating an explanatory text as a real-time breaking news report from the information aggregated by the generation means, a provision means for providing the explanatory text to other users, and a notification means for sending a push notification to the user based on the explanatory text. This makes it possible to quickly analyze information posted by users and accurately provide it to other users in real time.

[0202] "Input means" refers to a device or interface through which a user can post text and images.

[0203] "Communication means" refers to network communication technologies and protocols for transmitting text and image data input by the input means to a server.

[0204] "Generation means" refers to algorithms or software that have the function of analyzing the text data and image data received by the server and aggregating the information.

[0205] "Explanation generation means" refers to algorithms or software for generating real-time news from aggregated information.

[0206] "Providing means" refers to an interface or service for providing the generated description to other users.

[0207] "Notification means" refers to the technology or method for sending a push notification to a user based on the generated description.

[0208] "Question generation means" refers to an algorithm or software that generates questions to fill in missing information and sends them to the user.

[0209] "Reanalysis means" refers to algorithms or software that have the ability to receive additional information from the user and reanalyze the final summary and breaking news content based on that information.

[0210] In order to implement the present invention, the following system configuration and program processing will be described.

[0211] System Configuration

[0212] This invention is a social networking service-style information collection and provision system where users post text and images. The system mainly consists of the following components:

[0213] Input means: A smartphone or smart glasses with an interface that allows the user to post text and images.

[0214] Communication means: Technology (Wi-Fi, 4G / 5G, etc.) that transmits text and image data entered by the input means to a server.

[0215] Server: The central component that receives and analyzes data. Specific hardware used is a cloud server such as Amazon Web Services (AWS).

[0216] Generation method: Software that analyzes received data and generates information. For AI-related analysis, services such as Amazon Comprehend and Amazon Rekognition are used.

[0217] Description generator: An AI model (e.g., OpenAI GPT-3) for generating descriptions from aggregated information.

[0218] Delivery medium: A web interface or application that delivers the generated descriptions to other users.

[0219] Notification method: Technology that sends push notifications based on the description (e.g., Amazon SNS).

[0220] Program processing

[0221] The processing of this system is carried out in the following sequence:

[0222] 1. Collection of User Submissions

[0223] Users post text and images related to events and disasters using their smartphones or smart glasses.

[0224] When a post is made, the input means transmits the data to the server using the communication means.

[0225] 2. Data Preprocessing and Analysis

[0226] The server receives the data using AWS Lambda and stores it in Amazon DynamoDB.

[0227] The stored data is then uploaded to AWS S3 for text and image analysis using Amazon Comprehend and Amazon Rekognition.

[0228] 3. Generating Descriptions

[0229] Based on the received data and analysis results, a generative AI model using OpenAI GPT-3 generates explanatory text as real-time breaking news.

[0230] 4. Question generation

[0231] If the description contains missing information, the generative AI model generates a question requesting additional information, and the server sends the question to the user.

[0232] 5. Collection of additional information

[0233] The user enters additional information in response to the question, which is then sent back to the server.

[0234] The reanalysis means receives additional information and generates the final narrative and flash content.

[0235] 6. Provision of Information

[0236] The server provides the generated information to other users via AWS CloudFront and sends push notifications using notification methods.

[0237] Specific examples

[0238] Here's an example of how this system can be used in practice:

[0239] 1. A user posts about an event: The user posts to the application the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing the crowds at the stage.

[0240] 2. Analysis on the server: The server analyzes keywords such as "big music festival," "stage A," and "crowded" using Amazon Comprehend, and recognizes the level of congestion from the image using Amazon Rekognition.

[0241] 3. Automatic question generation for missing information: The generative AI model requires the name of the main artist as supplementary information, so it generates the question, "What is the name of the main artist?"

[0242] 4. Receive additional information from the user: The user responds, "The main artist is Band X," and sends this to the server.

[0243] 5. Final information provision: The final description is generated: "Band X will be performing on Stage A at the music festival, and it is very crowded," and is notified to other users.

[0244] Examples of prompts to input to a generative AI model:

[0245] There is a post that says "Stage A at a huge music festival is very crowded." Extract keywords from the post's details and images, and generate specific explanations and questions about the missing information.

[0246] Post content:

[0247] Text: I'm at a big music festival today. Stage A is especially crowded and it's tough!

[0248] Image: (Image data URL)

[0249] Generated keywords:

[0250] Big music festival

[0251] Stage A

[0252] congestion

[0253] Questions to generate:

[0254] What is the name of the main artist?

[0255] This system makes it possible to efficiently collect and quickly distribute accurate information in real time.

[0256] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0257] Step 1:

[0258] Collection of User Submissions

[0259] Input: The user uses a smartphone or smart glasses to input text and images related to the event or disaster.

[0260] Specific operation: Users post information about events and disaster situations to the application using text and images. For example, they might post something like, "I'm at a big music festival today. Stage A is especially crowded and it's really tough!"

[0261] Output: The entered text and image data is sent to the server via the application.

[0262] Step 2:

[0263] Data Preprocessing

[0264] Input: Text and image data submitted by the user.

[0265] How it works: The device receives text and image data and sends it to an AWS Lambda function via a RESTful API, where the received data is formatted and stored in Amazon DynamoDB, and the image data is uploaded to Amazon S3.

[0266] Output: Formatted text data and saved image data are sent to the next analysis step.

[0267] Step 3:

[0268] Data analysis

[0269] Input: Formatted text data and stored image data.

[0270] How it works: The server uses Amazon Comprehend to analyze the text data and extract important keywords. At the same time, it uses AWS Rekognition to analyze the image data and identify objects and situations within the image. For example, keywords such as "big music festival," "stage A," and "crowded" are extracted.

[0271] Output: The extracted keywords and analysis information are sent to the generative AI model.

[0272] Step 4:

[0273] Generating Descriptions

[0274] Input: Extracted keywords and analysis information.

[0275] How it works: The server uses OpenAI GPT-3 to generate real-time news descriptions based on the results of text and image analysis. For example, it might generate a description such as, "Stage A at the music festival is currently very crowded."

[0276] Output: The generated description is saved in the server's data store.

[0277] Step 5:

[0278] Missing information question generation

[0279] Input: The generated description.

[0280] How it works: Based on the description, the generative AI model identifies missing information and generates questions accordingly, such as "What is the name of the main artist?"

[0281] Output: The generated questions are stored on the server and sent to the user.

[0282] Step 6:

[0283] Collecting additional information

[0284] Input: The question sent by the server.

[0285] Specific operation: The user inputs additional information (text or image) in response to the received question, which is then retransmitted to the server via the terminal. For example, an answer such as "The main artist is Band X" is sent.

[0286] Output: Additional information is saved on the server, ready for reanalysis.

[0287] Step 7:

[0288] Reanalysis and generation of final description

[0289] Input: Additional information (text or image).

[0290] How it works: The server uses the generative AI model again to generate a final description based on the additional information, such as "Band X is performing on Stage A at the music festival, and it's very crowded."

[0291] Output: The final description is saved on the server and sent to the next serving step.

[0292] Step 8:

[0293] Information and Notification

[0294] Input: Final description.

[0295] Specific operation: The server publishes the generated description through a means of provision so that other users can access it. In addition, the user is notified as a breaking news item via the push notification function using AWS SNS.

[0296] Output: The user sees the description provided as real-time news and receives a push notification.

[0297] Through the above steps, information posted by users can be quickly analyzed and accurately provided to other users in real time.

[0298] 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.

[0299] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[0300] Program processing

[0301] 1. Collecting posts

[0302] Users can use their devices to input and post text and images into a social networking-style application.

[0303] The terminal transmits the posted text and image data to the server.

[0304] The server stores the received post data in a database.

[0305] 2. Data collection and analysis

[0306] The server preprocesses the text data and image data and sends them to the generation AI.

[0307] Generative AI analyzes text data to extract important keywords and phrases.

[0308] The generative AI also analyzes image data and associates it with text data.

[0309] The generative AI integrates the analysis results and generates an initial description.

[0310] 3. Emotional Recognition

[0311] The emotion engine analyzes user emotions from posted text and images.

[0312] The generative AI adjusts the tone of the generated description taking into account the user's emotions (e.g., a bright tone for positive emotions and a calm tone for negative emotions).

[0313] 4. Question generation and submission

[0314] If there are any gaps in the generated explanation, the generation AI will generate questions to fill in the gaps.

[0315] The emotion engine adjusts the tone and content of questions based on the user's emotions.

[0316] The server sends the generated question to the original posting user.

[0317] 5. Obtaining additional information

[0318] The user enters additional text or images in response to the received question and submits it.

[0319] The terminal transmits the user's answer to the server.

[0320] 6. Reanalysis and final summary generation

[0321] The server sends the additional information back to the generation AI for reanalysis.

[0322] The generation AI generates the final description based on the additional information.

[0323] The emotion engine makes final adjustments by checking whether the tone of the final description matches the user's emotions.

[0324] 7. Provision of Information

[0325] The server displays the final description in the application's UI for other users to access.

[0326] Users will see the final description provided and can also view the original post if desired.

[0327] Specific examples

[0328] 1. Collecting posts

[0329] User: Posts to the application the text "I'm at a music festival right now. Stage A is very crowded and I'm feeling a bit exhausted." along with a photo of the crowded stage.

[0330] Terminal: Sends posted text and images to the server.

[0331] Server: Stores the submission in a database and sends the text and images for analysis.

[0332] 2. Data collection and analysis

[0333] Generative AI: Extracts keywords from the text, such as "music festival," "Stage A," "very crowded," and "tired."

[0334] Generative AI: Recognizes congestion status from images.

[0335] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[0336] 3. Emotional Recognition

[0337] Emotion engine: Recognizes the negative emotion of "tired" from the user's text and adjusts the description to a calmer tone.

[0338] 4. Question generation and submission

[0339] Generative AI: Determines that more specific information is lacking and generates questions such as, "Please tell me the specific stage names."

[0340] Emotion Engine: Adjust the tone of your question to something like, "You seem tired, can you tell me the name of the stage?"

[0341] Server: Sends the question to the user.

[0342] 5. Obtaining additional information

[0343] User: Answers "Main Stage A" and submits.

[0344] Terminal: Sends the answer to the server.

[0345] 6. Reanalysis and final summary generation

[0346] Server: Sends additional information to the generating AI for reanalysis.

[0347] Generative AI: Generates the final description: "Main Stage A at the music festival is very crowded, with many people gathered."

[0348] Emotion Engine: Check the tone of your description and adjust it if necessary.

[0349] 7. Provision of Information

[0350] Server: Provides the final description for other users to see.

[0351] Users: can view the provided description and also see the original post.

[0352] In this way, the present invention is a system that makes it possible to provide information in real time that takes into account the user's emotions, thereby improving the user experience.

[0353] The processing flow will be explained below.

[0354] Program processing

[0355] Step 1:

[0356] A user logs into a social networking-style application on their device, then enters "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit tired," attaches an image showing the crowded stage, and hits the post button.

[0357] Step 2:

[0358] The terminal sends the text and image data posted by the user to the specified server endpoint using an HTTP POST request.

[0359] Step 3:

[0360] The server stores the received text and image data in a database, then preprocesses the text and image data and sends them to the generative AI module for analysis.

[0361] Step 4:

[0362] The generative AI extracts important keywords and phrases from the text data, specifically identifying keywords such as "music festival," "Stage A," "very crowded," and "tired."

[0363] Step 5:

[0364] Generative AI analyzes image data and associates the image content with text data. For example, it can detect situations where many people are gathered in an image and integrate that information into the text analysis results.

[0365] Step 6:

[0366] The generative AI generates an initial description based on the results of text and image analysis, such as a summary like "Stage A at a music festival is currently very crowded."

[0367] Step 7:

[0368] The emotion engine analyzes the user's text to determine their emotions. Based on the keyword "tired," it recognizes the user's emotion as negative and adjusts the description to a calmer tone.

[0369] Step 8:

[0370] The generation AI checks whether the generated description is missing anything. If so, it generates a follow-up question, and the emotion engine adjusts the tone and content of the question. For example, it creates a question like, "You seem tired. Could you tell me the name of the specific stage?"

[0371] Step 9:

[0372] The server sends the generated question to the user, notifying them in a form that is easy for the user to understand and prompting them to provide additional information.

[0373] Step 10:

[0374] The user responds to the received question message with "Main Stage A" and presses the send button again.

[0375] Step 11:

[0376] The terminal transmits the user's answer to the server.

[0377] Step 12:

[0378] The server stores the additional information sent by the user in a database and performs re-analysis on the generated AI.

[0379] Step 13:

[0380] The generation AI reanalyzes the data based on additional information from the user and generates the final description: "Main Stage A of the music festival is very crowded, with many people gathered."

[0381] Step 14:

[0382] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary.

[0383] Step 15:

[0384] The server makes this final, adjusted description available to other users for access, for example, by displaying it on the application's home screen or on specific information pages.

[0385] Step 16:

[0386] Users can access the application on their devices to view the final description provided, and can also view the original post if desired.

[0387] Specific examples

[0388] 1. Collecting posts

[0389] User: Posts the text "I'm at a music festival right now. Stage A is very crowded and I'm a bit tired." along with an image showing the crowds.

[0390] Terminal: Sends the post to the server.

[0391] Server: Receives the posted content, stores it in a database, and sends the data to the generation AI module.

[0392] 2. Data collection and analysis

[0393] Generative AI: Extracts important keywords and recognizes congestion situations from images.

[0394] Generative AI: Generates the initial description, "Stage A at the music festival is very crowded."

[0395] 3. Emotional awareness and regulation

[0396] Sentiment engine: Recognizes negative sentiment from text and adjusts descriptions accordingly.

[0397] 4. Question generation and additional information acquisition

[0398] Generative AI: Generates questions and an emotional engine adjusts the tone.

[0399] Server: Sends the question to the user.

[0400] User: "Main Stage A"

[0401] Terminal: Sends additional information to the server.

[0402] Server: Resends additional information to the generating AI.

[0403] 5. Final summary generation and serving

[0404] Generative AI: Generates the final description, "Main Stage A at the music festival is very crowded, with many people gathered."

[0405] Emotion Engine: Making final adjustments.

[0406] Server: Provides the final description to other users.

[0407] User: View the final description provided.

[0408] In this way, the present invention realizes a system that provides real-time information that takes into account the user's emotions.

[0409] Example 2

[0410] 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."

[0411] In modern social networking systems, when users post information in real time, the information may not be properly conveyed to other users. Furthermore, the posted information contains emotions, but if these emotions are not taken into consideration, the recipient may misunderstand the information. Furthermore, if information is missing, questions to fill in the gaps are not automatically generated, which hinders the user's experience. Therefore, there is a need for a system that recognizes users' emotions, provides appropriately tailored information to other users, and automatically fills in missing information.

[0412] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0413] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data in the server and aggregating information, a generation means for generating an explanatory text from the aggregated information, an emotion recognition means for adjusting the explanatory text based on the user's emotion, and a provision means for providing the explanatory text to other users, thereby enabling information to be provided in real time taking into account the user's emotion.

[0414] "Input means" refers to a device or interface through which a user submits text and images.

[0415] "Communication means" refers to a network device or protocol for transmitting input text and image data to a server.

[0416] "Generation means" refers to a device or algorithm that analyzes text data and image data on a server and aggregates the information.

[0417] "Emotion recognition means" refers to a device or software for adjusting the generated caption based on the user's emotions.

[0418] "Providing means" refers to a system or interface for providing the generated explanation to other users.

[0419] The term "question generation means" refers to a device or program for generating a question for a user to fill in missing information and sending it to the user.

[0420] "Reanalysis means" refers to a system or process that receives additional information from the user and performs another analysis to generate the final summary.

[0421] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[0422] System configuration

[0423] Input method: Users log in to a social networking-style application using their own devices, such as their smartphones or PCs, and enter text and images to post. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage.

[0424] Communication method: The terminal sends the posted text and image data to the server. Specifically, it makes a POST request to the endpoint using the HTTPS protocol.

[0425] Generation method: The server stores the received text and image data in a database (e.g., MySQL or MongoDB). Next, it performs preprocessing such as tokenizing the text data, removing noise, and resizing and formatting the image data. After preprocessing is complete, the data is sent to the generation AI, which analyzes it using, for example, OpenAI's ChatGPT to extract important keywords and phrases. It also analyzes the image data and associates it with the text data. An initial description is generated based on the analysis results. For example, it generates a description such as, "Stage A at the music festival is currently very crowded."

[0426] Emotion recognition means: An emotion engine (for example, Microsoft's EmoNet) is used to analyze the user's emotions from the posted text and images. For example, it recognizes the negative emotion of "tired." The generation AI adjusts the tone of the generated description taking the user's emotions into account. For example, the description may be calmer, such as "Stage A at the music festival is currently very crowded, and I am feeling a bit tired."

[0427] Question generation means: The generation AI generates questions for the user to fill in missing information. For example, it generates a question such as, "Please tell me the specific stage name." The emotion engine adjusts the tone and content of the question. For example, it may change the tone to something like, "You seem tired, but could you please tell me the specific stage name?" The server sends the generated question to the original poster. Specifically, it sends the question to the user's device as a push notification or in-app message.

[0428] Reanalysis method: The user inputs and sends additional text or images in response to the received question. For example, the user sends the text "This is Main Stage A." The device sends this additional information to the server, which then sends it to the generation AI for reanalysis. The generation AI generates the final description based on the additional information. For example, it generates the final description "Main Stage A at the music festival is very crowded, with many people gathered." The emotion engine checks the tone of the description and makes final adjustments if necessary.

[0429] Delivery method: The server displays the final description in the application's UI for other users to access. Users can view the delivered description, see the original post, and post additional comments and feedback.

[0430] Prompt Sentence Examples

[0431] "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit exhausted. Based on this information, what emotions can you analyze and generate a description for?"

[0432] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0433] Step 1:

[0434] Users log in to a social networking-style application using a device such as a smartphone or PC, and post by entering text and images. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage. This post becomes the input.

[0435] The output is the user's posted data (text and images).

[0436] Step 2:

[0437] The terminal sends the user's posted data to the server. The HTTPS protocol is used to send the data, and the request format is POST. The data sent includes text, images, and the user ID. This is the input data.

[0438] The output is the submitted data that is forwarded to the server.

[0439] Step 3:

[0440] The server stores the received submission data in a database (e.g., MySQL or MongoDB), which makes the text and images persistent. This storage process is part of the data processing. It also performs preprocessing such as tokenizing and denoising the text data, and resizing and formatting the image data.

[0441] The output is preprocessed text and image data.

[0442] Step 4:

[0443] The server sends the preprocessed text and image data to the generative AI model. As a concrete example, we will use a general generative AI as the generative AI model. The preprocessed data (tokenized text and resized images) are input. The generative AI analyzes this data and extracts important keywords and phrases. It also associates them with the text data through image analysis. Data analysis and processing are then performed.

[0444] The output is the analysis results and an initial description (e.g., "Stage A at the music festival is currently very crowded.").

