system

Abstract

A system is provided.SOLUTION: A system comprising: means for registering an account of an artificial intelligence model generated on an SNS; means for receiving a direct message transmitted by a user to the account; means for analyzing the received message and generating an answer using a generative artificial intelligence model; and means for returning the generated answer to the user as a direct message.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, social networking sites (SNS) have become an important means of communication, but opportunities for information gathering and communication using generative AI models are limited. As a result, many users are unfamiliar with generative AI models and are unable to fully utilize their usefulness. Furthermore, there is a need for an effective method for exchanging information using generative AI models. The present invention aims to solve these problems and realize efficient and natural communication between generative AI models and users. [Means for solving the problem]

[0005] The present invention solves the above-mentioned problems by the following means. Specifically, a system is provided that includes a means for registering an account of a generated AI model on a social networking site, a means for receiving direct messages sent by users to the account, a means for analyzing the received messages and generating a response using the generative AI model, and a means for replying to the user with the generated response as a direct message, thereby enabling users to communicate directly and effectively with the generative AI model. Furthermore, the system further includes a means for a user to reply to a post on the generative AI model's account, analyzing the reply message to the post, and again generating a response using the generative AI model, and a means for replying to the generated response to the user, thereby easily realizing two-way communication. Furthermore, the system further includes a means for providing a webhook for obtaining data on received user messages, thereby enabling efficient message processing in near real time.

[0006] "SNS" is an abbreviation for social networking service, an online platform for users to share information and content and communicate with each other.

[0007] A "generated artificial intelligence model" is an artificial intelligence system that has been trained using machine learning or deep learning techniques and has the ability to automatically generate text or information.

[0008] An "account" refers to the authentication information and profile that a user or system has individually on an online platform such as a social networking site.

[0009] "Direct message" is a function of social networking sites that allows users to send messages directly to specific people.

[0010] "Means for receiving" refers to a method or function for receiving data or messages sent from the outside.

[0011] "Means for analysis" refers to a method or function for understanding received information or data and performing the necessary processing or judgment.

[0012] A "means for generating answers using a generative artificial intelligence model" is a method or function that uses pre-trained artificial intelligence technology to automatically create appropriate responses to user questions.

[0013] A "means for replying" is a method or function for retransmitting the generated response or information to the other party.

[0014] A "webhook" is a mechanism that automatically sends notifications to a specified URL when a specific event occurs, enabling data to be sent and received in near real time. [Brief explanation of the drawings]

[0015] [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

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] 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).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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."

[0036] The present invention is a system that enables two-way communication by registering an account for an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses that are sent back to the user.

[0037] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0038] A user sends a direct message to the generated AI model's account on a social networking site using their device. For example, the user sends a message such as "What's the weather like today?" This message is transmitted to the server via the social networking site platform.

[0039] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are analyzed within the server and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message content.

[0040] The server receives an appropriate answer from the generated AI model, such as "It's sunny in Tokyo today." The server then organizes this answer, formats it in a way that's easy for the user to understand, and sends it back to the user as a direct message.

[0041] Users can get appropriate answers to their questions by receiving replies from the generative AI model. In addition, comments and questions on content posted by the generative AI model's account are also processed in the same way.

[0042] As a concrete example, if a user sends a direct message to a generative AI model's account saying, "Tell me the latest news," the server receives this and queries the generative AI model for information about news. The generative AI model generates a response containing appropriate news topics, and the server sends that response to the user. In this way, users can easily obtain the latest information.

[0043] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information that interests them.

[0044] This system enables efficient and natural communication between users and generative artificial intelligence models.

[0045] The processing flow will be explained below.

[0046] Step 1:

[0047] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0048] Step 2:

[0049] The user uses their device to send a direct message to the generative AI model's account on social media, asking a question such as, "What day is it today?"

[0050] Step 3:

[0051] The server receives direct messages sent by users using webhooks from the social networking platform, and obtains the sender ID and message content of the message.

[0052] Step 4:

[0053] The server analyzes the received message, extracts the necessary information, and prepares the message content appropriately to create a request to pass to the generative AI model.

[0054] Step 5:

[0055] The server sends a request to a generative AI model (e.g., OpenAI's GPT-3) asking it to generate an appropriate answer to the user's question.