[0445] Step 5:

[0446] The emotion engine analyzes the user's emotions from the posted text and images. Specifically, it uses a common emotion analysis system to obtain emotional information from the text and images. The input data used is the user's posted text, "I'm currently at a music festival. Stage A is very crowded and I'm a bit tired." and the posted image. The emotion engine recognizes the negative emotion of "tired."

[0447] The output is the analyzed emotion information.

[0448] Step 6:

[0449] The generative AI adjusts the tone of the description based on the results of the emotion analysis. It uses the initial description generated earlier as input. To respond to the negative emotion of "tired," it adjusts the description to something like "Stage A at the music festival is currently very crowded, and I am feeling a bit tired." This adjustment process is part of data processing and data calculation.

[0450] The output is a sentiment-adjusted description.

[0451] Step 7:

[0452] If there are gaps in the initial description, the generative AI generates questions to fill in those gaps. The initial description and analyzed emotional information are used as input data. As a specific example, it generates questions such as "Please tell me the specific stage name."

[0453] The emotion engine adjusts the tone and content of the question, for example, "You seem tired, can you tell me the name of the stage?"

[0454] The output is the generated question.

[0455] Step 8:

[0456] The server sends the generated question to the original poster. Specifically, the question is sent to the user's device as a push notification or an in-app message. The input data is the generated question text.

[0457] The output is the question sent to the user terminal.

[0458] Step 9:

[0459] The user inputs additional text or images in response to the received question and submits it. For example, the user might reply, "This is Main Stage A." This response becomes new input data.

[0460] The output is additional information for the user.

[0461] Step 10:

[0462] The terminal sends the user's additional information to the server. Specifically, the terminal sends the user's additional text and images as a POST request.

[0463] The output is additional information that is forwarded to the server.

[0464] Step 11:

[0465] The server then sends the received additional information to the generation AI for reanalysis. The additional information from the user and the initial analysis data are used as input data. The generation AI then analyzes and processes the data again to generate the final description. For example, it generates the description "Main Stage A at the music festival is very crowded, with many people gathered."

[0466] The output is the final description.

[0467] Step 12:

[0468] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary. The input data is the final description and the emotion analysis data.

[0469] The output is a final, adjusted description.

[0470] Step 13:

[0471] The server displays the final description in the application's UI for other users to access, for example, as an in-app feed or notification. The input data is the final, adjusted description.

[0472] Users can view the final description provided, see the original post, and provide additional comments and feedback.

[0473] The output is the final information that can be viewed by other users.

[0474] (Application example 2)

[0475] 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."

[0476] In brick-and-mortar stores, it is currently difficult to grasp the inconveniences and satisfaction levels of users in real time. In particular, there is a need to properly analyze users' emotions and provide information and improve services accordingly. Therefore, in order to improve the user experience in brick-and-mortar stores, a system is needed that analyzes users' emotions in real time and provides this information, along with user feedback, to other users and staff.

[0477] The specific processing by the specific 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 an input means through which a user posts text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means in the server for analyzing the text data and image data and aggregating information, a generation means for generating an explanatory text from the information aggregated by the generation means, and an emotion analysis means for analyzing the user's emotion data and adjusting the tone of the explanatory text. This makes it possible to provide information that appropriately reflects the user's emotions and to provide real-time feedback to other users and staff.

[0478] "User" means an individual or end user who posts information using the System.

[0479] "Text" refers to character string information that is input by the user using an input means.

[0480] "Image" refers to still image data posted by a user using an input means.

[0481] "Input means" refers to a device, such as a smartphone or tablet, that allows a user to input text and images into the system.

[0482] "Communication means" refers to an internet connection or wireless communication technology for transmitting text and image data entered by the input means to a server.

[0483] A "server" is a computer system on a network that receives data from users, analyzes it, and aggregates the information.

[0484] "Text data" refers to text information posted by users that is held in digital format.

[0485] "Image data" refers to image information posted by users that is stored in digital format.

[0486] "Generation means" refers to the algorithms or software that analyzes text and image data, aggregates information, and generates descriptions on the server.

[0487] "Emotion analysis means" is a technology for analyzing the user's emotional data and adjusting the tone of the generated explanation.

[0488] The "provision means" is a function within the system for displaying the generated explanation to other users.

[0489] The "question generation means" is a technique for generating a question for the user to fill in the missing information, adjusting the tone of the question, and sending it to the user.

[0490] The "re-analysis means" is an algorithm or software that receives additional information from the user, performs the analysis again, and generates the final summary.

[0491] That's all.

[0492] The present invention is a system that allows users to post their experiences at physical stores in text and image format, analyzes the information in real time, and provides it to other users and store staff.

[0493] This system includes the following components: A user uses a mobile device, such as a smartphone or tablet, as input means for posting text and images. The text and image data entered through these input means are sent to a server via communication means, which utilizes an internet connection or wireless communication technology.

[0494] The server includes a generator for analyzing the received text and image data, including software libraries such as Hugging Face Transformers and OpenCV. The generator analyzes the submitted data, extracts important keywords and phrases, and generates a description.

[0495] Furthermore, the server includes a sentiment analysis module that analyzes users' emotional data. This sentiment analysis module extracts emotions from users' posts and adjusts the tone of the generated descriptions. For sentiment analysis, a natural language processing library such as TextBlob is used.

[0496] The server also includes a question generator that generates questions for the user to fill in the missing information, and sends the questions to the user with the tone adjusted by the sentiment analyzer, providing detailed feedback on the user's experience.

[0497] If additional information is available, the server will analyze it using a re-analysis method to generate the final description, using the same algorithms and software as the initial generation method.

[0498] As a specific example, if a user posts the text "I came to store B. The product layout is confusing," along with photos of products in the store, the system will process the following:

[0499] Users post text and images using their smartphones.

[0500] Data is sent from the terminal to the server.

[0501] The server analyzes the text and images and extracts important keywords.

[0502] A sentiment analysis means determines the user's sentiment and adjusts the tone of the generated description.

[0503] A question generation means generates questions to fill in the missing information and adjusts the tone of the questions based on sentiment analysis.

[0504] The user provides additional information.

[0505] A reanalysis means analyzes the additional information and generates the final description.

[0506] The final description will be displayed to other users and store staff.

[0507] The following can be provided as examples of prompt sentences:

[0508] "Currently, I'm finding the layout of the XX store difficult to understand. Could you please tell me more about it?"

[0509] In this way, the present invention allows for an improved user experience in a physical store, providing relevant feedback in real time.

[0510] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0511] Step 1:

[0512] The user inputs text and images. Using a smartphone, the user takes and inputs text such as, "I'm at store B. The product layout is confusing," along with a photo of the store. The input data is temporarily saved on the device.

[0513] Step 2:

[0514] The terminal sends the input text and image data to the server. The communication method is via the Internet or wireless communication. The input data (text and image) is sent to the server, and the server receives it.

[0515] Step 3:

[0516] The server analyzes the received data. Using Hugging Face Transformers, the generation method, important keywords and phrases are extracted from the text data. Image data is analyzed using OpenCV and associated with the text data. The input data (text and images) is analyzed, and extracted keywords and related information are generated.

[0517] Step 4:

[0518] The server generates an initial description based on the analysis results. Based on the extracted keywords, the generative AI model Hugging Face Transformers generates a description such as "The product layout at store B is difficult to understand." The input data (analyzed keywords) is processed to generate the initial description.

[0519] Step 5:

[0520] The server analyzes the user's emotions. Using TextBlob, a sentiment analysis tool, emotions are extracted from the posted text data and the negative emotions contained in "difficult to understand" are recognized. The analyzed text data is input and emotional data is output.

[0521] Step 6:

[0522] The server adjusts the tone of the description based on the emotion data. The tone of the description generated using the emotion analysis results is adjusted, changing the description "The product layout at store B is difficult to understand" to a "calmer tone." The description is adjusted based on the emotion data.

[0523] Step 7:

[0524] The server generates a question to fill in the missing information. The question generation means generates a question such as "Which shelf specifically is difficult to find?", and then generates an adjusted question based on the emotion data such as "You seem tired, but could you tell me which shelf specifically?". The generated explanation is used as input, and the adjusted question is output.

[0525] Step 8:

[0526] The server sends the generated question to the user. The communication means sends the adjusted question to the user's terminal. The user receives the adjusted question as input.

[0527] Step 9:

[0528] The user inputs additional information. The user then inputs specific additional information, such as "This is the beverage shelf," and sends it from the terminal to the server. The user's response data is sent from the terminal and received by the server.

[0529] Step 10:

[0530] The server re-analyzes the additional information. The re-analysis means analyzes the received response and generates a final explanatory sentence. The analyzed response data is used as input to generate a final summary sentence such as "The layout of the beverage shelves at store B is difficult to understand."

[0531] Step 11:

[0532] The server provides the final description. The generated final summary is displayed to other users and store staff using a display means. The final summary is input and displayed so that users and staff can view it.

[0533] The above processing steps improve the user experience in real time in physical stores.

[0534] 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.

[0535] 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.

[0536] 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.

[0537] [Second embodiment]

[0538] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0539] 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.

[0540] 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).

[0541] 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.

[0542] 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.

[0543] 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).

[0544] 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.

[0545] 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.

[0546] 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.

[0547] 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.

[0548] 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.

[0549] 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."

[0550] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The program processing will be explained in natural language below, along with specific examples.

[0551] Program processing

[0552] 1. Collecting posts

[0553] Users use their devices to post text and images about events and disasters to a social networking-style application.

[0554] The terminal transmits the text and image data entered by the user to the server.

[0555] The server stores the received post data in a database.

[0556] 2. Data collection and analysis

[0557] The server preprocesses the received text and image data and sends it to the generation AI.

[0558] The generative AI analyzes text data to extract important keywords and phrases, and also analyzes image data and associates it with the text data.

[0559] The generative AI integrates the analysis results and generates a comprehensive explanation.

[0560] 3. Question generation

[0561] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[0562] The server sends the generated question to the user.

[0563] 4. Obtaining additional information

[0564] The user enters additional text or images in response to the received question and submits it.

[0565] The terminal transmits the user's answer to the server.

[0566] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[0567] 5. Provision of Information

[0568] The generation AI generates the final complete description.

[0569] The server makes this description accessible to other users.

[0570] Users can view the server-provided description and, if desired, view the original post.

[0571] Specific examples

[0572] 1. Collecting posts

[0573] User: Posts to the application the text "I'm at a big music festival today. Stage A is especially crowded!" along with an image showing how crowded the stage is.

[0574] Terminal: Sends posted text and images to the server.

[0575] Server: Stores the submission in a database and sends the text and images for analysis.

[0576] 2. Data collection and analysis

[0577] Generative AI: Extracts keywords from text such as "big music festival," "stage A," and "crowded," and recognizes crowded situations from images.

[0578] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[0579] 3. Question generation

[0580] Generative AI: Determines that more specific information is lacking and generates questions such as "What is the name of the main artist?"

[0581] Server: Sends the question to the user.

[0582] 4. Obtaining additional information

[0583] User: Enters answer "The main artist is Band X" and submits.

[0584] Terminal: Sends the answer to the server.

[0585] Server: Sends additional information to the generating AI for reanalysis.

[0586] 5. Provision of Information

[0587] Generative AI: Generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[0588] Server: Provides the final description for other users to see.

[0589] Users: can view the provided description and, if desired, the original post.

[0590] In this way, the system can efficiently provide users with the real-time, accurate information they desire.

[0591] The processing flow will be explained below.

[0592] Step 1:

[0593] Users use their own devices to input text and images into a social networking-style application and post.

[0594] Step 2:

[0595] The terminal transmits the posted text and image data to the server.

[0596] Step 3:

[0597] The server stores the received post data in a database.

[0598] Step 4:

[0599] The server preprocesses the stored text and image data and sends it to the generation AI.

[0600] Step 5:

[0601] The generative AI analyzes the received text data and extracts important keywords and phrases.

[0602] Step 6:

[0603] The generative AI analyzes image data and associates it with text data (e.g., "A large crowd is gathering").

[0604] Step 7:

[0605] The generative AI integrates the analysis results and generates an initial description.

[0606] Step 8:

[0607] The generation AI determines whether there are any deficiencies in the generated description.

[0608] Step 9:

[0609] Generative AI generates questions to fill in missing information (e.g., "Please tell me specific location and stage information").

[0610] Step 10:

[0611] The server sends the generated question to the original posting user.

[0612] Step 11:

[0613] The user enters additional information (text or images) in response to the question and submits the answer.

[0614] Step 12:

[0615] The terminal transmits the user's response data to the server.

[0616] Step 13:

[0617] The server then sends the additional information back to the generation AI for reanalysis.

[0618] Step 14:

[0619] The generation AI generates the final description based on the additional information.

[0620] Step 15:

[0621] The server displays the final description in the application's UI for other users to access.

[0622] Step 16:

[0623] The user sees the final description provided by the server and, if desired, the original post.

[0624] Example 1

[0625] 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."

[0626] Existing SNS-style information gathering and provision systems have difficulty effectively analyzing text and image data posted by users and providing appropriate information to other users. In particular, they lack the ability to perform detailed analysis of posted content, supplement missing information, or incorporate additional information, making it difficult to provide accurate information in real time.

[0627] 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.

[0628] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for preprocessing and analyzing the text data and image data in the server, a generation means for generating an explanatory text from the information analyzed by the generation means, a provision means for providing the explanatory text to other users, a reanalysis means for receiving additional information from users and reanalyzing it to generate a final summary, and a storage means for saving the text and image data input by users in a database. This makes it possible to effectively analyze the information posted by users and obtain additional information as needed, thereby providing accurate information to other users in real time.

[0629] "Input means" is an interface through which users contribute text and images to the system.

[0630] The "communication means" is a function for transmitting text and image data posted by the user via the input means to the server.

[0631] The "generation means" is a function for preprocessing and analyzing text data and image data received by the server.

[0632] The "providing means" is a function for disclosing and providing the description generated by the generating means to other users.

[0633] The "re-analysis means" is a function that receives additional information from the user and re-analyzes the data to generate the final summary.

[0634] The "storage means" is a function for storing the text and image data entered by the user in a database.

[0635] The "question generation means" is a function for generating a question for the user to supplement the missing information and sending the question to the user.

[0636] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The purpose of this system is to enable users to collect information about events and disasters in real time and provide accurate and detailed information to other users. A specific embodiment of this system is described below.

[0637] System configuration

[0638] The system includes an input means for users to post text and images, a communication means, a generation means, a provision means, a reanalysis means, and a storage means. These means are primarily implemented using servers, terminals, and generative AI models (e.g., OpenAI's GPT-4).

[0639] Hardware and software used

[0640] User device: A device such as a smartphone, tablet, or PC.

[0641] Server: High-performance cloud server (e.g. AWS, Google Cloud Platform).

[0642] Generative AI models: Models that perform advanced natural language processing and image analysis, such as OpenAI's GPT-4.

[0643] Explanation of program processing

[0644] Collecting Posts

[0645] Users use their devices to post text and images about events and disasters to a social networking-style application.

[0646] The terminal transmits the text and image data entered by the user to the server.

[0647] The server stores the received post data in a database.

[0648] Data aggregation and analysis

[0649] The server preprocesses the received text and image data and sends it to the generative AI model, which includes string cleansing, removing unnecessary tags, and adjusting image resolution.

[0650] The generative AI model extracts important keywords and phrases from text data and also analyzes image data and associates it with the text data.

[0651] The generative AI integrates the analysis results and generates a comprehensive explanation.

[0652] question generation

[0653] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[0654] The server sends the generated question to the user.

[0655] Obtaining additional information

[0656] The user enters additional text or images in response to the received question and submits it.

[0657] The terminal transmits the user's answer to the server.

[0658] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[0659] Providing information

[0660] The generation AI generates the final complete description.

[0661] The server makes this description accessible to other users.

[0662] Users can view the server-provided description and, if desired, view the original post.

[0663] Specific examples

[0664] 1. A user uses their smartphone to post the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing how crowded the stage is.

[0665] 2. The device sends the posted text and images to the server.

[0666] 3. The server stores the post in a database and sends the text and images for analysis.

[0667] 4. The generative AI model extracts keywords from the text, such as "big music festival," "stage A," and "crowded," and recognizes the crowded situation from the image.

[0668] 5. The AI ​​generates the initial description: "Stage A at the music festival is currently very crowded."

[0669] 6. The generative AI determines that more specific information is lacking and generates questions such as, "What is the name of the main artist?"

[0670] 7. The server sends the question to the user.

[0671] 8. The user answers, "The main artist is Band X," and submits.

[0672] 9. The device sends the response to the server.

[0673] 10. The server sends additional information to the generation AI for reanalysis.

[0674] 11. The AI ​​generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[0675] 12. The server provides the final description for other users to see.

[0676] 13. Users can view the description provided and, if necessary, the original post.

[0677] Prompt Sentence Examples

[0678] "I'm at a big music festival. Stage A seems particularly busy. I need more information. Can you tell me the names of the main artists and how busy the other stages are?"

[0679] In this way, the present invention analyzes information provided by users in real time, supplements it with necessary additional information in a timely manner, and enables other users to receive accurate and detailed information.

[0680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0681] Step 1:

[0682] A user uses their device to launch a social networking-style application and input text and images related to an event or disaster. For example, they can input text such as "I'm at a big music festival today. Stage A is particularly crowded and it's really tough!" along with an image showing the crowding situation on the stage. The input data is temporarily saved on the device and then sent to the server via a communication means by pressing the post button.

[0683] Step 2:

[0684] The terminal sends the text and image data entered by the user to the server. Specifically, the terminal divides the data into packets and transfers them to the server using the TCP / IP protocol. If the server confirms receipt, the terminal displays a notification of successful transmission to the user. At this stage, the input is the user's submitted data, and the output is a notification of successful transmission to the server.

[0685] Step 3:

[0686] The server saves the received text and image data in a database. Specifically, the server saves the text data as a string and the image data in binary format in storage. The saved data is placed in a queue for preprocessing, and the next process begins. The input in this step is the posted data received from the device, and the output is the data being saved to the database.

[0687] Step 4:

[0688] The server preprocesses the posted data stored in the database. Preprocessing includes removing unnecessary tags, normalizing text, adjusting image size, etc. This organizes the input data for the generative AI model. The input in this step is the posted data read from the database, and the output is the preprocessed data.

[0689] Step 5:

[0690] The server sends the preprocessed data to the generative AI model. Specifically, it uses an API to pass text data and image data to the generative AI. The generative AI model (e.g., OpenAI's GPT-4) extracts important keywords and phrases from the text data and also analyzes and associates them with the image data. The input in this step is the preprocessed data, and the output is the analysis results.

[0691] Step 6:

[0692] The generation AI integrates the analysis results and generates an initial description. Specifically, it creates a description such as "Stage A at the music festival is currently very crowded." The generated description is returned to the server and proceeds to the next step. The input in this step is the analysis data sent to the generation AI, and the output is the initial description.

[0693] Step 7:

[0694] If the generation AI determines that the description is incomplete, it generates a question to fill in the gaps. For example, it generates a question like, "What is the name of the main artist?" The generated question is returned to the server and is ready to be sent to the user. The input in this step is the initial description, and the output is the generated question.

[0695] Step 8:

[0696] The server sends the generated question to the user. Specifically, it sends the question to the user's device as a push notification or an in-app message. The input in this step is the generated question, and the output is a question notification to the user.

[0697] Step 9:

[0698] The user inputs additional text or image information in response to the received question and sends it to the server from their device. For example, they provide an answer such as "The main artist is Band X." The input in this step is the question from the server, and the output is the additional information from the user.

[0699] Step 10:

[0700] The terminal sends the additional information from the user to the server. This process is the same as in step 2, where additional text and image data are sent. The input in this step is the additional information, and the output is a notification of successful transmission to the server.

[0701] Step 11:

[0702] The server receives the additional information and sends it to the generative AI model for analysis again. The generative AI model takes the additional information into account to generate the final summary. For example, it creates a description such as "Band X is performing on Stage A at a music festival, and it's very crowded." The input in this step is the additional information, and the output is the final summary.

[0703] Step 12:

[0704] The server publishes the generated final description for other users to access. Specifically, it adds the description to a social networking application feed and updates it in real time. The input for this step is the final summary, and the output is the published description.

[0705] Step 13:

[0706] The user views the final description provided by the server and, if necessary, checks the original post. This allows the user to obtain accurate information in real time. The input in this step is the description from the server, and the output is the user's viewing result.

[0707] This is the specific flow of processing in the program for this system. At each step, the input data is processed appropriately, and ultimately a mechanism is established to provide the user with accurate and detailed information.

[0708] (Application example 1)

[0709] 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."

[0710] In today's world, there is a need to quickly and accurately obtain and share real-time information about events, disasters, and other events. However, conventional systems often take time to properly analyze and disseminate information posted by users, which impairs real-time reporting. Furthermore, inaccurate reports due to incomplete information can become a problem. The present invention aims to solve these problems and provide a system that provides accurate information in real time.

[0711] 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.

[0712] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data and aggregating information in the server, a generation means for generating an explanatory text as a real-time breaking news report from the information aggregated by the generation means, a provision means for providing the explanatory text to other users, and a notification means for sending a push notification to the user based on the explanatory text. This makes it possible to quickly analyze information posted by users and accurately provide it to other users in real time.

[0713] "Input means" refers to a device or interface through which a user can post text and images.

[0714] "Communication means" refers to network communication technologies and protocols for transmitting text and image data input by the input means to a server.

[0715] "Generation means" refers to algorithms or software that have the function of analyzing the text data and image data received by the server and aggregating the information.

[0716] "Explanation generation means" refers to algorithms or software for generating real-time news from aggregated information.

[0717] "Providing means" refers to an interface or service for providing the generated description to other users.

[0718] "Notification means" refers to the technology or method for sending a push notification to a user based on the generated description.

[0719] "Question generation means" refers to an algorithm or software that generates questions to fill in missing information and sends them to the user.

[0720] "Reanalysis means" refers to algorithms or software that have the ability to receive additional information from the user and reanalyze the final summary and breaking news content based on that information.

[0721] In order to implement the present invention, the following system configuration and program processing will be described.

[0722] System Configuration

[0723] This invention is a social networking service-style information collection and provision system where users post text and images. The system mainly consists of the following components:

[0724] Input means: A smartphone or smart glasses with an interface that allows the user to post text and images.

[0725] Communication means: Technology (Wi-Fi, 4G / 5G, etc.) that transmits text and image data entered by the input means to a server.

[0726] Server: The central component that receives and analyzes data. Specific hardware used is a cloud server such as Amazon Web Services (AWS).

[0727] Generation method: Software that analyzes received data and generates information. For AI-related analysis, services such as Amazon Comprehend and Amazon Rekognition are used.

[0728] Description generator: An AI model (e.g., OpenAI GPT-3) for generating descriptions from aggregated information.

[0729] Delivery medium: A web interface or application that delivers the generated descriptions to other users.

[0730] Notification method: Technology that sends push notifications based on the description (e.g., Amazon SNS).

[0731] Program processing

[0732] The processing of this system is carried out in the following sequence:

[0733] 1. Collection of User Submissions

[0734] Users post text and images related to events and disasters using their smartphones or smart glasses.

[0735] When a post is made, the input means transmits the data to the server using the communication means.

[0736] 2. Data Preprocessing and Analysis

[0737] The server receives the data using AWS Lambda and stores it in Amazon DynamoDB.

[0738] The stored data is then uploaded to AWS S3 for text and image analysis using Amazon Comprehend and Amazon Rekognition.

[0739] 3. Generating Descriptions

[0740] Based on the received data and analysis results, a generative AI model using OpenAI GPT-3 generates explanatory text as real-time breaking news.

[0741] 4. Question generation

[0742] If the description contains missing information, the generative AI model generates a question requesting additional information, and the server sends the question to the user.

[0743] 5. Collection of additional information

[0744] The user enters additional information in response to the question, which is then sent back to the server.

[0745] The reanalysis means receives additional information and generates the final narrative and flash content.

[0746] 6. Provision of Information

[0747] The server provides the generated information to other users via AWS CloudFront and sends push notifications using notification methods.

[0748] Specific examples

[0749] Here's an example of how this system can be used in practice:

[0750] 1. A user posts about an event: The user posts to the application the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing the crowds at the stage.

[0751] 2. Analysis on the server: The server analyzes keywords such as "big music festival," "stage A," and "crowded" using Amazon Comprehend, and recognizes the level of congestion from the image using Amazon Rekognition.

[0752] 3. Automatic question generation for missing information: The generative AI model requires the name of the main artist as supplementary information, so it generates the question, "What is the name of the main artist?"

[0753] 4. Receive additional information from the user: The user responds, "The main artist is Band X," and sends this to the server.

[0754] 5. Final information provision: The final description is generated: "Band X will be performing on Stage A at the music festival, and it is very crowded," and is notified to other users.

[0755] Examples of prompts to input to a generative AI model:

[0756] There is a post that says "Stage A at a huge music festival is very crowded." Extract keywords from the post's details and images, and generate specific explanations and questions about the missing information.

[0757] Post content:

[0758] Text: I'm at a big music festival today. Stage A is especially crowded and it's tough!

[0759] Image: (Image data URL)

[0760] Generated keywords:

[0761] Big music festival

[0762] Stage A

[0763] congestion

[0764] Questions to generate:

[0765] What is the name of the main artist?

[0766] This system makes it possible to efficiently collect and quickly distribute accurate information in real time.

[0767] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0768] Step 1:

[0769] Collection of User Submissions

[0770] Input: The user uses a smartphone or smart glasses to input text and images related to the event or disaster.

[0771] Specific operation: Users post information about events and disaster situations to the application using text and images. For example, they might post something like, "I'm at a big music festival today. Stage A is especially crowded and it's really tough!"

[0772] Output: The entered text and image data is sent to the server via the application.

[0773] Step 2:

[0774] Data Preprocessing

[0775] Input: Text and image data submitted by the user.

[0776] How it works: The device receives text and image data and sends it to an AWS Lambda function via a RESTful API, where the received data is formatted and stored in Amazon DynamoDB, and the image data is uploaded to Amazon S3.

[0777] Output: Formatted text data and saved image data are sent to the next analysis step.

[0778] Step 3:

[0779] Data analysis

[0780] Input: Formatted text data and stored image data.

[0781] How it works: The server uses Amazon Comprehend to analyze the text data and extract important keywords. At the same time, it uses AWS Rekognition to analyze the image data and identify objects and situations within the image. For example, keywords such as "big music festival," "stage A," and "crowded" are extracted.

[0782] Output: The extracted keywords and analysis information are sent to the generative AI model.

[0783] Step 4:

[0784] Generating Descriptions

[0785] Input: Extracted keywords and analysis information.

[0786] How it works: The server uses OpenAI GPT-3 to generate real-time news descriptions based on the results of text and image analysis. For example, it might generate a description such as, "Stage A at the music festival is currently very crowded."

[0787] Output: The generated description is saved in the server's data store.

[0788] Step 5:

[0789] Missing information question generation

[0790] Input: The generated description.

[0791] How it works: Based on the description, the generative AI model identifies missing information and generates questions accordingly, such as "What is the name of the main artist?"

[0792] Output: The generated questions are stored on the server and sent to the user.

[0793] Step 6:

[0794] Collecting additional information

[0795] Input: The question sent by the server.

[0796] Specific operation: The user inputs additional information (text or image) in response to the received question, which is then retransmitted to the server via the terminal. For example, an answer such as "The main artist is Band X" is sent.

[0797] Output: Additional information is saved on the server, ready for reanalysis.

[0798] Step 7:

[0799] Reanalysis and generation of final description

[0800] Input: Additional information (text or image).

[0801] How it works: The server uses the generative AI model again to generate a final description based on the additional information, such as "Band X is performing on Stage A at the music festival, and it's very crowded."

[0802] Output: The final description is saved on the server and sent to the next serving step.

[0803] Step 8:

[0804] Information and Notification

[0805] Input: Final description.

[0806] Specific operation: The server publishes the generated description through a means of provision so that other users can access it. In addition, the user is notified as a breaking news item via the push notification function using AWS SNS.

[0807] Output: The user sees the description provided as real-time news and receives a push notification.

[0808] Through the above steps, information posted by users can be quickly analyzed and accurately provided to other users in real time.

[0809] 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.

[0810] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[0811] Program processing

[0812] 1. Collecting posts

[0813] Users can use their devices to input and post text and images into a social networking-style application.

[0814] The terminal transmits the posted text and image data to the server.

[0815] The server stores the received post data in a database.

[0816] 2. Data collection and analysis

[0817] The server preprocesses the text data and image data and sends them to the generation AI.

[0818] Generative AI analyzes text data to extract important keywords and phrases.

[0819] The generative AI also analyzes image data and associates it with text data.

[0820] The generative AI integrates the analysis results and generates an initial description.

[0821] 3. Emotional Recognition

[0822] The emotion engine analyzes user emotions from posted text and images.

[0823] The generative AI adjusts the tone of the generated description taking into account the user's emotions (e.g., a bright tone for positive emotions and a calm tone for negative emotions).

[0824] 4. Question generation and submission

[0825] If there are any gaps in the generated explanation, the generation AI will generate questions to fill in the gaps.

[0826] The emotion engine adjusts the tone and content of questions based on the user's emotions.

[0827] The server sends the generated question to the original posting user.

[0828] 5. Obtaining additional information

[0829] The user enters additional text or images in response to the received question and submits it.

[0830] The terminal transmits the user's answer to the server.

[0831] 6. Reanalysis and final summary generation

[0832] The server sends the additional information back to the generation AI for reanalysis.

[0833] The generation AI generates the final description based on the additional information.

[0834] The emotion engine makes final adjustments by checking whether the tone of the final description matches the user's emotions.

[0835] 7. Provision of Information

[0836] The server displays the final description in the application's UI for other users to access.

[0837] Users will see the final description provided and can also view the original post if desired.

[0838] Specific examples

[0839] 1. Collecting posts

[0840] User: Posts to the application the text "I'm at a music festival right now. Stage A is very crowded and I'm feeling a bit exhausted." along with a photo of the crowded stage.

[0841] Terminal: Sends posted text and images to the server.

[0842] Server: Stores the submission in a database and sends the text and images for analysis.

[0843] 2. Data collection and analysis

[0844] Generative AI: Extracts keywords from the text, such as "music festival," "Stage A," "very crowded," and "tired."

[0845] Generative AI: Recognizes congestion status from images.

[0846] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[0847] 3. Emotional Recognition

[0848] Emotion engine: Recognizes the negative emotion of "tired" from the user's text and adjusts the description to a calmer tone.

[0849] 4. Question generation and submission

[0850] Generative AI: Determines that more specific information is lacking and generates questions such as, "Please tell me the specific stage names."

[0851] Emotion Engine: Adjust the tone of your question to something like, "You seem tired, can you tell me the name of the stage?"

[0852] Server: Sends the question to the user.

[0853] 5. Obtaining additional information

[0854] User: Answers "Main Stage A" and submits.

[0855] Terminal: Sends the answer to the server.

[0856] 6. Reanalysis and final summary generation

[0857] Server: Sends additional information to the generating AI for reanalysis.

[0858] Generative AI: Generates the final description: "Main Stage A at the music festival is very crowded, with many people gathered."

[0859] Emotion Engine: Check the tone of your description and adjust it if necessary.

[0860] 7. Provision of Information

[0861] Server: Provides the final description for other users to see.

[0862] Users: can view the provided description and also see the original post.

[0863] In this way, the present invention is a system that makes it possible to provide information in real time that takes into account the user's emotions, thereby improving the user experience.

[0864] The processing flow will be explained below.

[0865] Program processing

[0866] Step 1:

[0867] A user logs into a social networking-style application on their device, then enters "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit tired," attaches an image showing the crowded stage, and hits the post button.

[0868] Step 2:

[0869] The terminal sends the text and image data posted by the user to the specified server endpoint using an HTTP POST request.

[0870] Step 3:

[0871] The server stores the received text and image data in a database, then preprocesses the text and image data and sends them to the generative AI module for analysis.

[0872] Step 4:

[0873] The generative AI extracts important keywords and phrases from the text data, specifically identifying keywords such as "music festival," "Stage A," "very crowded," and "tired."

[0874] Step 5:

[0875] Generative AI analyzes image data and associates the image content with text data. For example, it can detect situations where many people are gathered in an image and integrate that information into the text analysis results.

[0876] Step 6:

[0877] The generative AI generates an initial description based on the results of text and image analysis, such as a summary like "Stage A at a music festival is currently very crowded."

[0878] Step 7:

[0879] The emotion engine analyzes the user's text to determine their emotions. Based on the keyword "tired," it recognizes the user's emotion as negative and adjusts the description to a calmer tone.

[0880] Step 8:

[0881] The generation AI checks whether the generated description is missing anything. If so, it generates a follow-up question, and the emotion engine adjusts the tone and content of the question. For example, it creates a question like, "You seem tired. Could you tell me the name of the specific stage?"

[0882] Step 9:

[0883] The server sends the generated question to the user, notifying them in a form that is easy for the user to understand and prompting them to provide additional information.

[0884] Step 10:

[0885] The user responds to the received question message with "Main Stage A" and presses the send button again.

[0886] Step 11:

[0887] The terminal transmits the user's answer to the server.

[0888] Step 12:

[0889] The server stores the additional information sent by the user in a database and performs re-analysis on the generated AI.

[0890] Step 13:

[0891] The generation AI reanalyzes the data based on additional information from the user and generates the final description: "Main Stage A of the music festival is very crowded, with many people gathered."

[0892] Step 14:

[0893] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary.

[0894] Step 15:

[0895] The server makes this final, adjusted description available to other users for access, for example, by displaying it on the application's home screen or on specific information pages.

[0896] Step 16:

[0897] Users can access the application on their devices to view the final description provided, and can also view the original post if desired.

[0898] Specific examples

[0899] 1. Collecting posts

[0900] User: Posts the text "I'm at a music festival right now. Stage A is very crowded and I'm a bit tired." along with an image showing the crowds.

[0901] Terminal: Sends the post to the server.

[0902] Server: Receives the posted content, stores it in a database, and sends the data to the generation AI module.

[0903] 2. Data collection and analysis

[0904] Generative AI: Extracts important keywords and recognizes congestion situations from images.

[0905] Generative AI: Generates the initial description, "Stage A at the music festival is very crowded."

[0906] 3. Emotional awareness and regulation

[0907] Sentiment engine: Recognizes negative sentiment from text and adjusts descriptions accordingly.

[0908] 4. Question generation and additional information acquisition

[0909] Generative AI: Generates questions and an emotional engine adjusts the tone.

[0910] Server: Sends the question to the user.

[0911] User: "Main Stage A"

[0912] Terminal: Sends additional information to the server.

[0913] Server: Resends additional information to the generating AI.

[0914] 5. Final summary generation and serving

[0915] Generative AI: Generates the final description, "Main Stage A at the music festival is very crowded, with many people gathered."

[0916] Emotion Engine: Making final adjustments.

[0917] Server: Provides the final description to other users.

[0918] User: View the final description provided.

[0919] In this way, the present invention realizes a system that provides real-time information that takes into account the user's emotions.

[0920] Example 2

[0921] 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."

[0922] In modern social networking systems, when users post information in real time, the information may not be properly conveyed to other users. Furthermore, the posted information contains emotions, but if these emotions are not taken into consideration, the recipient may misunderstand the information. Furthermore, if information is missing, questions to fill in the gaps are not automatically generated, which hinders the user's experience. Therefore, there is a need for a system that recognizes users' emotions, provides appropriately tailored information to other users, and automatically fills in missing information.

[0923] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0924] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data in the server and aggregating information, a generation means for generating an explanatory text from the aggregated information, an emotion recognition means for adjusting the explanatory text based on the user's emotion, and a provision means for providing the explanatory text to other users, thereby enabling information to be provided in real time taking into account the user's emotion.

[0925] "Input means" refers to a device or interface through which a user submits text and images.

[0926] "Communication means" refers to a network device or protocol for transmitting input text and image data to a server.

[0927] "Generation means" refers to a device or algorithm that analyzes text data and image data on a server and aggregates the information.

[0928] "Emotion recognition means" refers to a device or software for adjusting the generated caption based on the user's emotions.

[0929] "Providing means" refers to a system or interface for providing the generated explanation to other users.

[0930] The term "question generation means" refers to a device or program for generating a question for a user to fill in missing information and sending it to the user.

[0931] "Reanalysis means" refers to a system or process that receives additional information from the user and performs another analysis to generate the final summary.

[0932] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[0933] System configuration

[0934] Input method: Users log in to a social networking-style application using their own devices, such as their smartphones or PCs, and enter text and images to post. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage.

[0935] Communication method: The terminal sends the posted text and image data to the server. Specifically, it makes a POST request to the endpoint using the HTTPS protocol.

[0936] Generation method: The server stores the received text and image data in a database (e.g., MySQL or MongoDB). Next, it performs preprocessing such as tokenizing the text data, removing noise, and resizing and formatting the image data. After preprocessing is complete, the data is sent to the generation AI, which analyzes it using, for example, OpenAI's ChatGPT to extract important keywords and phrases. It also analyzes the image data and associates it with the text data. An initial description is generated based on the analysis results. For example, it generates a description such as, "Stage A at the music festival is currently very crowded."

[0937] Emotion recognition means: An emotion engine (for example, Microsoft's EmoNet) is used to analyze the user's emotions from the posted text and images. For example, it recognizes the negative emotion of "tired." The generation AI adjusts the tone of the generated description taking the user's emotions into account. For example, the description may be calmer, such as "Stage A at the music festival is currently very crowded, and I am feeling a bit tired."

[0938] Question generation means: The generation AI generates questions for the user to fill in missing information. For example, it generates a question such as, "Please tell me the specific stage name." The emotion engine adjusts the tone and content of the question. For example, it may change the tone to something like, "You seem tired, but could you please tell me the specific stage name?" The server sends the generated question to the original poster. Specifically, it sends the question to the user's device as a push notification or in-app message.