[0056] Step 6:

[0057] The generative AI model receives requests from the server and generates a response based on the question, which is then returned to the server in text format.

[0058] Step 7:

[0059] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0060] Step 8:

[0061] The server then sends the prepared answer as a direct message to the user, so the user receives the answer to their question.

[0062] Step 9:

[0063] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0064] Step 10:

[0065] When a user replies to a post made by the generative AI model, the server receives the message again, analyzes it, and passes it to the generative AI model, which then generates a new response, which the server sends back to the user, thus realizing two-way communication.

[0066] Through the above steps, the system of the present invention realizes efficient and natural communication between the user and the generative AI model.

[0067] Example 1

[0068] 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."

[0069] To achieve natural, two-way communication between users and AI models on social media, it is necessary to receive messages in real time, analyze them appropriately, and quickly generate and reply to them. However, conventional systems have been inefficient in receiving and analyzing messages, resulting in delays in generating and replying to responses. Furthermore, there is a lack of a way to securely manage the account information of generated AI models.

[0070] 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.

[0071] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving direct messages sent by users to the account, means for analyzing the received messages and generating responses using the generative AI model, means for replying to the user with the generated responses as direct messages, means for securely managing account information of the generated AI model in a database, means for receiving messages in real time using a webhook function, means for analyzing the content of the messages and understanding their intent using analysis software, and means for sending requests to the generative AI model and receiving responses, thereby enabling the server to receive user messages in real time, analyze their content, and quickly generate and reply to appropriate responses.

[0072] An "artificial intelligence model" is an algorithm or system that uses natural language processing and machine learning techniques to generate appropriate answers or analytical results based on input data.

[0073] "Account" means an identifier and related information that individually identifies a user or system on a social networking platform.

[0074] "Direct Message" means a private message exchanged directly between specific users or accounts on a social media platform.

[0075] "Receiving" means the act of the server obtaining messages sent by users or other accounts from the SNS platform.

[0076] "Analysis" is the process of understanding the content of a received message and extracting its intent and meaning.

[0077] The "webhook function" is a function that sends notifications to a server when a specific event occurs, and is used to receive data in real time.

[0078] "Means for generating an answer" refers to the process of using an artificial intelligence model to create an appropriate answer for input data, as well as the system or technology for doing so.

[0079] "Reply" is the act of sending the generated answer to the user in response.

[0080] A "database" is a system for efficiently managing and storing account information, message data, etc.

[0081] "Analysis software" means programs or tools used to analyze the content of received messages.

[0082] "Submitting a request" is the process of making a specific request or query to an artificial intelligence model.

[0083] "Means for receiving a response" refers to the process and system for receiving answers or information to a request from an artificial intelligence model.

[0084] The present invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking service, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses and returning them to the users. Specific embodiments are described below.

[0085] The server first registers an account for the generated AI model using the API of the social media platform. This account information is stored and securely managed in a database. For example, a bot account is created using the Twitter API, authentication is performed using the API key and secret, and the account information is saved in the database.

[0086] The user uses a device to send a direct message to the generated AI model's account on a social networking site. The device can be a regular smartphone or tablet, and uses a dedicated application (e.g., the Twitter app) to access the social networking site. Specifically, the user opens the Twitter app on their smartphone and sends a message such as "What's the weather like today?" to the generated AI model's account.

[0087] The server uses the webhook function of the social media platform to receive messages sent by users in real time. For example, a Twitter webhook is set up to process the received messages in real time. The received messages are analyzed using analysis software (such as NLTK, a natural language processing library) to extract their intent and meaning. Based on the analysis results, a request is sent to a generative AI model (such as OpenAI's GPT-4) to generate an appropriate response.

[0088] The server receives appropriate answers from the generated AI model and organizes them. For example, when a user sends a message asking, "What's the weather like today?", the generated AI model generates an answer such as, "It's sunny in Tokyo today." The server then organizes this answer into a format that is easy for the user to understand and sends it back to the user as a direct message.

[0089] Users can get appropriate answers to their questions by receiving replies from the generative AI model. Furthermore, comments and questions on content posted by the generative AI model's account are also processed in the same manner. For example, if a user sends a direct message to the AI ​​model's account saying, "Tell me about the latest news," the server receives this and queries the generative AI model for information about the news. The generative AI model generates an answer containing appropriate news topics, and the server sends the answer to the user.