[0939] Reanalysis method: The user inputs and sends additional text or images in response to the received question. For example, the user sends the text "This is Main Stage A." The device sends this additional information to the server, which then sends it to the generation AI for reanalysis. The generation AI generates the final description based on the additional information. For example, it generates the final description "Main Stage A at the music festival is very crowded, with many people gathered." The emotion engine checks the tone of the description and makes final adjustments if necessary.

[0940] Delivery method: The server displays the final description in the application's UI for other users to access. Users can view the delivered description, see the original post, and post additional comments and feedback.

[0941] Prompt Sentence Examples

[0942] "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit exhausted. Based on this information, what emotions can you analyze and generate a description for?"

[0943] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0944] Step 1:

[0945] Users log in to a social networking-style application using a device such as a smartphone or PC, and post by entering text and images. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage. This post becomes the input.

[0946] The output is the user's posted data (text and images).

[0947] Step 2:

[0948] The terminal sends the user's posted data to the server. The HTTPS protocol is used to send the data, and the request format is POST. The data sent includes text, images, and the user ID. This is the input data.

[0949] The output is the submitted data that is forwarded to the server.

[0950] Step 3:

[0951] The server stores the received submission data in a database (e.g., MySQL or MongoDB), which makes the text and images persistent. This storage process is part of the data processing. It also performs preprocessing such as tokenizing and denoising the text data, and resizing and formatting the image data.

[0952] The output is preprocessed text and image data.

[0953] Step 4:

[0954] The server sends the preprocessed text and image data to the generative AI model. As a concrete example, we will use a general generative AI as the generative AI model. The preprocessed data (tokenized text and resized images) are input. The generative AI analyzes this data and extracts important keywords and phrases. It also associates them with the text data through image analysis. Data analysis and processing are then performed.

[0955] The output is the analysis results and an initial description (e.g., "Stage A at the music festival is currently very crowded.").

[0956] Step 5:

[0957] The emotion engine analyzes the user's emotions from the posted text and images. Specifically, it uses a common emotion analysis system to obtain emotional information from the text and images. The input data used is the user's posted text, "I'm currently at a music festival. Stage A is very crowded and I'm a bit tired." and the posted image. The emotion engine recognizes the negative emotion of "tired."

[0958] The output is the analyzed emotion information.

[0959] Step 6:

[0960] The generative AI adjusts the tone of the description based on the results of the emotion analysis. It uses the initial description generated earlier as input. To respond to the negative emotion of "tired," it adjusts the description to something like "Stage A at the music festival is currently very crowded, and I am feeling a bit tired." This adjustment process is part of data processing and data calculation.

[0961] The output is a sentiment-adjusted description.

[0962] Step 7:

[0963] If there are gaps in the initial description, the generative AI generates questions to fill in those gaps. The initial description and analyzed emotional information are used as input data. As a specific example, it generates questions such as "Please tell me the specific stage name."

[0964] The emotion engine adjusts the tone and content of the question, for example, "You seem tired, can you tell me the name of the stage?"

[0965] The output is the generated question.

[0966] Step 8:

[0967] The server sends the generated question to the original poster. Specifically, the question is sent to the user's device as a push notification or an in-app message. The input data is the generated question text.

[0968] The output is the question sent to the user terminal.

[0969] Step 9:

[0970] The user inputs additional text or images in response to the received question and submits it. For example, the user might reply, "This is Main Stage A." This response becomes new input data.

[0971] The output is additional information for the user.

[0972] Step 10:

[0973] The terminal sends the user's additional information to the server. Specifically, the terminal sends the user's additional text and images as a POST request.

[0974] The output is additional information that is forwarded to the server.

[0975] Step 11:

[0976] The server then sends the received additional information to the generation AI for reanalysis. The additional information from the user and the initial analysis data are used as input data. The generation AI then analyzes and processes the data again to generate the final description. For example, it generates the description "Main Stage A at the music festival is very crowded, with many people gathered."

[0977] The output is the final description.

[0978] Step 12:

[0979] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary. The input data is the final description and the emotion analysis data.

[0980] The output is a final, adjusted description.

[0981] Step 13:

[0982] The server displays the final description in the application's UI for other users to access, for example, as an in-app feed or notification. The input data is the final, adjusted description.

[0983] Users can view the final description provided, see the original post, and provide additional comments and feedback.

[0984] The output is the final information that can be viewed by other users.

[0985] (Application example 2)

[0986] 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."

[0987] In brick-and-mortar stores, it is currently difficult to grasp the inconveniences and satisfaction levels of users in real time. In particular, there is a need to properly analyze users' emotions and provide information and improve services accordingly. Therefore, in order to improve the user experience in brick-and-mortar stores, a system is needed that analyzes users' emotions in real time and provides this information, along with user feedback, to other users and staff.

[0988] The specific processing by the specific 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 an input means through which a user posts text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means in the server for analyzing the text data and image data and aggregating information, a generation means for generating an explanatory text from the information aggregated by the generation means, and an emotion analysis means for analyzing the user's emotion data and adjusting the tone of the explanatory text. This makes it possible to provide information that appropriately reflects the user's emotions and to provide real-time feedback to other users and staff.

[0989] "User" means an individual or end user who posts information using the System.

[0990] "Text" refers to character string information that is input by the user using an input means.

[0991] "Image" refers to still image data posted by a user using an input means.

[0992] "Input means" refers to a device, such as a smartphone or tablet, that allows a user to input text and images into the system.

[0993] "Communication means" refers to an internet connection or wireless communication technology for transmitting text and image data entered by the input means to a server.

[0994] A "server" is a computer system on a network that receives data from users, analyzes it, and aggregates the information.

[0995] "Text data" refers to text information posted by users that is held in digital format.

[0996] "Image data" refers to image information posted by users that is stored in digital format.

[0997] "Generation means" refers to the algorithms or software that analyzes text and image data, aggregates information, and generates descriptions on the server.

[0998] "Emotion analysis means" is a technology for analyzing the user's emotional data and adjusting the tone of the generated explanation.

[0999] The "provision means" is a function within the system for displaying the generated explanation to other users.

[1000] The "question generation means" is a technique for generating a question for the user to fill in the missing information, adjusting the tone of the question, and sending it to the user.

[1001] The "re-analysis means" is an algorithm or software that receives additional information from the user, performs the analysis again, and generates the final summary.

[1002] That's all.

[1003] The present invention is a system that allows users to post their experiences at physical stores in text and image format, analyzes the information in real time, and provides it to other users and store staff.

[1004] This system includes the following components: A user uses a mobile device, such as a smartphone or tablet, as input means for posting text and images. The text and image data entered through these input means are sent to a server via communication means, which utilizes an internet connection or wireless communication technology.

[1005] The server includes a generator for analyzing the received text and image data, including software libraries such as Hugging Face Transformers and OpenCV. The generator analyzes the submitted data, extracts important keywords and phrases, and generates a description.

[1006] Furthermore, the server includes a sentiment analysis module that analyzes users' emotional data. This sentiment analysis module extracts emotions from users' posts and adjusts the tone of the generated descriptions. For sentiment analysis, a natural language processing library such as TextBlob is used.

[1007] The server also includes a question generator that generates questions for the user to fill in the missing information, and sends the questions to the user with the tone adjusted by the sentiment analyzer, providing detailed feedback on the user's experience.

[1008] If additional information is available, the server will analyze it using a re-analysis method to generate the final description, using the same algorithms and software as the initial generation method.

[1009] As a specific example, if a user posts the text "I came to store B. The product layout is confusing," along with photos of products in the store, the system will process the following:

[1010] Users post text and images using their smartphones.

[1011] Data is sent from the terminal to the server.

[1012] The server analyzes the text and images and extracts important keywords.

[1013] A sentiment analysis means determines the user's sentiment and adjusts the tone of the generated description.

[1014] A question generation means generates questions to fill in the missing information and adjusts the tone of the questions based on sentiment analysis.

[1015] The user provides additional information.

[1016] A reanalysis means analyzes the additional information and generates the final description.

[1017] The final description will be displayed to other users and store staff.

[1018] The following can be provided as examples of prompt sentences:

[1019] "Currently, I'm finding the layout of the XX store difficult to understand. Could you please tell me more about it?"

[1020] In this way, the present invention allows for an improved user experience in a physical store, providing relevant feedback in real time.

[1021] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1022] Step 1:

[1023] The user inputs text and images. Using a smartphone, the user takes and inputs text such as, "I'm at store B. The product layout is confusing," along with a photo of the store. The input data is temporarily saved on the device.

[1024] Step 2:

[1025] The terminal sends the input text and image data to the server. The communication method is via the Internet or wireless communication. The input data (text and image) is sent to the server, and the server receives it.

[1026] Step 3:

[1027] The server analyzes the received data. Using Hugging Face Transformers, the generation method, important keywords and phrases are extracted from the text data. Image data is analyzed using OpenCV and associated with the text data. The input data (text and images) is analyzed, and extracted keywords and related information are generated.

[1028] Step 4:

[1029] The server generates an initial description based on the analysis results. Based on the extracted keywords, the generative AI model Hugging Face Transformers generates a description such as "The product layout at store B is difficult to understand." The input data (analyzed keywords) is processed to generate the initial description.

[1030] Step 5:

[1031] The server analyzes the user's emotions. Using TextBlob, a sentiment analysis tool, emotions are extracted from the posted text data and the negative emotions contained in "difficult to understand" are recognized. The analyzed text data is input and emotional data is output.

[1032] Step 6:

[1033] The server adjusts the tone of the description based on the emotion data. The tone of the description generated using the emotion analysis results is adjusted, changing the description "The product layout at store B is difficult to understand" to a "calmer tone." The description is adjusted based on the emotion data.

[1034] Step 7:

[1035] The server generates a question to fill in the missing information. The question generation means generates a question such as "Which shelf specifically is difficult to find?", and then generates an adjusted question based on the emotion data such as "You seem tired, but could you tell me which shelf specifically?". The generated explanation is used as input, and the adjusted question is output.

[1036] Step 8:

[1037] The server sends the generated question to the user. The communication means sends the adjusted question to the user's terminal. The user receives the adjusted question as input.

[1038] Step 9:

[1039] The user inputs additional information. The user then inputs specific additional information, such as "This is the beverage shelf," and sends it from the terminal to the server. The user's response data is sent from the terminal and received by the server.

[1040] Step 10:

[1041] The server re-analyzes the additional information. The re-analysis means analyzes the received response and generates a final explanatory sentence. The analyzed response data is used as input to generate a final summary sentence such as "The layout of the beverage shelves at store B is difficult to understand."

[1042] Step 11:

[1043] The server provides the final description. The generated final summary is displayed to other users and store staff using a display means. The final summary is input and displayed so that users and staff can view it.

[1044] The above processing steps improve the user experience in real time in physical stores.

[1045] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1046] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

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

[1048] [Third embodiment]

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

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

[1051] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1052] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

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

[1054] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1055] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1056] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1057] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1058] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

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

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

[1061] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The program processing will be explained in natural language below, along with specific examples.

[1062] Program processing

[1063] 1. Collecting posts

[1064] Users use their devices to post text and images about events and disasters to a social networking-style application.

[1065] The terminal transmits the text and image data entered by the user to the server.

[1066] The server stores the received post data in a database.

[1067] 2. Data collection and analysis

[1068] The server preprocesses the received text and image data and sends it to the generation AI.

[1069] The generative AI analyzes text data to extract important keywords and phrases, and also analyzes image data and associates it with the text data.

[1070] The generative AI integrates the analysis results and generates a comprehensive explanation.

[1071] 3. Question generation

[1072] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[1073] The server sends the generated question to the user.

[1074] 4. Obtaining additional information

[1075] The user enters additional text or images in response to the received question and submits it.

[1076] The terminal transmits the user's answer to the server.

[1077] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[1078] 5. Provision of Information

[1079] The generation AI generates the final complete description.

[1080] The server makes this description accessible to other users.

[1081] Users can view the server-provided description and, if desired, view the original post.

[1082] Specific examples

[1083] 1. Collecting posts

[1084] User: Posts to the application the text "I'm at a big music festival today. Stage A is especially crowded!" along with an image showing how crowded the stage is.

[1085] Terminal: Sends posted text and images to the server.

[1086] Server: Stores the submission in a database and sends the text and images for analysis.

[1087] 2. Data collection and analysis

[1088] Generative AI: Extracts keywords from text such as "big music festival," "stage A," and "crowded," and recognizes crowded situations from images.

[1089] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[1090] 3. Question generation

[1091] Generative AI: Determines that more specific information is lacking and generates questions such as "What is the name of the main artist?"

[1092] Server: Sends the question to the user.

[1093] 4. Obtaining additional information

[1094] User: Enters answer "The main artist is Band X" and submits.

[1095] Terminal: Sends the answer to the server.

[1096] Server: Sends additional information to the generating AI for reanalysis.

[1097] 5. Provision of Information

[1098] Generative AI: Generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[1099] Server: Provides the final description for other users to see.

[1100] Users: can view the provided description and, if desired, the original post.

[1101] In this way, the system can efficiently provide users with the real-time, accurate information they desire.

[1102] The processing flow will be explained below.

[1103] Step 1:

[1104] Users use their own devices to input text and images into a social networking-style application and post.

[1105] Step 2:

[1106] The terminal transmits the posted text and image data to the server.

[1107] Step 3:

[1108] The server stores the received post data in a database.

[1109] Step 4:

[1110] The server preprocesses the stored text and image data and sends it to the generation AI.

[1111] Step 5:

[1112] The generative AI analyzes the received text data and extracts important keywords and phrases.

[1113] Step 6:

[1114] The generative AI analyzes image data and associates it with text data (e.g., "A large crowd is gathering").

[1115] Step 7:

[1116] The generative AI integrates the analysis results and generates an initial description.

[1117] Step 8:

[1118] The generation AI determines whether there are any deficiencies in the generated description.

[1119] Step 9:

[1120] Generative AI generates questions to fill in missing information (e.g., "Please tell me specific location and stage information").

[1121] Step 10:

[1122] The server sends the generated question to the original posting user.

[1123] Step 11:

[1124] The user enters additional information (text or images) in response to the question and submits the answer.

[1125] Step 12:

[1126] The terminal transmits the user's response data to the server.

[1127] Step 13:

[1128] The server then sends the additional information back to the generation AI for reanalysis.

[1129] Step 14:

[1130] The generation AI generates the final description based on the additional information.

[1131] Step 15:

[1132] The server displays the final description in the application's UI for other users to access.

[1133] Step 16:

[1134] The user sees the final description provided by the server and, if desired, the original post.

[1135] Example 1

[1136] 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."

[1137] Existing SNS-style information gathering and provision systems have difficulty effectively analyzing text and image data posted by users and providing appropriate information to other users. In particular, they lack the ability to perform detailed analysis of posted content, supplement missing information, or incorporate additional information, making it difficult to provide accurate information in real time.

[1138] 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.

[1139] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for preprocessing and analyzing the text data and image data in the server, a generation means for generating an explanatory text from the information analyzed by the generation means, a provision means for providing the explanatory text to other users, a reanalysis means for receiving additional information from users and reanalyzing it to generate a final summary, and a storage means for saving the text and image data input by users in a database. This makes it possible to effectively analyze the information posted by users and obtain additional information as needed, thereby providing accurate information to other users in real time.

[1140] "Input means" is an interface through which users contribute text and images to the system.

[1141] The "communication means" is a function for transmitting text and image data posted by the user via the input means to the server.

[1142] The "generation means" is a function for preprocessing and analyzing text data and image data received by the server.

[1143] The "providing means" is a function for disclosing and providing the description generated by the generating means to other users.

[1144] The "re-analysis means" is a function that receives additional information from the user and re-analyzes the data to generate the final summary.

[1145] The "storage means" is a function for storing the text and image data entered by the user in a database.

[1146] The "question generation means" is a function for generating a question for the user to supplement the missing information and sending the question to the user.

[1147] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The purpose of this system is to enable users to collect information about events and disasters in real time and provide accurate and detailed information to other users. A specific embodiment of this system is described below.

[1148] System configuration

[1149] The system includes an input means for users to post text and images, a communication means, a generation means, a provision means, a reanalysis means, and a storage means. These means are primarily implemented using servers, terminals, and generative AI models (e.g., OpenAI's GPT-4).

[1150] Hardware and software used

[1151] User device: A device such as a smartphone, tablet, or PC.

[1152] Server: High-performance cloud server (e.g. AWS, Google Cloud Platform).

[1153] Generative AI models: Models that perform advanced natural language processing and image analysis, such as OpenAI's GPT-4.

[1154] Explanation of program processing

[1155] Collecting Posts

[1156] Users use their devices to post text and images about events and disasters to a social networking-style application.

[1157] The terminal transmits the text and image data entered by the user to the server.

[1158] The server stores the received post data in a database.

[1159] Data aggregation and analysis

[1160] The server preprocesses the received text and image data and sends it to the generative AI model, which includes string cleansing, removing unnecessary tags, and adjusting image resolution.

[1161] The generative AI model extracts important keywords and phrases from text data and also analyzes image data and associates it with the text data.

[1162] The generative AI integrates the analysis results and generates a comprehensive explanation.

[1163] question generation

[1164] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[1165] The server sends the generated question to the user.

[1166] Obtaining additional information

[1167] The user enters additional text or images in response to the received question and submits it.

[1168] The terminal transmits the user's answer to the server.

[1169] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[1170] Providing information

[1171] The generation AI generates the final complete description.

[1172] The server makes this description accessible to other users.

[1173] Users can view the server-provided description and, if desired, view the original post.

[1174] Specific examples

[1175] 1. A user uses their smartphone to post the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing how crowded the stage is.

[1176] 2. The device sends the posted text and images to the server.

[1177] 3. The server stores the post in a database and sends the text and images for analysis.

[1178] 4. The generative AI model extracts keywords from the text, such as "big music festival," "stage A," and "crowded," and recognizes the crowded situation from the image.

[1179] 5. The AI ​​generates the initial description: "Stage A at the music festival is currently very crowded."

[1180] 6. The generative AI determines that more specific information is lacking and generates questions such as, "What is the name of the main artist?"

[1181] 7. The server sends the question to the user.

[1182] 8. The user answers, "The main artist is Band X," and submits.

[1183] 9. The device sends the response to the server.

[1184] 10. The server sends additional information to the generation AI for reanalysis.

[1185] 11. The AI ​​generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[1186] 12. The server provides the final description for other users to see.

[1187] 13. Users can view the description provided and, if necessary, the original post.

[1188] Prompt Sentence Examples

[1189] "I'm at a big music festival. Stage A seems particularly busy. I need more information. Can you tell me the names of the main artists and how busy the other stages are?"

[1190] In this way, the present invention analyzes information provided by users in real time, supplements it with necessary additional information in a timely manner, and enables other users to receive accurate and detailed information.

[1191] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1192] Step 1:

[1193] A user uses their device to launch a social networking-style application and input text and images related to an event or disaster. For example, they can input text such as "I'm at a big music festival today. Stage A is particularly crowded and it's really tough!" along with an image showing the crowding situation on the stage. The input data is temporarily saved on the device and then sent to the server via a communication means by pressing the post button.

[1194] Step 2:

[1195] The terminal sends the text and image data entered by the user to the server. Specifically, the terminal divides the data into packets and transfers them to the server using the TCP / IP protocol. If the server confirms receipt, the terminal displays a notification of successful transmission to the user. At this stage, the input is the user's submitted data, and the output is a notification of successful transmission to the server.

[1196] Step 3:

[1197] The server saves the received text and image data in a database. Specifically, the server saves the text data as a string and the image data in binary format in storage. The saved data is placed in a queue for preprocessing, and the next process begins. The input in this step is the posted data received from the device, and the output is the data being saved to the database.

[1198] Step 4:

[1199] The server preprocesses the posted data stored in the database. Preprocessing includes removing unnecessary tags, normalizing text, adjusting image size, etc. This organizes the input data for the generative AI model. The input in this step is the posted data read from the database, and the output is the preprocessed data.

[1200] Step 5:

[1201] The server sends the preprocessed data to the generative AI model. Specifically, it uses an API to pass text data and image data to the generative AI. The generative AI model (e.g., OpenAI's GPT-4) extracts important keywords and phrases from the text data and also analyzes and associates them with the image data. The input in this step is the preprocessed data, and the output is the analysis results.

[1202] Step 6:

[1203] The generation AI integrates the analysis results and generates an initial description. Specifically, it creates a description such as "Stage A at the music festival is currently very crowded." The generated description is returned to the server and proceeds to the next step. The input in this step is the analysis data sent to the generation AI, and the output is the initial description.

[1204] Step 7:

[1205] If the generation AI determines that the description is incomplete, it generates a question to fill in the gaps. For example, it generates a question like, "What is the name of the main artist?" The generated question is returned to the server and is ready to be sent to the user. The input in this step is the initial description, and the output is the generated question.

[1206] Step 8:

[1207] The server sends the generated question to the user. Specifically, it sends the question to the user's device as a push notification or an in-app message. The input in this step is the generated question, and the output is a question notification to the user.

[1208] Step 9:

[1209] The user inputs additional text or image information in response to the received question and sends it to the server from their device. For example, they provide an answer such as "The main artist is Band X." The input in this step is the question from the server, and the output is the additional information from the user.

[1210] Step 10:

[1211] The terminal sends the additional information from the user to the server. This process is the same as in step 2, where additional text and image data are sent. The input in this step is the additional information, and the output is a notification of successful transmission to the server.

[1212] Step 11:

[1213] The server receives the additional information and sends it to the generative AI model for analysis again. The generative AI model takes the additional information into account to generate the final summary. For example, it creates a description such as "Band X is performing on Stage A at a music festival, and it's very crowded." The input in this step is the additional information, and the output is the final summary.

[1214] Step 12:

[1215] The server publishes the generated final description for other users to access. Specifically, it adds the description to a social networking application feed and updates it in real time. The input for this step is the final summary, and the output is the published description.

[1216] Step 13:

[1217] The user views the final description provided by the server and, if necessary, checks the original post. This allows the user to obtain accurate information in real time. The input in this step is the description from the server, and the output is the user's viewing result.

[1218] This is the specific flow of processing in the program for this system. At each step, the input data is processed appropriately, and ultimately a mechanism is established to provide the user with accurate and detailed information.

[1219] (Application example 1)

[1220] 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."

[1221] In today's world, there is a need to quickly and accurately obtain and share real-time information about events, disasters, and other events. However, conventional systems often take time to properly analyze and disseminate information posted by users, which impairs real-time reporting. Furthermore, inaccurate reports due to incomplete information can become a problem. The present invention aims to solve these problems and provide a system that provides accurate information in real time.

[1222] 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.

[1223] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data and aggregating information in the server, a generation means for generating an explanatory text as a real-time breaking news report from the information aggregated by the generation means, a provision means for providing the explanatory text to other users, and a notification means for sending a push notification to the user based on the explanatory text. This makes it possible to quickly analyze information posted by users and accurately provide it to other users in real time.

[1224] "Input means" refers to a device or interface through which a user can post text and images.

[1225] "Communication means" refers to network communication technologies and protocols for transmitting text and image data input by the input means to a server.

[1226] "Generation means" refers to algorithms or software that have the function of analyzing the text data and image data received by the server and aggregating the information.

[1227] "Explanation generation means" refers to algorithms or software for generating real-time news from aggregated information.

[1228] "Providing means" refers to an interface or service for providing the generated description to other users.

[1229] "Notification means" refers to the technology or method for sending a push notification to a user based on the generated description.

[1230] "Question generation means" refers to an algorithm or software that generates questions to fill in missing information and sends them to the user.

[1231] "Reanalysis means" refers to algorithms or software that have the ability to receive additional information from the user and reanalyze the final summary and breaking news content based on that information.

[1232] In order to implement the present invention, the following system configuration and program processing will be described.

[1233] System Configuration

[1234] This invention is a social networking service-style information collection and provision system where users post text and images. The system mainly consists of the following components:

[1235] Input means: A smartphone or smart glasses with an interface that allows the user to post text and images.

[1236] Communication means: Technology (Wi-Fi, 4G / 5G, etc.) that transmits text and image data entered by the input means to a server.

[1237] Server: The central component that receives and analyzes data. Specific hardware used is a cloud server such as Amazon Web Services (AWS).

[1238] Generation method: Software that analyzes received data and generates information. For AI-related analysis, services such as Amazon Comprehend and Amazon Rekognition are used.

[1239] Description generator: An AI model (e.g., OpenAI GPT-3) for generating descriptions from aggregated information.

[1240] Delivery medium: A web interface or application that delivers the generated descriptions to other users.

[1241] Notification method: Technology that sends push notifications based on the description (e.g., Amazon SNS).

[1242] Program processing

[1243] The processing of this system is carried out in the following sequence:

[1244] 1. Collection of User Submissions

[1245] Users post text and images related to events and disasters using their smartphones or smart glasses.

[1246] When a post is made, the input means transmits the data to the server using the communication means.

[1247] 2. Data Preprocessing and Analysis

[1248] The server receives the data using AWS Lambda and stores it in Amazon DynamoDB.

[1249] The stored data is then uploaded to AWS S3 for text and image analysis using Amazon Comprehend and Amazon Rekognition.

[1250] 3. Generating Descriptions

[1251] Based on the received data and analysis results, a generative AI model using OpenAI GPT-3 generates explanatory text as real-time breaking news.

[1252] 4. Question generation

[1253] If the description contains missing information, the generative AI model generates a question requesting additional information, and the server sends the question to the user.

[1254] 5. Collection of additional information

[1255] The user enters additional information in response to the question, which is then sent back to the server.

[1256] The reanalysis means receives additional information and generates the final narrative and flash content.

[1257] 6. Provision of Information

[1258] The server provides the generated information to other users via AWS CloudFront and sends push notifications using notification methods.

[1259] Specific examples

[1260] Here's an example of how this system can be used in practice:

[1261] 1. A user posts about an event: The user posts to the application the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing the crowds at the stage.

[1262] 2. Analysis on the server: The server analyzes keywords such as "big music festival," "stage A," and "crowded" using Amazon Comprehend, and recognizes the level of congestion from the image using Amazon Rekognition.

[1263] 3. Automatic question generation for missing information: The generative AI model requires the name of the main artist as supplementary information, so it generates the question, "What is the name of the main artist?"

[1264] 4. Receive additional information from the user: The user responds, "The main artist is Band X," and sends this to the server.

[1265] 5. Final information provision: The final description is generated: "Band X will be performing on Stage A at the music festival, and it is very crowded," and is notified to other users.

[1266] Examples of prompts to input to a generative AI model:

[1267] There is a post that says "Stage A at a huge music festival is very crowded." Extract keywords from the post's details and images, and generate specific explanations and questions about the missing information.

[1268] Post content:

[1269] Text: I'm at a big music festival today. Stage A is especially crowded and it's tough!

[1270] Image: (Image data URL)

[1271] Generated keywords:

[1272] Big music festival

[1273] Stage A

[1274] congestion

[1275] Questions to generate:

[1276] What is the name of the main artist?

[1277] This system makes it possible to efficiently collect and quickly distribute accurate information in real time.

[1278] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1279] Step 1:

[1280] Collection of User Submissions

[1281] Input: The user uses a smartphone or smart glasses to input text and images related to the event or disaster.

[1282] Specific operation: Users post information about events and disaster situations to the application using text and images. For example, they might post something like, "I'm at a big music festival today. Stage A is especially crowded and it's really tough!"

[1283] Output: The entered text and image data is sent to the server via the application.

[1284] Step 2:

[1285] Data Preprocessing

[1286] Input: Text and image data submitted by the user.

[1287] How it works: The device receives text and image data and sends it to an AWS Lambda function via a RESTful API, where the received data is formatted and stored in Amazon DynamoDB, and the image data is uploaded to Amazon S3.

[1288] Output: Formatted text data and saved image data are sent to the next analysis step.

[1289] Step 3:

[1290] Data analysis

[1291] Input: Formatted text data and stored image data.

[1292] How it works: The server uses Amazon Comprehend to analyze the text data and extract important keywords. At the same time, it uses AWS Rekognition to analyze the image data and identify objects and situations within the image. For example, keywords such as "big music festival," "stage A," and "crowded" are extracted.

[1293] Output: The extracted keywords and analysis information are sent to the generative AI model.

[1294] Step 4:

[1295] Generating Descriptions

[1296] Input: Extracted keywords and analysis information.

[1297] How it works: The server uses OpenAI GPT-3 to generate real-time news descriptions based on the results of text and image analysis. For example, it might generate a description such as, "Stage A at the music festival is currently very crowded."

[1298] Output: The generated description is saved in the server's data store.

[1299] Step 5:

[1300] Missing information question generation

[1301] Input: The generated description.

[1302] How it works: Based on the description, the generative AI model identifies missing information and generates questions accordingly, such as "What is the name of the main artist?"

[1303] Output: The generated questions are stored on the server and sent to the user.

[1304] Step 6:

[1305] Collecting additional information

[1306] Input: The question sent by the server.

[1307] Specific operation: The user inputs additional information (text or image) in response to the received question, which is then retransmitted to the server via the terminal. For example, an answer such as "The main artist is Band X" is sent.

[1308] Output: Additional information is saved on the server, ready for reanalysis.

[1309] Step 7:

[1310] Reanalysis and generation of final description

[1311] Input: Additional information (text or image).

[1312] How it works: The server uses the generative AI model again to generate a final description based on the additional information, such as "Band X is performing on Stage A at the music festival, and it's very crowded."

[1313] Output: The final description is saved on the server and sent to the next serving step.

[1314] Step 8:

[1315] Information and Notification

[1316] Input: Final description.

[1317] Specific operation: The server publishes the generated description through a means of provision so that other users can access it. In addition, the user is notified as a breaking news item via the push notification function using AWS SNS.

[1318] Output: The user sees the description provided as real-time news and receives a push notification.

[1319] Through the above steps, information posted by users can be quickly analyzed and accurately provided to other users in real time.

[1320] 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.

[1321] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[1322] Program processing

[1323] 1. Collecting posts

[1324] Users can use their devices to input and post text and images into a social networking-style application.

[1325] The terminal transmits the posted text and image data to the server.

[1326] The server stores the received post data in a database.

[1327] 2. Data collection and analysis

[1328] The server preprocesses the text data and image data and sends them to the generation AI.

[1329] Generative AI analyzes text data to extract important keywords and phrases.

[1330] The generative AI also analyzes image data and associates it with text data.

[1331] The generative AI integrates the analysis results and generates an initial description.

[1332] 3. Emotional Recognition

[1333] The emotion engine analyzes user emotions from posted text and images.

[1334] The generative AI adjusts the tone of the generated description taking into account the user's emotions (e.g., a bright tone for positive emotions and a calm tone for negative emotions).

[1335] 4. Question generation and submission

[1336] If there are any gaps in the generated explanation, the generation AI will generate questions to fill in the gaps.

[1337] The emotion engine adjusts the tone and content of questions based on the user's emotions.

[1338] The server sends the generated question to the original posting user.

[1339] 5. Obtaining additional information

[1340] The user enters additional text or images in response to the received question and submits it.

[1341] The terminal transmits the user's answer to the server.

[1342] 6. Reanalysis and final summary generation

[1343] The server sends the additional information back to the generation AI for reanalysis.

[1344] The generation AI generates the final description based on the additional information.

[1345] The emotion engine makes final adjustments by checking whether the tone of the final description matches the user's emotions.

[1346] 7. Provision of Information

[1347] The server displays the final description in the application's UI for other users to access.

[1348] Users will see the final description provided and can also view the original post if desired.

[1349] Specific examples

[1350] 1. Collecting posts

[1351] User: Posts to the application the text "I'm at a music festival right now. Stage A is very crowded and I'm feeling a bit exhausted." along with a photo of the crowded stage.

[1352] Terminal: Sends posted text and images to the server.

[1353] Server: Stores the submission in a database and sends the text and images for analysis.

[1354] 2. Data collection and analysis

[1355] Generative AI: Extracts keywords from the text, such as "music festival," "Stage A," "very crowded," and "tired."

[1356] Generative AI: Recognizes congestion status from images.

[1357] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[1358] 3. Emotional Recognition

[1359] Emotion engine: Recognizes the negative emotion of "tired" from the user's text and adjusts the description to a calmer tone.

[1360] 4. Question generation and submission

[1361] Generative AI: Determines that more specific information is lacking and generates questions such as, "Please tell me the specific stage names."

[1362] Emotion Engine: Adjust the tone of your question to something like, "You seem tired, can you tell me the name of the stage?"

[1363] Server: Sends the question to the user.

[1364] 5. Obtaining additional information

[1365] User: Answers "Main Stage A" and submits.

[1366] Terminal: Sends the answer to the server.

[1367] 6. Reanalysis and final summary generation

[1368] Server: Sends additional information to the generating AI for reanalysis.

[1369] Generative AI: Generates the final description: "Main Stage A at the music festival is very crowded, with many people gathered."

[1370] Emotion Engine: Check the tone of your description and adjust it if necessary.

[1371] 7. Provision of Information

[1372] Server: Provides the final description for other users to see.

[1373] Users: can view the provided description and also see the original post.

[1374] In this way, the present invention is a system that makes it possible to provide information in real time that takes into account the user's emotions, thereby improving the user experience.

[1375] The processing flow will be explained below.

[1376] Program processing

[1377] Step 1:

[1378] A user logs into a social networking-style application on their device, then enters "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit tired," attaches an image showing the crowded stage, and hits the post button.

[1379] Step 2:

[1380] The terminal sends the text and image data posted by the user to the specified server endpoint using an HTTP POST request.

[1381] Step 3:

[1382] The server stores the received text and image data in a database, then preprocesses the text and image data and sends them to the generative AI module for analysis.

[1383] Step 4:

[1384] The generative AI extracts important keywords and phrases from the text data, specifically identifying keywords such as "music festival," "Stage A," "very crowded," and "tired."

[1385] Step 5:

[1386] Generative AI analyzes image data and associates the image content with text data. For example, it can detect situations where many people are gathered in an image and integrate that information into the text analysis results.

[1387] Step 6:

[1388] The generative AI generates an initial description based on the results of text and image analysis, such as a summary like "Stage A at a music festival is currently very crowded."

[1389] Step 7:

[1390] The emotion engine analyzes the user's text to determine their emotions. Based on the keyword "tired," it recognizes the user's emotion as negative and adjusts the description to a calmer tone.

[1391] Step 8:

[1392] The generation AI checks whether the generated description is missing anything. If so, it generates a follow-up question, and the emotion engine adjusts the tone and content of the question. For example, it creates a question like, "You seem tired. Could you tell me the name of the specific stage?"

[1393] Step 9:

[1394] The server sends the generated question to the user, notifying them in a form that is easy for the user to understand and prompting them to provide additional information.

[1395] Step 10:

[1396] The user responds to the received question message with "Main Stage A" and presses the send button again.

[1397] Step 11:

[1398] The terminal transmits the user's answer to the server.

[1399] Step 12:

[1400] The server stores the additional information sent by the user in a database and performs re-analysis on the generated AI.

[1401] Step 13:

[1402] The generation AI reanalyzes the data based on additional information from the user and generates the final description: "Main Stage A of the music festival is very crowded, with many people gathered."

[1403] Step 14:

[1404] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary.

[1405] Step 15:

[1406] The server makes this final, adjusted description available to other users for access, for example, by displaying it on the application's home screen or on specific information pages.

[1407] Step 16:

[1408] Users can access the application on their devices to view the final description provided, and can also view the original post if desired.

[1409] Specific examples

[1410] 1. Collecting posts

[1411] User: Posts the text "I'm at a music festival right now. Stage A is very crowded and I'm a bit tired." along with an image showing the crowds.

[1412] Terminal: Sends the post to the server.

[1413] Server: Receives the posted content, stores it in a database, and sends the data to the generation AI module.

[1414] 2. Data collection and analysis

[1415] Generative AI: Extracts important keywords and recognizes congestion situations from images.

[1416] Generative AI: Generates the initial description, "Stage A at the music festival is very crowded."

[1417] 3. Emotional awareness and regulation

[1418] Sentiment engine: Recognizes negative sentiment from text and adjusts descriptions accordingly.

[1419] 4. Question generation and additional information acquisition

[1420] Generative AI: Generates questions and an emotional engine adjusts the tone.

[1421] Server: Sends the question to the user.

[1422] User: "Main Stage A"

[1423] Terminal: Sends additional information to the server.

[1424] Server: Resends additional information to the generating AI.

[1425] 5. Final summary generation and serving

[1426] Generative AI: Generates the final description, "Main Stage A at the music festival is very crowded, with many people gathered."

[1427] Emotion Engine: Making final adjustments.

[1428] Server: Provides the final description to other users.

[1429] User: View the final description provided.

[1430] In this way, the present invention realizes a system that provides real-time information that takes into account the user's emotions.

[1431] Example 2

[1432] 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."

[1433] In modern social networking systems, when users post information in real time, the information may not be properly conveyed to other users. Furthermore, the posted information contains emotions, but if these emotions are not taken into consideration, the recipient may misunderstand the information. Furthermore, if information is missing, questions to fill in the gaps are not automatically generated, which hinders the user's experience. Therefore, there is a need for a system that recognizes users' emotions, provides appropriately tailored information to other users, and automatically fills in missing information.

[1434] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1435] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data in the server and aggregating information, a generation means for generating an explanatory text from the aggregated information, an emotion recognition means for adjusting the explanatory text based on the user's emotion, and a provision means for providing the explanatory text to other users, thereby enabling information to be provided in real time taking into account the user's emotion.

[1436] "Input means" refers to a device or interface through which a user submits text and images.

[1437] "Communication means" refers to a network device or protocol for transmitting input text and image data to a server.

[1438] "Generation means" refers to a device or algorithm that analyzes text data and image data on a server and aggregates the information.