[0090] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information they are interested in.

[0091] This system enables efficient and natural communication between users and generative AI models.

[0092] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0093] Step 1:

[0094] The server uses the API of the social media platform to register the account of the generated artificial intelligence model. This account information is securely managed in a database. The input requires the API key and authentication information of the social media platform, and the generated account information is obtained as output. Specifically, the server creates a bot account using the Twitter API, authenticates using the API key and secret, and stores the account information in the database.

[0095] Step 2:

[0096] A user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the user's message (e.g., "What's the weather like today?"), and the output is the message sent to the social networking site. Specifically, the user opens the Twitter app on their smartphone, enters a message to the generative AI model's account, and clicks the send button.

[0097] Step 3:

[0098] The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is messages from the SNS platform, and the output is the received messages. Specifically, it sets up a Twitter WebHook and processes the received messages in real time.

[0099] Step 4:

[0100] The server analyzes the received message. This analysis extracts the intent and meaning of the message. The received message is the input, and the analysis results are the output. Specifically, the server analyzes the content of the message using analysis software (e.g., NLTK).

[0101] Step 5:

[0102] The server sends a request to the generative AI model based on the analysis results. The analysis results are the input, and the response from the generative AI model is the output. Specifically, it sends an API request to a generative AI model such as GPT-4 based on the analyzed content.

[0103] Step 6:

[0104] The server receives the appropriate answer from the generative AI model. The input is a response from the generative AI model, and the output is an appropriate answer. Specifically, it receives an answer such as "It's sunny in Tokyo today" from GPT-4.

[0105] Step 7:

[0106] The server organizes the received answers and formats them in a way that is easy for the user to understand. The input is the answer from the generative AI model, and the output is the formatted answer. Specifically, the server formats the answer and converts it into the SNS direct message format.

[0107] Step 8:

[0108] The server then returns the formatted response to the user as a direct message. The input is the formatted response, and the output is a reply to the user. Specifically, the server uses the Twitter API to send a direct message to the user.

[0109] This allows users to have natural, two-way communication with generative AI models in real time.

[0110] (Application example 1)

[0111] 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."

[0112] In conventional content distribution services, it is difficult for users to easily find movies and TV shows that suit their preferences, and there is a lack of systems that can recommend appropriate content, resulting in low user satisfaction.In addition, there is no established technology that can recommend appropriate content while enabling two-way communication through social networking services, so user convenience has not been sufficiently improved.

[0113] 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.

[0114] In this invention, the server includes means for registering an account of the generated AI model on the SNS, means for receiving direct messages sent by users to the account, means for analyzing the received message and generating a response using the generating AI model, means for returning the generated response to the user as a direct message, means for recommending content based on the user's message, and means for organizing the recommended content and providing it to the user, thereby enabling users to engage in two-way communication through the SNS and easily find content that suits their preferences.

[0115] "SNS" refers to social networking services, which are online platforms that allow users to exchange information and communicate with each other via the Internet.

[0116] An "artificial intelligence model" refers to a computer program that uses algorithms such as machine learning and deep learning to automatically perform pattern recognition, data analysis, and natural language understanding.

[0117] "Account Registration" refers to the process by which a user or system establishes and records the unique authentication information required to use a particular service.

[0118] "Direct messages" refer to private messages sent and received directly by users to each other on social media.

[0119] "Message analysis" is the process of understanding the content of a received message using natural language processing technology and extracting its intent and important information.

[0120] A "generative artificial intelligence model" refers to a system that uses artificial intelligence technologies such as large-scale language models to automatically generate responses to user inquiries and requests.

[0121] "Content recommendation" is the process of suggesting content such as movies, TV shows, and music that a user might like based on their interests and past behavior.

[0122] A "webhook" is a mechanism that sends an HTTP request to a pre-defined URL when a specific event occurs.

[0123] A system for realizing this invention includes a means for registering an account of a generated artificial intelligence model on a social networking site, a means for receiving direct messages sent by users to the account, a means for analyzing the received message and generating a response using the generated artificial intelligence model, a means for replying to the user with the generated response as a direct message, a means for recommending content based on the user's message, a means for organizing the recommended content and providing it to the user, and a means having a web hook for obtaining data on received user messages.