[1439] "Emotion recognition means" refers to a device or software for adjusting the generated caption based on the user's emotions.

[1440] "Providing means" refers to a system or interface for providing the generated explanation to other users.

[1441] The term "question generation means" refers to a device or program for generating a question for a user to fill in missing information and sending it to the user.

[1442] "Reanalysis means" refers to a system or process that receives additional information from the user and performs another analysis to generate the final summary.

[1443] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[1444] System configuration

[1445] Input method: Users log in to a social networking-style application using their own devices, such as their smartphones or PCs, and enter text and images to post. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage.

[1446] Communication method: The terminal sends the posted text and image data to the server. Specifically, it makes a POST request to the endpoint using the HTTPS protocol.

[1447] Generation method: The server stores the received text and image data in a database (e.g., MySQL or MongoDB). Next, it performs preprocessing such as tokenizing the text data, removing noise, and resizing and formatting the image data. After preprocessing is complete, the data is sent to the generation AI, which analyzes it using, for example, OpenAI's ChatGPT to extract important keywords and phrases. It also analyzes the image data and associates it with the text data. An initial description is generated based on the analysis results. For example, it generates a description such as, "Stage A at the music festival is currently very crowded."

[1448] Emotion recognition means: An emotion engine (for example, Microsoft's EmoNet) is used to analyze the user's emotions from the posted text and images. For example, it recognizes the negative emotion of "tired." The generation AI adjusts the tone of the generated description taking the user's emotions into account. For example, the description may be calmer, such as "Stage A at the music festival is currently very crowded, and I am feeling a bit tired."

[1449] Question generation means: The generation AI generates questions for the user to fill in missing information. For example, it generates a question such as, "Please tell me the specific stage name." The emotion engine adjusts the tone and content of the question. For example, it may change the tone to something like, "You seem tired, but could you please tell me the specific stage name?" The server sends the generated question to the original poster. Specifically, it sends the question to the user's device as a push notification or in-app message.

[1450] Reanalysis method: The user inputs and sends additional text or images in response to the received question. For example, the user sends the text "This is Main Stage A." The device sends this additional information to the server, which then sends it to the generation AI for reanalysis. The generation AI generates the final description based on the additional information. For example, it generates the final description "Main Stage A at the music festival is very crowded, with many people gathered." The emotion engine checks the tone of the description and makes final adjustments if necessary.

[1451] Delivery method: The server displays the final description in the application's UI for other users to access. Users can view the delivered description, see the original post, and post additional comments and feedback.

[1452] Prompt Sentence Examples

[1453] "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit exhausted. Based on this information, what emotions can you analyze and generate a description for?"

[1454] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1455] Step 1:

[1456] Users log in to a social networking-style application using a device such as a smartphone or PC, and post by entering text and images. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage. This post becomes the input.

[1457] The output is the user's posted data (text and images).

[1458] Step 2:

[1459] The terminal sends the user's posted data to the server. The HTTPS protocol is used to send the data, and the request format is POST. The data sent includes text, images, and the user ID. This is the input data.

[1460] The output is the submitted data that is forwarded to the server.

[1461] Step 3:

[1462] The server stores the received submission data in a database (e.g., MySQL or MongoDB), which makes the text and images persistent. This storage process is part of the data processing. It also performs preprocessing such as tokenizing and denoising the text data, and resizing and formatting the image data.

[1463] The output is preprocessed text and image data.

[1464] Step 4:

[1465] The server sends the preprocessed text and image data to the generative AI model. As a concrete example, we will use a general generative AI as the generative AI model. The preprocessed data (tokenized text and resized images) are input. The generative AI analyzes this data and extracts important keywords and phrases. It also associates them with the text data through image analysis. Data analysis and processing are then performed.

[1466] The output is the analysis results and an initial description (e.g., "Stage A at the music festival is currently very crowded.").

[1467] Step 5:

[1468] The emotion engine analyzes the user's emotions from the posted text and images. Specifically, it uses a common emotion analysis system to obtain emotional information from the text and images. The input data used is the user's posted text, "I'm currently at a music festival. Stage A is very crowded and I'm a bit tired." and the posted image. The emotion engine recognizes the negative emotion of "tired."

[1469] The output is the analyzed emotion information.

[1470] Step 6:

[1471] The generative AI adjusts the tone of the description based on the results of the emotion analysis. It uses the initial description generated earlier as input. To respond to the negative emotion of "tired," it adjusts the description to something like "Stage A at the music festival is currently very crowded, and I am feeling a bit tired." This adjustment process is part of data processing and data calculation.

[1472] The output is a sentiment-adjusted description.

[1473] Step 7:

[1474] If there are gaps in the initial description, the generative AI generates questions to fill in those gaps. The initial description and analyzed emotional information are used as input data. As a specific example, it generates questions such as "Please tell me the specific stage name."

[1475] The emotion engine adjusts the tone and content of the question, for example, "You seem tired, can you tell me the name of the stage?"

[1476] The output is the generated question.

[1477] Step 8:

[1478] The server sends the generated question to the original poster. Specifically, the question is sent to the user's device as a push notification or an in-app message. The input data is the generated question text.

[1479] The output is the question sent to the user terminal.

[1480] Step 9:

[1481] The user inputs additional text or images in response to the received question and submits it. For example, the user might reply, "This is Main Stage A." This response becomes new input data.

[1482] The output is additional information for the user.

[1483] Step 10:

[1484] The terminal sends the user's additional information to the server. Specifically, the terminal sends the user's additional text and images as a POST request.

[1485] The output is additional information that is forwarded to the server.

[1486] Step 11:

[1487] The server then sends the received additional information to the generation AI for reanalysis. The additional information from the user and the initial analysis data are used as input data. The generation AI then analyzes and processes the data again to generate the final description. For example, it generates the description "Main Stage A at the music festival is very crowded, with many people gathered."

[1488] The output is the final description.

[1489] Step 12:

[1490] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary. The input data is the final description and the emotion analysis data.

[1491] The output is a final, adjusted description.

[1492] Step 13:

[1493] The server displays the final description in the application's UI for other users to access, for example, as an in-app feed or notification. The input data is the final, adjusted description.

[1494] Users can view the final description provided, see the original post, and provide additional comments and feedback.

[1495] The output is the final information that can be viewed by other users.

[1496] (Application example 2)

[1497] 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."

[1498] In brick-and-mortar stores, it is currently difficult to grasp the inconveniences and satisfaction levels of users in real time. In particular, there is a need to properly analyze users' emotions and provide information and improve services accordingly. Therefore, in order to improve the user experience in brick-and-mortar stores, a system is needed that analyzes users' emotions in real time and provides this information, along with user feedback, to other users and staff.

[1499] The specific processing by the specific 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 an input means through which a user posts text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means in the server for analyzing the text data and image data and aggregating information, a generation means for generating an explanatory text from the information aggregated by the generation means, and an emotion analysis means for analyzing the user's emotion data and adjusting the tone of the explanatory text. This makes it possible to provide information that appropriately reflects the user's emotions and to provide real-time feedback to other users and staff.

[1500] "User" means an individual or end user who posts information using the System.

[1501] "Text" refers to character string information that is input by the user using an input means.

[1502] "Image" refers to still image data posted by a user using an input means.

[1503] "Input means" refers to a device, such as a smartphone or tablet, that allows a user to input text and images into the system.

[1504] "Communication means" refers to an internet connection or wireless communication technology for transmitting text and image data entered by the input means to a server.

[1505] A "server" is a computer system on a network that receives data from users, analyzes it, and aggregates the information.

[1506] "Text data" refers to text information posted by users that is held in digital format.

[1507] "Image data" refers to image information posted by users that is stored in digital format.

[1508] "Generation means" refers to the algorithms or software that analyzes text and image data, aggregates information, and generates descriptions on the server.

[1509] "Emotion analysis means" is a technology for analyzing the user's emotional data and adjusting the tone of the generated explanation.

[1510] The "provision means" is a function within the system for displaying the generated explanation to other users.

[1511] The "question generation means" is a technique for generating a question for the user to fill in the missing information, adjusting the tone of the question, and sending it to the user.

[1512] The "re-analysis means" is an algorithm or software that receives additional information from the user, performs the analysis again, and generates the final summary.

[1513] That's all.

[1514] The present invention is a system that allows users to post their experiences at physical stores in text and image format, analyzes the information in real time, and provides it to other users and store staff.

[1515] This system includes the following components: A user uses a mobile device, such as a smartphone or tablet, as input means for posting text and images. The text and image data entered through these input means are sent to a server via communication means, which utilizes an internet connection or wireless communication technology.

[1516] The server includes a generator for analyzing the received text and image data, including software libraries such as Hugging Face Transformers and OpenCV. The generator analyzes the submitted data, extracts important keywords and phrases, and generates a description.

[1517] Furthermore, the server includes a sentiment analysis module that analyzes users' emotional data. This sentiment analysis module extracts emotions from users' posts and adjusts the tone of the generated descriptions. For sentiment analysis, a natural language processing library such as TextBlob is used.

[1518] The server also includes a question generator that generates questions for the user to fill in the missing information, and sends the questions to the user with the tone adjusted by the sentiment analyzer, providing detailed feedback on the user's experience.

[1519] If additional information is available, the server will analyze it using a re-analysis method to generate the final description, using the same algorithms and software as the initial generation method.

[1520] As a specific example, if a user posts the text "I came to store B. The product layout is confusing," along with photos of products in the store, the system will process the following:

[1521] Users post text and images using their smartphones.

[1522] Data is sent from the terminal to the server.

[1523] The server analyzes the text and images and extracts important keywords.

[1524] A sentiment analysis means determines the user's sentiment and adjusts the tone of the generated description.

[1525] A question generation means generates questions to fill in the missing information and adjusts the tone of the questions based on sentiment analysis.

[1526] The user provides additional information.

[1527] A reanalysis means analyzes the additional information and generates the final description.

[1528] The final description will be displayed to other users and store staff.

[1529] The following can be provided as examples of prompt sentences:

[1530] "Currently, I'm finding the layout of the XX store difficult to understand. Could you please tell me more about it?"

[1531] In this way, the present invention allows for an improved user experience in a physical store, providing relevant feedback in real time.

[1532] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1533] Step 1:

[1534] The user inputs text and images. Using a smartphone, the user takes and inputs text such as, "I'm at store B. The product layout is confusing," along with a photo of the store. The input data is temporarily saved on the device.

[1535] Step 2:

[1536] The terminal sends the input text and image data to the server. The communication method is via the Internet or wireless communication. The input data (text and image) is sent to the server, and the server receives it.

[1537] Step 3:

[1538] The server analyzes the received data. Using Hugging Face Transformers, the generation method, important keywords and phrases are extracted from the text data. Image data is analyzed using OpenCV and associated with the text data. The input data (text and images) is analyzed, and extracted keywords and related information are generated.

[1539] Step 4:

[1540] The server generates an initial description based on the analysis results. Based on the extracted keywords, the generative AI model Hugging Face Transformers generates a description such as "The product layout at store B is difficult to understand." The input data (analyzed keywords) is processed to generate the initial description.

[1541] Step 5:

[1542] The server analyzes the user's emotions. Using TextBlob, a sentiment analysis tool, emotions are extracted from the posted text data and the negative emotions contained in "difficult to understand" are recognized. The analyzed text data is input and emotional data is output.

[1543] Step 6:

[1544] The server adjusts the tone of the description based on the emotion data. The tone of the description generated using the emotion analysis results is adjusted, changing the description "The product layout at store B is difficult to understand" to a "calmer tone." The description is adjusted based on the emotion data.

[1545] Step 7:

[1546] The server generates a question to fill in the missing information. The question generation means generates a question such as "Which shelf specifically is difficult to find?", and then generates an adjusted question based on the emotion data such as "You seem tired, but could you tell me which shelf specifically?". The generated explanation is used as input, and the adjusted question is output.

[1547] Step 8:

[1548] The server sends the generated question to the user. The communication means sends the adjusted question to the user's terminal. The user receives the adjusted question as input.

[1549] Step 9:

[1550] The user inputs additional information. The user then inputs specific additional information, such as "This is the beverage shelf," and sends it from the terminal to the server. The user's response data is sent from the terminal and received by the server.

[1551] Step 10:

[1552] The server re-analyzes the additional information. The re-analysis means analyzes the received response and generates a final explanatory sentence. The analyzed response data is used as input to generate a final summary sentence such as "The layout of the beverage shelves at store B is difficult to understand."

[1553] Step 11:

[1554] The server provides the final description. The generated final summary is displayed to other users and store staff using a display means. The final summary is input and displayed so that users and staff can view it.

[1555] The above processing steps improve the user experience in real time in physical stores.

[1556] 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.

[1557] 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.

[1558] 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.

[1559] [Fourth embodiment]

[1560] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1561] 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.

[1562] 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).

[1563] 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.

[1564] 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.

[1565] 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).

[1566] 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.

[1567] 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.

[1568] 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.

[1569] 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.

[1570] 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.

[1571] 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.

[1572] 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."

[1573] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The program processing will be explained in natural language below, along with specific examples.

[1574] Program processing

[1575] 1. Collecting posts

[1576] Users use their devices to post text and images about events and disasters to a social networking-style application.

[1577] The terminal transmits the text and image data entered by the user to the server.

[1578] The server stores the received post data in a database.

[1579] 2. Data collection and analysis

[1580] The server preprocesses the received text and image data and sends it to the generation AI.

[1581] The generative AI analyzes text data to extract important keywords and phrases, and also analyzes image data and associates it with the text data.

[1582] The generative AI integrates the analysis results and generates a comprehensive explanation.

[1583] 3. Question generation

[1584] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[1585] The server sends the generated question to the user.

[1586] 4. Obtaining additional information

[1587] The user enters additional text or images in response to the received question and submits it.

[1588] The terminal transmits the user's answer to the server.

[1589] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[1590] 5. Provision of Information

[1591] The generation AI generates the final complete description.

[1592] The server makes this description accessible to other users.

[1593] Users can view the server-provided description and, if desired, view the original post.

[1594] Specific examples

[1595] 1. Collecting posts

[1596] User: Posts to the application the text "I'm at a big music festival today. Stage A is especially crowded!" along with an image showing how crowded the stage is.

[1597] Terminal: Sends posted text and images to the server.

[1598] Server: Stores the submission in a database and sends the text and images for analysis.

[1599] 2. Data collection and analysis

[1600] Generative AI: Extracts keywords from text such as "big music festival," "stage A," and "crowded," and recognizes crowded situations from images.

[1601] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[1602] 3. Question generation

[1603] Generative AI: Determines that more specific information is lacking and generates questions such as "What is the name of the main artist?"

[1604] Server: Sends the question to the user.

[1605] 4. Obtaining additional information

[1606] User: Enters answer "The main artist is Band X" and submits.

[1607] Terminal: Sends the answer to the server.

[1608] Server: Sends additional information to the generating AI for reanalysis.

[1609] 5. Provision of Information

[1610] Generative AI: Generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[1611] Server: Provides the final description for other users to see.

[1612] Users: can view the provided description and, if desired, the original post.

[1613] In this way, the system can efficiently provide users with the real-time, accurate information they desire.

[1614] The processing flow will be explained below.

[1615] Step 1:

[1616] Users use their own devices to input text and images into a social networking-style application and post.

[1617] Step 2:

[1618] The terminal transmits the posted text and image data to the server.

[1619] Step 3:

[1620] The server stores the received post data in a database.

[1621] Step 4:

[1622] The server preprocesses the stored text and image data and sends it to the generation AI.

[1623] Step 5:

[1624] The generative AI analyzes the received text data and extracts important keywords and phrases.

[1625] Step 6:

[1626] The generative AI analyzes image data and associates it with text data (e.g., "A large crowd is gathering").

[1627] Step 7:

[1628] The generative AI integrates the analysis results and generates an initial description.

[1629] Step 8:

[1630] The generation AI determines whether there are any deficiencies in the generated description.

[1631] Step 9:

[1632] Generative AI generates questions to fill in missing information (e.g., "Please tell me specific location and stage information").

[1633] Step 10:

[1634] The server sends the generated question to the original posting user.

[1635] Step 11:

[1636] The user enters additional information (text or images) in response to the question and submits the answer.

[1637] Step 12:

[1638] The terminal transmits the user's response data to the server.

[1639] Step 13:

[1640] The server then sends the additional information back to the generation AI for reanalysis.

[1641] Step 14:

[1642] The generation AI generates the final description based on the additional information.

[1643] Step 15:

[1644] The server displays the final description in the application's UI for other users to access.

[1645] Step 16:

[1646] The user sees the final description provided by the server and, if desired, the original post.

[1647] Example 1

[1648] 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."

[1649] Existing SNS-style information gathering and provision systems have difficulty effectively analyzing text and image data posted by users and providing appropriate information to other users. In particular, they lack the ability to perform detailed analysis of posted content, supplement missing information, or incorporate additional information, making it difficult to provide accurate information in real time.

[1650] 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.

[1651] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for preprocessing and analyzing the text data and image data in the server, a generation means for generating an explanatory text from the information analyzed by the generation means, a provision means for providing the explanatory text to other users, a reanalysis means for receiving additional information from users and reanalyzing it to generate a final summary, and a storage means for saving the text and image data input by users in a database. This makes it possible to effectively analyze the information posted by users and obtain additional information as needed, thereby providing accurate information to other users in real time.

[1652] "Input means" is an interface through which users contribute text and images to the system.

[1653] The "communication means" is a function for transmitting text and image data posted by the user via the input means to the server.

[1654] The "generation means" is a function for preprocessing and analyzing text data and image data received by the server.

[1655] The "providing means" is a function for disclosing and providing the description generated by the generating means to other users.

[1656] The "re-analysis means" is a function that receives additional information from the user and re-analyzes the data to generate the final summary.

[1657] The "storage means" is a function for storing the text and image data entered by the user in a database.

[1658] The "question generation means" is a function for generating a question for the user to supplement the missing information and sending the question to the user.

[1659] The present invention relates to a social networking service (SNS)-style information collection and provision system in which users post text and images. The purpose of this system is to enable users to collect information about events and disasters in real time and provide accurate and detailed information to other users. A specific embodiment of this system is described below.

[1660] System configuration

[1661] The system includes an input means for users to post text and images, a communication means, a generation means, a provision means, a reanalysis means, and a storage means. These means are primarily implemented using servers, terminals, and generative AI models (e.g., OpenAI's GPT-4).

[1662] Hardware and software used

[1663] User device: A device such as a smartphone, tablet, or PC.

[1664] Server: High-performance cloud server (e.g. AWS, Google Cloud Platform).

[1665] Generative AI models: Models that perform advanced natural language processing and image analysis, such as OpenAI's GPT-4.

[1666] Explanation of program processing

[1667] Collecting Posts

[1668] Users use their devices to post text and images about events and disasters to a social networking-style application.

[1669] The terminal transmits the text and image data entered by the user to the server.

[1670] The server stores the received post data in a database.

[1671] Data aggregation and analysis

[1672] The server preprocesses the received text and image data and sends it to the generative AI model, which includes string cleansing, removing unnecessary tags, and adjusting image resolution.