[0124] The server uses the API of the social media platform to register an account for the generated AI model. This account information is managed securely on the server side. The user uses their device to send a direct message to the generated AI model's account on the social media platform. For example, the user sends a message such as, "What recent sci-fi movies do you recommend?" This message is transmitted to the server via the social media platform.

[0125] The server uses the webhook function from the social media platform to receive messages sent by users in real time. The received messages are analyzed within the server, and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message's content. The server receives an appropriate answer from the generated artificial intelligence model. For example, the server can get an answer such as, "Recommended recent science fiction movies are 'Inception' and 'Interstellar'."

[0126] The server then organizes the answers, formats them in a way that is easy for the user to understand, and sends them back to the user as a direct message. By receiving a reply from the generative AI model, the user can get a proper answer to their question. Furthermore, based on the user's message, the AI ​​model can recommend related content.

[0127] For example, if a user sends a direct message asking, "What recent superhero movies do you recommend?", the server receives the message and queries the generative AI model for information about superhero movies. The generative AI model generates a response containing appropriate movie recommendations, and the server sends the response to the user. In this way, users can easily obtain recommended content in areas and genres that interest them.

[0128] Example prompt sentence:

[0129] User: Recommend movies based on "What are some recent superhero movies you recommend?"

[0130] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0131] Step 1:

[0132] A user sends a direct message to the generative AI model's account on a social networking site using a device. For example, the user might type a message like, "What recent sci-fi movies do you recommend?" The input data is the user's message, which is then sent to the server via the social networking site platform.

[0133] Step 2:

[0134] The server receives direct messages sent by users in real time using the webhook function of the SNS platform. The input data is the user's message from the SNS platform. The server extracts text data from the received message to analyze it.

[0135] Step 3:

[0136] The server analyzes the received message and generates a prompt to send a request to a generative AI model (e.g., a large-scale language model). The input data is the extracted text of the user message, and data processing and calculations are performed during the analysis and prompt generation process. The output data is the generated prompt.

[0137] Step 4:

[0138] The server sends a request to the generative AI model using the generated prompt. The input data is the generated prompt. The generative AI model generates an answer based on the prompt and returns it to the server. The output data is the answer text from the generative AI model.

[0139] Step 5:

[0140] The server receives the answer from the generative AI model and organizes it into a format that is easy for the user to understand. The input data is the answer text from the generative AI model, and the answer is organized through data processing and calculation. The output data is the organized answer text.

[0141] Step 6:

[0142] The server sends the organized answer back to the user as a direct message. The input data is the organized answer text, which is sent to the user via the SNS platform. The output data is the answer message displayed on the user's device.

[0143] Step 7:

[0144] Once the user receives the answer, they can then send a new direct message asking a related question, starting a feedback loop that allows the user to continually receive content recommendations via the generative AI model. The input data is the new user message, which is then sent back to the server.

[0145] 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.

[0146] This invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate replies to the users. This system is combined with an emotion engine that recognizes the user's emotions, adding a function that provides more natural and emotionally appropriate responses.

[0147] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0148] The user sends a direct message to the generative AI model's account on a social networking site using their device, such as "I'm very tired today." This message is then transmitted to the server via the social networking site.

[0149] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are passed to the emotion engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0150] Specifically, the emotion engine analyzes the message "I'm very tired today" and recognizes emotions such as fatigue and sadness. Based on this analysis, the server makes a request to the generative AI model, asking it to generate an answer appropriate to the emotion.

[0151] The server receives an appropriate answer from the generative AI model. For example, it might say, "Thank you for your hard work. Please take a good rest today." This answer is tailored based on the emotional data analyzed by the emotion engine.

[0152] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0153] If a user replies to a post by the generative AI model by saying, "I'd like to learn more about this topic," the process is similar. The server receives the message again, analyzes it, and passes it on to the generative AI model. The generative AI model generates a new response, which the server sends back to the user. This allows for natural, emotionally sensitive two-way communication.

[0154] As a concrete example, consider the case where a user sends a direct message saying, "Please tell me the latest news." The emotion engine analyzes this message as indicating the emotion of "curiosity." Based on this, the server instructs the generative AI model to generate detailed and interesting news information and provides the results to the user. For example, it might send a response to the user such as, "In the latest technology news, a next-generation smartphone has been announced. This technology is..."

[0155] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0156] The processing flow will be explained below.

[0157] Step 1:

[0158] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0159] Step 2:

[0160] The user uses the device to send a direct message to the generative AI model's account on social media, such as "I'm very tired today."

[0161] Step 3:

[0162] The server receives direct messages sent by users in real time using webhooks from the social media platform, and obtains the sender ID and message content of the message.

[0163] Step 4:

[0164] The server passes the received message to the emotion engine, which analyzes the emotions (e.g., joy, sadness, anger, etc.) contained in the message. Specifically, for a message like "I'm very tired today," it recognizes emotions such as fatigue and sadness.

[0165] Step 5:

[0166] Based on the analysis results of the emotion engine, the server creates an appropriate request to the generative AI model, which includes the user's message content and emotion data.

[0167] Step 6:

[0168] The server sends a request to the generative AI model, asking it to generate an emotionally relevant answer, for example, generating an appropriate response for the emotional data "I'm very tired today."

[0169] Step 7:

[0170] The generative AI model receives requests from the server and generates a response based on the question and emotion data, such as "Thank you for your hard work. Please take a good rest today."

[0171] Step 8:

[0172] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0173] Step 9:

[0174] The server then sends the prepared response as a direct message to the user, allowing the user to receive a response that is in tune with their emotions.

[0175] Step 10:

[0176] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0177] Step 11:

[0178] A similar process occurs when a user replies to a post made by the generative AI model. The server receives the message again, analyzes it through the emotion engine, and then asks the generative AI model to generate a response. This process ensures two-way communication in a natural and emotionally relevant way.

[0179] In this way, this system achieves efficient and natural communication between the user and the generative AI model that reflects emotions. As a specific example, if a user sends a direct message saying, "Please tell me the latest news," the emotion engine recognizes the emotion "curiosity." Based on this, the server has the generative AI model generate interesting news and provide that content to the user. In this way, it is possible to provide information that is in line with the user's emotions.

[0180] Example 2

[0181] 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."

[0182] In the past, it was difficult to realize natural, emotional interactions through automated responses in two-way communication on social networking sites. There was also a need for systems that could properly recognize users' emotions and provide responses based on those emotions. Furthermore, there was a need for systems that could respond in real time and provide detailed information.

[0183] 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.

[0184] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received messages and recognizing emotions using an emotion analysis engine, means for sending prompts to the generated AI model based on the emotion analysis results and generating an answer, and means for sending the generated answer back to the user as a message, thereby enabling natural and efficient two-way communication that is in line with emotions between the user and the AI ​​model.

[0185] "SNS" is an abbreviation for Social Networking Service, an online service that allows people to communicate over the Internet.

[0186] An "artificial intelligence model" is a computer program that can learn from data and make inferences and judgments like a human.

[0187] "Account" means the credentials and corresponding profile required for a particular User to access the Online Services.

[0188] A "message" is a short message or piece of information that a user sends to another user or system.

[0189] An "emotion analysis engine" is software or an algorithm that analyzes data such as text or voice and recognizes the emotions contained in that data.

[0190] A "prompt" is a text input that instructs an artificial intelligence model to respond or act in a particular way.

[0191] A "webhook" is a mechanism or technology for sending notifications to external systems when specific events occur.

[0192] This invention is a system for realizing natural and emotional two-way communication between users and AI models on social networking sites. Specific implementation methods for this system are described below.

[0193] System configuration

[0194] The server registers an account for the generated AI model using the API of the social media platform. This account information is managed on the server side while ensuring appropriate security.

[0195] The user sends a direct message to the account of the generated AI model on a social networking site using their device, and the message is transmitted to the server via the social networking site platform.

[0196] The server receives messages sent by users in real time using the webhook function of the social media platform. The received messages are passed to an emotion analysis engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0197] The sentiment analysis engine can be implemented using external services such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the analysis results, the server makes a request to a generative AI model, such as OpenAI or other natural language generation models, to generate an emotionally relevant answer.