[1673] The generative AI model extracts important keywords and phrases from text data and also analyzes image data and associates it with the text data.

[1674] The generative AI integrates the analysis results and generates a comprehensive explanation.

[1675] question generation

[1676] If there are any gaps in the description, the generation AI will generate questions to fill in the gaps.

[1677] The server sends the generated question to the user.

[1678] Obtaining additional information

[1679] The user enters additional text or images in response to the received question and submits it.

[1680] The terminal transmits the user's answer to the server.

[1681] The server then sends the additional information back to the generation AI, which uses it to generate the final summary.

[1682] Providing information

[1683] The generation AI generates the final complete description.

[1684] The server makes this description accessible to other users.

[1685] Users can view the server-provided description and, if desired, view the original post.

[1686] Specific examples

[1687] 1. A user uses their smartphone to post the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing how crowded the stage is.

[1688] 2. The device sends the posted text and images to the server.

[1689] 3. The server stores the post in a database and sends the text and images for analysis.

[1690] 4. The generative AI model extracts keywords from the text, such as "big music festival," "stage A," and "crowded," and recognizes the crowded situation from the image.

[1691] 5. The AI ​​generates the initial description: "Stage A at the music festival is currently very crowded."

[1692] 6. The generative AI determines that more specific information is lacking and generates questions such as, "What is the name of the main artist?"

[1693] 7. The server sends the question to the user.

[1694] 8. The user answers, "The main artist is Band X," and submits.

[1695] 9. The device sends the response to the server.

[1696] 10. The server sends additional information to the generation AI for reanalysis.

[1697] 11. The AI ​​generates the final description: "Band X is performing on Stage A at a music festival, and it's very crowded."

[1698] 12. The server provides the final description for other users to see.

[1699] 13. Users can view the description provided and, if necessary, the original post.

[1700] Prompt Sentence Examples

[1701] "I'm at a big music festival. Stage A seems particularly busy. I need more information. Can you tell me the names of the main artists and how busy the other stages are?"

[1702] In this way, the present invention analyzes information provided by users in real time, supplements it with necessary additional information in a timely manner, and enables other users to receive accurate and detailed information.

[1703] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1704] Step 1:

[1705] A user uses their device to launch a social networking-style application and input text and images related to an event or disaster. For example, they can input text such as "I'm at a big music festival today. Stage A is particularly crowded and it's really tough!" along with an image showing the crowding situation on the stage. The input data is temporarily saved on the device and then sent to the server via a communication means by pressing the post button.

[1706] Step 2:

[1707] The terminal sends the text and image data entered by the user to the server. Specifically, the terminal divides the data into packets and transfers them to the server using the TCP / IP protocol. If the server confirms receipt, the terminal displays a notification of successful transmission to the user. At this stage, the input is the user's submitted data, and the output is a notification of successful transmission to the server.

[1708] Step 3:

[1709] The server saves the received text and image data in a database. Specifically, the server saves the text data as a string and the image data in binary format in storage. The saved data is placed in a queue for preprocessing, and the next process begins. The input in this step is the posted data received from the device, and the output is the data being saved to the database.

[1710] Step 4:

[1711] The server preprocesses the posted data stored in the database. Preprocessing includes removing unnecessary tags, normalizing text, adjusting image size, etc. This organizes the input data for the generative AI model. The input in this step is the posted data read from the database, and the output is the preprocessed data.

[1712] Step 5:

[1713] The server sends the preprocessed data to the generative AI model. Specifically, it uses an API to pass text data and image data to the generative AI. The generative AI model (e.g., OpenAI's GPT-4) extracts important keywords and phrases from the text data and also analyzes and associates them with the image data. The input in this step is the preprocessed data, and the output is the analysis results.

[1714] Step 6:

[1715] The generation AI integrates the analysis results and generates an initial description. Specifically, it creates a description such as "Stage A at the music festival is currently very crowded." The generated description is returned to the server and proceeds to the next step. The input in this step is the analysis data sent to the generation AI, and the output is the initial description.

[1716] Step 7:

[1717] If the generation AI determines that the description is incomplete, it generates a question to fill in the gaps. For example, it generates a question like, "What is the name of the main artist?" The generated question is returned to the server and is ready to be sent to the user. The input in this step is the initial description, and the output is the generated question.

[1718] Step 8:

[1719] The server sends the generated question to the user. Specifically, it sends the question to the user's device as a push notification or an in-app message. The input in this step is the generated question, and the output is a question notification to the user.

[1720] Step 9:

[1721] The user inputs additional text or image information in response to the received question and sends it to the server from their device. For example, they provide an answer such as "The main artist is Band X." The input in this step is the question from the server, and the output is the additional information from the user.

[1722] Step 10:

[1723] The terminal sends the additional information from the user to the server. This process is the same as in step 2, where additional text and image data are sent. The input in this step is the additional information, and the output is a notification of successful transmission to the server.

[1724] Step 11:

[1725] The server receives the additional information and sends it to the generative AI model for analysis again. The generative AI model takes the additional information into account to generate the final summary. For example, it creates a description such as "Band X is performing on Stage A at a music festival, and it's very crowded." The input in this step is the additional information, and the output is the final summary.

[1726] Step 12:

[1727] The server publishes the generated final description for other users to access. Specifically, it adds the description to a social networking application feed and updates it in real time. The input for this step is the final summary, and the output is the published description.

[1728] Step 13:

[1729] The user views the final description provided by the server and, if necessary, checks the original post. This allows the user to obtain accurate information in real time. The input in this step is the description from the server, and the output is the user's viewing result.

[1730] This is the specific flow of processing in the program for this system. At each step, the input data is processed appropriately, and ultimately a mechanism is established to provide the user with accurate and detailed information.

[1731] (Application example 1)

[1732] 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."

[1733] In today's world, there is a need to quickly and accurately obtain and share real-time information about events, disasters, and other events. However, conventional systems often take time to properly analyze and disseminate information posted by users, which impairs real-time reporting. Furthermore, inaccurate reports due to incomplete information can become a problem. The present invention aims to solve these problems and provide a system that provides accurate information in real time.

[1734] 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.

[1735] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data and aggregating information in the server, a generation means for generating an explanatory text as a real-time breaking news report from the information aggregated by the generation means, a provision means for providing the explanatory text to other users, and a notification means for sending a push notification to the user based on the explanatory text. This makes it possible to quickly analyze information posted by users and accurately provide it to other users in real time.

[1736] "Input means" refers to a device or interface through which a user can post text and images.

[1737] "Communication means" refers to network communication technologies and protocols for transmitting text and image data input by the input means to a server.

[1738] "Generation means" refers to algorithms or software that have the function of analyzing the text data and image data received by the server and aggregating the information.

[1739] "Explanation generation means" refers to algorithms or software for generating real-time news from aggregated information.

[1740] "Providing means" refers to an interface or service for providing the generated description to other users.

[1741] "Notification means" refers to the technology or method for sending a push notification to a user based on the generated description.

[1742] "Question generation means" refers to an algorithm or software that generates questions to fill in missing information and sends them to the user.

[1743] "Reanalysis means" refers to algorithms or software that have the ability to receive additional information from the user and reanalyze the final summary and breaking news content based on that information.

[1744] In order to implement the present invention, the following system configuration and program processing will be described.

[1745] System Configuration

[1746] This invention is a social networking service-style information collection and provision system where users post text and images. The system mainly consists of the following components:

[1747] Input means: A smartphone or smart glasses with an interface that allows the user to post text and images.

[1748] Communication means: Technology (Wi-Fi, 4G / 5G, etc.) that transmits text and image data entered by the input means to a server.

[1749] Server: The central component that receives and analyzes data. Specific hardware used is a cloud server such as Amazon Web Services (AWS).

[1750] Generation method: Software that analyzes received data and generates information. For AI-related analysis, services such as Amazon Comprehend and Amazon Rekognition are used.

[1751] Description generator: An AI model (e.g., OpenAI GPT-3) for generating descriptions from aggregated information.

[1752] Delivery medium: A web interface or application that delivers the generated descriptions to other users.

[1753] Notification method: Technology that sends push notifications based on the description (e.g., Amazon SNS).

[1754] Program processing

[1755] The processing of this system is carried out in the following sequence:

[1756] 1. Collection of User Submissions

[1757] Users post text and images related to events and disasters using their smartphones or smart glasses.

[1758] When a post is made, the input means transmits the data to the server using the communication means.

[1759] 2. Data Preprocessing and Analysis

[1760] The server receives the data using AWS Lambda and stores it in Amazon DynamoDB.

[1761] The stored data is then uploaded to AWS S3 for text and image analysis using Amazon Comprehend and Amazon Rekognition.

[1762] 3. Generating Descriptions

[1763] Based on the received data and analysis results, a generative AI model using OpenAI GPT-3 generates explanatory text as real-time breaking news.

[1764] 4. Question generation

[1765] If the description contains missing information, the generative AI model generates a question requesting additional information, and the server sends the question to the user.

[1766] 5. Collection of additional information

[1767] The user enters additional information in response to the question, which is then sent back to the server.

[1768] The reanalysis means receives additional information and generates the final narrative and flash content.

[1769] 6. Provision of Information

[1770] The server provides the generated information to other users via AWS CloudFront and sends push notifications using notification methods.

[1771] Specific examples

[1772] Here's an example of how this system can be used in practice:

[1773] 1. A user posts about an event: The user posts to the application the text "I'm at a big music festival today. Stage A is especially crowded and it's really tough!" along with an image showing the crowds at the stage.

[1774] 2. Analysis on the server: The server analyzes keywords such as "big music festival," "stage A," and "crowded" using Amazon Comprehend, and recognizes the level of congestion from the image using Amazon Rekognition.

[1775] 3. Automatic question generation for missing information: The generative AI model requires the name of the main artist as supplementary information, so it generates the question, "What is the name of the main artist?"

[1776] 4. Receive additional information from the user: The user responds, "The main artist is Band X," and sends this to the server.

[1777] 5. Final information provision: The final description is generated: "Band X will be performing on Stage A at the music festival, and it is very crowded," and is notified to other users.

[1778] Examples of prompts to input to a generative AI model:

[1779] There is a post that says "Stage A at a huge music festival is very crowded." Extract keywords from the post's details and images, and generate specific explanations and questions about the missing information.

[1780] Post content:

[1781] Text: I'm at a big music festival today. Stage A is especially crowded and it's tough!

[1782] Image: (Image data URL)

[1783] Generated keywords:

[1784] Big music festival

[1785] Stage A

[1786] congestion

[1787] Questions to generate:

[1788] What is the name of the main artist?

[1789] This system makes it possible to efficiently collect and quickly distribute accurate information in real time.

[1790] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1791] Step 1:

[1792] Collection of User Submissions

[1793] Input: The user uses a smartphone or smart glasses to input text and images related to the event or disaster.

[1794] Specific operation: Users post information about events and disaster situations to the application using text and images. For example, they might post something like, "I'm at a big music festival today. Stage A is especially crowded and it's really tough!"

[1795] Output: The entered text and image data is sent to the server via the application.

[1796] Step 2:

[1797] Data Preprocessing

[1798] Input: Text and image data submitted by the user.

[1799] How it works: The device receives text and image data and sends it to an AWS Lambda function via a RESTful API, where the received data is formatted and stored in Amazon DynamoDB, and the image data is uploaded to Amazon S3.

[1800] Output: Formatted text data and saved image data are sent to the next analysis step.

[1801] Step 3:

[1802] Data analysis

[1803] Input: Formatted text data and stored image data.

[1804] How it works: The server uses Amazon Comprehend to analyze the text data and extract important keywords. At the same time, it uses AWS Rekognition to analyze the image data and identify objects and situations within the image. For example, keywords such as "big music festival," "stage A," and "crowded" are extracted.

[1805] Output: The extracted keywords and analysis information are sent to the generative AI model.

[1806] Step 4:

[1807] Generating Descriptions

[1808] Input: Extracted keywords and analysis information.

[1809] How it works: The server uses OpenAI GPT-3 to generate real-time news descriptions based on the results of text and image analysis. For example, it might generate a description such as, "Stage A at the music festival is currently very crowded."

[1810] Output: The generated description is saved in the server's data store.

[1811] Step 5:

[1812] Missing information question generation

[1813] Input: The generated description.

[1814] How it works: Based on the description, the generative AI model identifies missing information and generates questions accordingly, such as "What is the name of the main artist?"

[1815] Output: The generated questions are stored on the server and sent to the user.

[1816] Step 6:

[1817] Collecting additional information

[1818] Input: The question sent by the server.

[1819] Specific operation: The user inputs additional information (text or image) in response to the received question, which is then retransmitted to the server via the terminal. For example, an answer such as "The main artist is Band X" is sent.

[1820] Output: Additional information is saved on the server, ready for reanalysis.

[1821] Step 7:

[1822] Reanalysis and generation of final description

[1823] Input: Additional information (text or image).

[1824] How it works: The server uses the generative AI model again to generate a final description based on the additional information, such as "Band X is performing on Stage A at the music festival, and it's very crowded."

[1825] Output: The final description is saved on the server and sent to the next serving step.

[1826] Step 8:

[1827] Information and Notification

[1828] Input: Final description.

[1829] Specific operation: The server publishes the generated description through a means of provision so that other users can access it. In addition, the user is notified as a breaking news item via the push notification function using AWS SNS.

[1830] Output: The user sees the description provided as real-time news and receives a push notification.

[1831] Through the above steps, information posted by users can be quickly analyzed and accurately provided to other users in real time.

[1832] 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.

[1833] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[1834] Program processing

[1835] 1. Collecting posts

[1836] Users can use their devices to input and post text and images into a social networking-style application.

[1837] The terminal transmits the posted text and image data to the server.

[1838] The server stores the received post data in a database.

[1839] 2. Data collection and analysis

[1840] The server preprocesses the text data and image data and sends them to the generation AI.

[1841] Generative AI analyzes text data to extract important keywords and phrases.

[1842] The generative AI also analyzes image data and associates it with text data.

[1843] The generative AI integrates the analysis results and generates an initial description.

[1844] 3. Emotional Recognition

[1845] The emotion engine analyzes user emotions from posted text and images.

[1846] The generative AI adjusts the tone of the generated description taking into account the user's emotions (e.g., a bright tone for positive emotions and a calm tone for negative emotions).

[1847] 4. Question generation and submission

[1848] If there are any gaps in the generated explanation, the generation AI will generate questions to fill in the gaps.

[1849] The emotion engine adjusts the tone and content of questions based on the user's emotions.

[1850] The server sends the generated question to the original posting user.

[1851] 5. Obtaining additional information

[1852] The user enters additional text or images in response to the received question and submits it.

[1853] The terminal transmits the user's answer to the server.

[1854] 6. Reanalysis and final summary generation

[1855] The server sends the additional information back to the generation AI for reanalysis.

[1856] The generation AI generates the final description based on the additional information.

[1857] The emotion engine makes final adjustments by checking whether the tone of the final description matches the user's emotions.

[1858] 7. Provision of Information

[1859] The server displays the final description in the application's UI for other users to access.

[1860] Users will see the final description provided and can also view the original post if desired.

[1861] Specific examples

[1862] 1. Collecting posts

[1863] User: Posts to the application the text "I'm at a music festival right now. Stage A is very crowded and I'm feeling a bit exhausted." along with a photo of the crowded stage.

[1864] Terminal: Sends posted text and images to the server.

[1865] Server: Stores the submission in a database and sends the text and images for analysis.

[1866] 2. Data collection and analysis

[1867] Generative AI: Extracts keywords from the text, such as "music festival," "Stage A," "very crowded," and "tired."

[1868] Generative AI: Recognizes congestion status from images.

[1869] Generative AI: Generates the initial description, "Stage A at the music festival is currently very crowded."

[1870] 3. Emotional Recognition

[1871] Emotion engine: Recognizes the negative emotion of "tired" from the user's text and adjusts the description to a calmer tone.

[1872] 4. Question generation and submission

[1873] Generative AI: Determines that more specific information is lacking and generates questions such as, "Please tell me the specific stage names."

[1874] Emotion Engine: Adjust the tone of your question to something like, "You seem tired, can you tell me the name of the stage?"

[1875] Server: Sends the question to the user.

[1876] 5. Obtaining additional information

[1877] User: Answers "Main Stage A" and submits.

[1878] Terminal: Sends the answer to the server.

[1879] 6. Reanalysis and final summary generation

[1880] Server: Sends additional information to the generating AI for reanalysis.

[1881] Generative AI: Generates the final description: "Main Stage A at the music festival is very crowded, with many people gathered."

[1882] Emotion Engine: Check the tone of your description and adjust it if necessary.

[1883] 7. Provision of Information

[1884] Server: Provides the final description for other users to see.

[1885] Users: can view the provided description and also see the original post.

[1886] In this way, the present invention is a system that makes it possible to provide information in real time that takes into account the user's emotions, thereby improving the user experience.

[1887] The processing flow will be explained below.

[1888] Program processing

[1889] Step 1:

[1890] A user logs into a social networking-style application on their device, then enters "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit tired," attaches an image showing the crowded stage, and hits the post button.

[1891] Step 2:

[1892] The terminal sends the text and image data posted by the user to the specified server endpoint using an HTTP POST request.

[1893] Step 3:

[1894] The server stores the received text and image data in a database, then preprocesses the text and image data and sends them to the generative AI module for analysis.

[1895] Step 4:

[1896] The generative AI extracts important keywords and phrases from the text data, specifically identifying keywords such as "music festival," "Stage A," "very crowded," and "tired."

[1897] Step 5:

[1898] Generative AI analyzes image data and associates the image content with text data. For example, it can detect situations where many people are gathered in an image and integrate that information into the text analysis results.

[1899] Step 6:

[1900] The generative AI generates an initial description based on the results of text and image analysis, such as a summary like "Stage A at a music festival is currently very crowded."

[1901] Step 7:

[1902] The emotion engine analyzes the user's text to determine their emotions. Based on the keyword "tired," it recognizes the user's emotion as negative and adjusts the description to a calmer tone.

[1903] Step 8:

[1904] The generation AI checks whether the generated description is missing anything. If so, it generates a follow-up question, and the emotion engine adjusts the tone and content of the question. For example, it creates a question like, "You seem tired. Could you tell me the name of the specific stage?"

[1905] Step 9:

[1906] The server sends the generated question to the user, notifying them in a form that is easy for the user to understand and prompting them to provide additional information.

[1907] Step 10:

[1908] The user responds to the received question message with "Main Stage A" and presses the send button again.

[1909] Step 11:

[1910] The terminal transmits the user's answer to the server.

[1911] Step 12:

[1912] The server stores the additional information sent by the user in a database and performs re-analysis on the generated AI.

[1913] Step 13:

[1914] The generation AI reanalyzes the data based on additional information from the user and generates the final description: "Main Stage A of the music festival is very crowded, with many people gathered."

[1915] Step 14:

[1916] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary.

[1917] Step 15:

[1918] The server makes this final, adjusted description available to other users for access, for example, by displaying it on the application's home screen or on specific information pages.