[0198] The server receives an appropriate response from the generative AI model, which is adjusted based on sentiment analysis data. For example, a message like "I'm very tired today" can be answered with "Thank you for your hard work. Please take a good rest today."

[0199] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0200] Specific examples

[0201] Consider a scenario where a user uses their smartphone to send a direct message saying, "I'm so tired today." This message is received by the server via a webhook, and the emotion analysis engine recognizes emotions like "fatigue" and "sadness."

[0202] Based on the analysis results, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0203] The generative AI model generates a response such as, "Thank you for your hard work. Please take a good rest today." This response is organized by the server and sent back to the user as a direct message.

[0204] Prompt Sentence Examples

[0205] Sample prompt 1: "The user says, 'I'm very tired today.' Please generate a comforting response to this message."

[0206] Sample prompt 2: "The user says, 'What's the latest news?' Please respond with a detailed description of the latest technology news."

[0207] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0208] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0209] Step 1:

[0210] The server registers a social media account. The server registers an account for the generated artificial intelligence model using the API of the social media platform. This operation saves the API key and secret on the server. The input is the authentication information provided by the API of the social media platform, and the output is the registered account information. For example, consider the case where the server creates a new bot account using the API of a specific social media platform.

[0211] Step 2:

[0212] A user sends a message. The user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the message typed by the user on the device, and the output is the message sent to the social networking site. For example, a user might send the message "I'm very tired today."

[0213] Step 3:

[0214] The server receives the message. The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is the notification from the SNS platform, and the output is the received message data. By configuring the webhook, the server is established to receive messages at a specific URL.

[0215] Step 4:

[0216] The server performs sentiment analysis. The server passes the message received via webhook to a sentiment analysis engine, which analyzes the emotions contained in the message. The input is the message data received via webhook, and the output is the sentiment analysis result. For example, the server sends the message "I'm very tired today" to the sentiment analysis engine, and the resulting emotion data is "fatigue" or "sadness."

[0217] Step 5:

[0218] The server makes a request to the generative AI model. Based on the results of the sentiment analysis engine, the server sends a prompt to the generative AI model to generate an answer that is in line with the emotion. The input is the sentiment analysis result, and the output is a prompt request to the generative AI model. For example, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0219] Step 6:

[0220] The generative AI model generates an answer. The generative AI model generates an appropriate answer based on the prompt it receives. The input is the prompt request to the generative AI model, and the output is the generated answer data. For example, the generative AI model generates the message, "Thank you for your hard work. Please take a good rest today."

[0221] Step 7:

[0222] The server sends a response to the user. The server organizes the response received from the generative AI model, formats it in a format that is easy for the user to understand, and sends it back to the user as a direct message. The input is the generated response data, and the output is a direct message to the user. For example, consider the case where the server sends a response to the user with the message, "Thank you for your hard work. Please take a good rest today."

[0223] The above are the specific processing steps of the system.

[0224] (Application example 2)

[0225] 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."

[0226] Traditional customer service in brick-and-mortar stores relies on the experience and knowledge of store staff, making it difficult to maintain consistent customer service quality. It is also difficult to provide responses that reflect the customer's emotions, making improving customer satisfaction a challenge. Furthermore, there is a lack of ways to utilize rapidly advancing information technology to streamline communication between customers and store staff. To solve these issues, a new system is needed that utilizes AI technology to provide customer service that is sensitive to their emotions.

[0227] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0228] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received message and detecting the user's emotion, means for generating a response using the generative AI model based on the detected emotion, means for returning the generated response to the user as a message, and means for displaying the generated response on a staff member's terminal and providing the response, thereby enabling the provision of consistent, high-quality customer service that is sensitive to the emotions of customers.

[0229] "SNS" is an abbreviation for social network service, an online platform where users can share information and content and communicate with each other.

[0230] A "generated artificial intelligence model" is an AI system designed and trained for a specific application or service, capable of generating appropriate responses or actions based on user input.

[0231] "Account" means authentication information that uniquely identifies and grants access to a specific user or system on an SNS.

[0232] "User" refers to an individual user of a social media platform, who performs actions such as sending and receiving messages.

[0233] A "direct message" is a private message sent only to a specific person on a social media platform.

[0234] "Means for detecting emotions" refers to algorithms or technologies that analyze the content of messages sent by users and identify the emotional elements contained therein (such as joy, sadness, or anger).