[1919] Step 16:

[1920] Users can access the application on their devices to view the final description provided, and can also view the original post if desired.

[1921] Specific examples

[1922] 1. Collecting posts

[1923] User: Posts the text "I'm at a music festival right now. Stage A is very crowded and I'm a bit tired." along with an image showing the crowds.

[1924] Terminal: Sends the post to the server.

[1925] Server: Receives the posted content, stores it in a database, and sends the data to the generation AI module.

[1926] 2. Data collection and analysis

[1927] Generative AI: Extracts important keywords and recognizes congestion situations from images.

[1928] Generative AI: Generates the initial description, "Stage A at the music festival is very crowded."

[1929] 3. Emotional awareness and regulation

[1930] Sentiment engine: Recognizes negative sentiment from text and adjusts descriptions accordingly.

[1931] 4. Question generation and additional information acquisition

[1932] Generative AI: Generates questions and an emotional engine adjusts the tone.

[1933] Server: Sends the question to the user.

[1934] User: "Main Stage A"

[1935] Terminal: Sends additional information to the server.

[1936] Server: Resends additional information to the generating AI.

[1937] 5. Final summary generation and serving

[1938] Generative AI: Generates the final description, "Main Stage A at the music festival is very crowded, with many people gathered."

[1939] Emotion Engine: Making final adjustments.

[1940] Server: Provides the final description to other users.

[1941] User: View the final description provided.

[1942] In this way, the present invention realizes a system that provides real-time information that takes into account the user's emotions.

[1943] Example 2

[1944] 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."

[1945] In modern social networking systems, when users post information in real time, the information may not be properly conveyed to other users. Furthermore, the posted information contains emotions, but if these emotions are not taken into consideration, the recipient may misunderstand the information. Furthermore, if information is missing, questions to fill in the gaps are not automatically generated, which hinders the user's experience. Therefore, there is a need for a system that recognizes users' emotions, provides appropriately tailored information to other users, and automatically fills in missing information.

[1946] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1947] In this invention, the server includes an input means for users to post text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means for analyzing the text data and image data in the server and aggregating information, a generation means for generating an explanatory text from the aggregated information, an emotion recognition means for adjusting the explanatory text based on the user's emotion, and a provision means for providing the explanatory text to other users, thereby enabling information to be provided in real time taking into account the user's emotion.

[1948] "Input means" refers to a device or interface through which a user submits text and images.

[1949] "Communication means" refers to a network device or protocol for transmitting input text and image data to a server.

[1950] "Generation means" refers to a device or algorithm that analyzes text data and image data on a server and aggregates the information.

[1951] "Emotion recognition means" refers to a device or software for adjusting the generated caption based on the user's emotions.

[1952] "Providing means" refers to a system or interface for providing the generated explanation to other users.

[1953] The term "question generation means" refers to a device or program for generating a question for a user to fill in missing information and sending it to the user.

[1954] "Reanalysis means" refers to a system or process that receives additional information from the user and performs another analysis to generate the final summary.

[1955] The present invention relates to a system that allows users to post information in real time using text and images, and aggregates that information to provide it to other users. In particular, the present invention describes a system that combines an emotion engine that recognizes the user's emotions and adjusts the content of the generated information and questions.

[1956] System configuration

[1957] Input method: Users log in to a social networking-style application using their own devices, such as their smartphones or PCs, and enter text and images to post. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage.

[1958] Communication method: The terminal sends the posted text and image data to the server. Specifically, it makes a POST request to the endpoint using the HTTPS protocol.

[1959] Generation method: The server stores the received text and image data in a database (e.g., MySQL or MongoDB). Next, it performs preprocessing such as tokenizing the text data, removing noise, and resizing and formatting the image data. After preprocessing is complete, the data is sent to the generation AI, which analyzes it using, for example, OpenAI's ChatGPT to extract important keywords and phrases. It also analyzes the image data and associates it with the text data. An initial description is generated based on the analysis results. For example, it generates a description such as, "Stage A at the music festival is currently very crowded."

[1960] Emotion recognition means: An emotion engine (for example, Microsoft's EmoNet) is used to analyze the user's emotions from the posted text and images. For example, it recognizes the negative emotion of "tired." The generation AI adjusts the tone of the generated description taking the user's emotions into account. For example, the description may be calmer, such as "Stage A at the music festival is currently very crowded, and I am feeling a bit tired."

[1961] Question generation means: The generation AI generates questions for the user to fill in missing information. For example, it generates a question such as, "Please tell me the specific stage name." The emotion engine adjusts the tone and content of the question. For example, it may change the tone to something like, "You seem tired, but could you please tell me the specific stage name?" The server sends the generated question to the original poster. Specifically, it sends the question to the user's device as a push notification or in-app message.

[1962] Reanalysis method: The user inputs and sends additional text or images in response to the received question. For example, the user sends the text "This is Main Stage A." The device sends this additional information to the server, which then sends it to the generation AI for reanalysis. The generation AI generates the final description based on the additional information. For example, it generates the final description "Main Stage A at the music festival is very crowded, with many people gathered." The emotion engine checks the tone of the description and makes final adjustments if necessary.

[1963] Delivery method: The server displays the final description in the application's UI for other users to access. Users can view the delivered description, see the original post, and post additional comments and feedback.

[1964] Prompt Sentence Examples

[1965] "I'm currently at a music festival. Stage A is very crowded and I'm feeling a bit exhausted. Based on this information, what emotions can you analyze and generate a description for?"

[1966] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1967] Step 1:

[1968] Users log in to a social networking-style application using a device such as a smartphone or PC, and post by entering text and images. For example, a user might post, "I'm currently at a music festival. Stage A is very crowded, and I'm a bit tired," along with a photo of the crowded stage. This post becomes the input.

[1969] The output is the user's posted data (text and images).

[1970] Step 2:

[1971] The terminal sends the user's posted data to the server. The HTTPS protocol is used to send the data, and the request format is POST. The data sent includes text, images, and the user ID. This is the input data.

[1972] The output is the submitted data that is forwarded to the server.

[1973] Step 3:

[1974] The server stores the received submission data in a database (e.g., MySQL or MongoDB), which makes the text and images persistent. This storage process is part of the data processing. It also performs preprocessing such as tokenizing and denoising the text data, and resizing and formatting the image data.

[1975] The output is preprocessed text and image data.

[1976] Step 4:

[1977] The server sends the preprocessed text and image data to the generative AI model. As a concrete example, we will use a general generative AI as the generative AI model. The preprocessed data (tokenized text and resized images) are input. The generative AI analyzes this data and extracts important keywords and phrases. It also associates them with the text data through image analysis. Data analysis and processing are then performed.

[1978] The output is the analysis results and an initial description (e.g., "Stage A at the music festival is currently very crowded.").

[1979] Step 5:

[1980] The emotion engine analyzes the user's emotions from the posted text and images. Specifically, it uses a common emotion analysis system to obtain emotional information from the text and images. The input data used is the user's posted text, "I'm currently at a music festival. Stage A is very crowded and I'm a bit tired." and the posted image. The emotion engine recognizes the negative emotion of "tired."

[1981] The output is the analyzed emotion information.

[1982] Step 6:

[1983] The generative AI adjusts the tone of the description based on the results of the emotion analysis. It uses the initial description generated earlier as input. To respond to the negative emotion of "tired," it adjusts the description to something like "Stage A at the music festival is currently very crowded, and I am feeling a bit tired." This adjustment process is part of data processing and data calculation.

[1984] The output is a sentiment-adjusted description.

[1985] Step 7:

[1986] If there are gaps in the initial description, the generative AI generates questions to fill in those gaps. The initial description and analyzed emotional information are used as input data. As a specific example, it generates questions such as "Please tell me the specific stage name."

[1987] The emotion engine adjusts the tone and content of the question, for example, "You seem tired, can you tell me the name of the stage?"

[1988] The output is the generated question.

[1989] Step 8:

[1990] The server sends the generated question to the original poster. Specifically, the question is sent to the user's device as a push notification or an in-app message. The input data is the generated question text.

[1991] The output is the question sent to the user terminal.

[1992] Step 9:

[1993] The user inputs additional text or images in response to the received question and submits it. For example, the user might reply, "This is Main Stage A." This response becomes new input data.

[1994] The output is additional information for the user.

[1995] Step 10:

[1996] The terminal sends the user's additional information to the server. Specifically, the terminal sends the user's additional text and images as a POST request.

[1997] The output is additional information that is forwarded to the server.

[1998] Step 11:

[1999] The server then sends the received additional information to the generation AI for reanalysis. The additional information from the user and the initial analysis data are used as input data. The generation AI then analyzes and processes the data again to generate the final description. For example, it generates the description "Main Stage A at the music festival is very crowded, with many people gathered."

[2000] The output is the final description.

[2001] Step 12:

[2002] The emotion engine checks whether the tone of the final description matches the user's emotions and makes final adjustments if necessary. The input data is the final description and the emotion analysis data.

[2003] The output is a final, adjusted description.

[2004] Step 13:

[2005] The server displays the final description in the application's UI for other users to access, for example, as an in-app feed or notification. The input data is the final, adjusted description.

[2006] Users can view the final description provided, see the original post, and provide additional comments and feedback.

[2007] The output is the final information that can be viewed by other users.

[2008] (Application example 2)

[2009] 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."

[2010] In brick-and-mortar stores, it is currently difficult to grasp the inconveniences and satisfaction levels of users in real time. In particular, there is a need to properly analyze users' emotions and provide information and improve services accordingly. Therefore, in order to improve the user experience in brick-and-mortar stores, a system is needed that analyzes users' emotions in real time and provides this information, along with user feedback, to other users and staff.

[2011] The specific processing by the specific 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 an input means through which a user posts text and images, a communication means for transmitting the text and image data input by the input means to the server, a generation means in the server for analyzing the text data and image data and aggregating information, a generation means for generating an explanatory text from the information aggregated by the generation means, and an emotion analysis means for analyzing the user's emotion data and adjusting the tone of the explanatory text. This makes it possible to provide information that appropriately reflects the user's emotions and to provide real-time feedback to other users and staff.

[2012] "User" means an individual or end user who posts information using the System.

[2013] "Text" refers to character string information that is input by the user using an input means.

[2014] "Image" refers to still image data posted by a user using an input means.

[2015] "Input means" refers to a device, such as a smartphone or tablet, that allows a user to input text and images into the system.

[2016] "Communication means" refers to an internet connection or wireless communication technology for transmitting text and image data entered by the input means to a server.

[2017] A "server" is a computer system on a network that receives data from users, analyzes it, and aggregates the information.

[2018] "Text data" refers to text information posted by users that is held in digital format.

[2019] "Image data" refers to image information posted by users that is stored in digital format.

[2020] "Generation means" refers to the algorithms or software that analyzes text and image data, aggregates information, and generates descriptions on the server.

[2021] "Emotion analysis means" is a technology for analyzing the user's emotional data and adjusting the tone of the generated explanation.

[2022] The "provision means" is a function within the system for displaying the generated explanation to other users.

[2023] The "question generation means" is a technique for generating a question for the user to fill in the missing information, adjusting the tone of the question, and sending it to the user.

[2024] The "re-analysis means" is an algorithm or software that receives additional information from the user, performs the analysis again, and generates the final summary.

[2025] That's all.

[2026] The present invention is a system that allows users to post their experiences at physical stores in text and image format, analyzes the information in real time, and provides it to other users and store staff.

[2027] This system includes the following components: A user uses a mobile device, such as a smartphone or tablet, as input means for posting text and images. The text and image data entered through these input means are sent to a server via communication means, which utilizes an internet connection or wireless communication technology.

[2028] The server includes a generator for analyzing the received text and image data, including software libraries such as Hugging Face Transformers and OpenCV. The generator analyzes the submitted data, extracts important keywords and phrases, and generates a description.

[2029] Furthermore, the server includes a sentiment analysis module that analyzes users' emotional data. This sentiment analysis module extracts emotions from users' posts and adjusts the tone of the generated descriptions. For sentiment analysis, a natural language processing library such as TextBlob is used.

[2030] The server also includes a question generator that generates questions for the user to fill in the missing information, and sends the questions to the user with the tone adjusted by the sentiment analyzer, providing detailed feedback on the user's experience.

[2031] If additional information is available, the server will analyze it using a re-analysis method to generate the final description, using the same algorithms and software as the initial generation method.

[2032] As a specific example, if a user posts the text "I came to store B. The product layout is confusing," along with photos of products in the store, the system will process the following:

[2033] Users post text and images using their smartphones.

[2034] Data is sent from the terminal to the server.

[2035] The server analyzes the text and images and extracts important keywords.

[2036] A sentiment analysis means determines the user's sentiment and adjusts the tone of the generated description.

[2037] A question generation means generates questions to fill in the missing information and adjusts the tone of the questions based on sentiment analysis.

[2038] The user provides additional information.

[2039] A reanalysis means analyzes the additional information and generates the final description.

[2040] The final description will be displayed to other users and store staff.

[2041] The following can be provided as examples of prompt sentences:

[2042] "Currently, I'm finding the layout of the XX store difficult to understand. Could you please tell me more about it?"

[2043] In this way, the present invention allows for an improved user experience in a physical store, providing relevant feedback in real time.

[2044] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2045] Step 1:

[2046] The user inputs text and images. Using a smartphone, the user takes and inputs text such as, "I'm at store B. The product layout is confusing," along with a photo of the store. The input data is temporarily saved on the device.

[2047] Step 2:

[2048] The terminal sends the input text and image data to the server. The communication method is via the Internet or wireless communication. The input data (text and image) is sent to the server, and the server receives it.

[2049] Step 3:

[2050] The server analyzes the received data. Using Hugging Face Transformers, the generation method, important keywords and phrases are extracted from the text data. Image data is analyzed using OpenCV and associated with the text data. The input data (text and images) is analyzed, and extracted keywords and related information are generated.

[2051] Step 4:

[2052] The server generates an initial description based on the analysis results. Based on the extracted keywords, the generative AI model Hugging Face Transformers generates a description such as "The product layout at store B is difficult to understand." The input data (analyzed keywords) is processed to generate the initial description.

[2053] Step 5:

[2054] The server analyzes the user's emotions. Using TextBlob, a sentiment analysis tool, emotions are extracted from the posted text data and the negative emotions contained in "difficult to understand" are recognized. The analyzed text data is input and emotional data is output.

[2055] Step 6:

[2056] The server adjusts the tone of the description based on the emotion data. The tone of the description generated using the emotion analysis results is adjusted, changing the description "The product layout at store B is difficult to understand" to a "calmer tone." The description is adjusted based on the emotion data.

[2057] Step 7:

[2058] The server generates a question to fill in the missing information. The question generation means generates a question such as "Which shelf specifically is difficult to find?", and then generates an adjusted question based on the emotion data such as "You seem tired, but could you tell me which shelf specifically?". The generated explanation is used as input, and the adjusted question is output.

[2059] Step 8:

[2060] The server sends the generated question to the user. The communication means sends the adjusted question to the user's terminal. The user receives the adjusted question as input.

[2061] Step 9:

[2062] The user inputs additional information. The user then inputs specific additional information, such as "This is the beverage shelf," and sends it from the terminal to the server. The user's response data is sent from the terminal and received by the server.

[2063] Step 10:

[2064] The server re-analyzes the additional information. The re-analysis means analyzes the received response and generates a final explanatory sentence. The analyzed response data is used as input to generate a final summary sentence such as "The layout of the beverage shelves at store B is difficult to understand."

[2065] Step 11:

[2066] The server provides the final description. The generated final summary is displayed to other users and store staff using a display means. The final summary is input and displayed so that users and staff can view it.

[2067] The above processing steps improve the user experience in real time in physical stores.

[2068] 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.

[2069] 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.

[2070] 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.

[2071] 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.

[2072] FIG. 9 illustrates 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 behaviors 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.

[2073] 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.

[2074] 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).

[2075] 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.

[2076] 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."

[2077] 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.

[2078] 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).

[2079] 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.

[2080] 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.

[2081] 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.

[2082] 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.

[2083] 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.

[2084] 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.

[2085] 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.

[2086] 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.

[2087] 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.

[2088] 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.

[2089] The following is further disclosed regarding the above embodiment.

[2090] (Claim 1)

[2091] an input means for users to post text and images;

[2092] a communication means for transmitting the text and image data input by the input means to a server;

[2093] a generating means for analyzing text data and image data in the server and aggregating information;

[2094] a generating means for generating an explanatory sentence from the information collected by the generating means;

[2095] The system includes a providing means for providing the description to other users.

[2096] (Claim 2)

[2097] 2. The system according to claim 1, wherein the generating means includes a question generating means for generating a question for the user to fill in the missing information and transmitting the question to the user.

[2098] (Claim 3)

[2099] 2. The system of claim 1, wherein the generating means includes reanalyzing means for receiving additional information from the user and generating a final summary.

[2100] "Example 1"

[2101] (Claim 1)

[2102] an input means for users to post text and images;

[2103] a communication means for transmitting the text and image data input by the input means to a server;

[2104] generating means for preprocessing and analyzing text data and image data in the server;

[2105] a generating means for generating an explanatory sentence from the information analyzed by the generating means;

[2106] providing means for providing the description to other users;

[2107] The system includes a reanalysis means for receiving additional information from the user and reanalyzing the information to generate a final summary.

[2108] (Claim 2)

[2109] 2. The system according to claim 1, wherein the generating means includes a question generating means for generating a question for the user to fill in the missing information and transmitting the question to the user.

[2110] (Claim 3)

[2111] 2. The system according to claim 1, further comprising a storage means for storing the text and image data input by the user through said input means in a database.

[2112] "Application Example 1"

[2113] (Claim 1)

[2114] an input means for users to post text and images;

[2115] a communication means for transmitting the text and image data input by the input means to a server;

[2116] a generating means for analyzing text data and image data in the server and aggregating information;

[2117] a generating means for generating a description as a real-time breaking news from the information collected by the generating means;

[2118] providing means for providing the description to other users;

[2119] a notification means for sending a push notification to a user based on the description;

[2120] A system including:

[2121] (Claim 2)

[2122] 2. The system according to claim 1, wherein the generating means includes a question generating means for generating a question for the user to fill in the missing information and transmitting the question to the user.

[2123] (Claim 3)

[2124] 10. The system of claim 1, wherein the generating means includes reanalyzing means for receiving additional information from the user and generating final summary and breaking news content.

[2125] "Example 2: Combining Emotion Engines"

[2126] (Claim 1)

[2127] an input means for users to post text and images;

[2128] a communication means for transmitting the text and image data input by the input means to a s...

Claims

1. an input means for users to post text and images; a communication means for transmitting the text and image data input by the input means to a server; a generating means for analyzing text data and image data in the server and aggregating information; a generating means for generating an explanatory sentence from the information collected by the generating means; The system includes a providing means for providing the description to other users.

2. 2. The system according to claim 1, wherein said generating means includes a question generating means for generating a question for the user to fill in the missing information and transmitting said question to the user.

3. 2. The system of claim 1, wherein the generating means includes reanalyzing means for receiving additional information from the user and generating a final summary.

Images