[0235] "Answer generation means" refers to an AI system or algorithm that creates and provides an appropriate response to the user based on the results of sentiment analysis.

[0236] A "terminal" is a hardware device for information processing and communication, and specifically includes smartphones and tablets.

[0237] "Staff" refers to employees working in physical stores who are responsible for providing products and services to customers.

[0238] This invention is a system that uses an account of an artificial intelligence model generated on a social networking site to realize two-way communication that is sensitive to the user's emotions. This system is mainly composed of a social networking site platform, an emotion analysis engine, a generative AI model, a smartphone, etc.

[0239] The server first registers an account for the AI ​​model created using the API of the social media platform. This account is managed in a secure environment. Users use their smartphones to send direct messages to the AI ​​model's account on the social media platform. For example, if a user sends a message saying, "Please tell me how to use this product," the message is transmitted to the server using the webhook function of the social media platform.

[0240] The server sends the received message to a sentiment analysis engine, which analyzes the user's emotions (e.g., confusion, curiosity) from the message's content. Specifically, sentiment analysis is performed using a natural language processing library such as TextBlob. Based on the results of this analysis, the server creates a prompt for the generative AI model to generate an appropriate response. The prompt might be in the format, for example, "Emotion: curiosity, Message: 'Please tell me how to use this product.'"

[0241] The generative AI model generates an appropriate response based on this prompt, such as "Please turn on this product first, then..." This response is then sent back to the server, which then sends it back to the user as a direct message.

[0242] Furthermore, the generated answer is also displayed on the smartphone of the store staff, who can use the answer to provide appropriate support to the user. In this way, the system enables consistent responses that are sensitive to the customer's emotions, contributing to improved customer satisfaction.

[0243] As a concrete example, if a user sends a direct message saying, "Please tell me how to use this product," the server uses an emotion analysis engine to detect the emotion "curiosity" and generates the prompt "Emotion: curiosity, Message: 'Please tell me how to use this product.'" Based on this prompt, the generative AI model generates an answer such as "First, turn on this product, then..." and displays this on the smartphones of the user and store staff. In this way, customer service in physical stores is enhanced.

[0244] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0245] Step 1:

[0246] The server registers the account of the generated AI model using the API of the social media platform. Specifically, it sends an API request to obtain account information. The obtained account information is then stored in a secure database. The input is the API request, and the output is the obtained account information.

[0247] Step 2:

[0248] A user uses a smartphone to send a message to the account of the generated AI model on a social networking site. For example, the user sends a message such as "Please tell me how to use this product." This message is transmitted to the server via the social networking site platform. The input is the user's message, and the output is the data sent to the server via the social networking site platform.

[0249] Step 3:

[0250] The server receives messages sent by users in real time using the webhook function of the SNS platform. These messages are sent to the server in JSON format, which the server interprets and passes to the sentiment analysis engine. The input is the user's message, and the output is the message data passed to the analysis engine.

[0251] Step 4:

[0252] The server sends the received message to a sentiment analysis engine, which analyzes the emotions contained in the message. Specifically, it uses a natural language processing library such as TextBlob to classify the emotion of the message into categories such as "curiosity" or "confusion." The input is the user's message, and the output is the analyzed emotional data.

[0253] Step 5:

[0254] The server creates a prompt for the generative AI model based on the analysis results. For example, it generates a prompt in the format "Emotion: curiosity, Message: 'Please tell me how to use this product.'" The input is the analyzed emotion data and the user's message, and the output is the generated prompt.

[0255] Step 6:

[0256] The server sends the generated prompt sentence to the generative AI model and requests it to generate an appropriate response. The generative AI model generates a response based on the prompt and returns it to the server. The input is the generated prompt sentence, and the output is the generated response.

[0257] Step 7:

[0258] The server receives the generated response, converts it into an appropriate format, and returns it to the user as a direct message. Specifically, it formats the response text. The input is the generated response, and the output is the direct message sent to the user.

[0259] Step 8:

[0260] The server simultaneously sends the generated response to the store staff's smartphone device. Based on this information, the staff can provide more detailed and accurate support to the user. The input is the generated response, and the output is the response displayed on the staff's device.

[0261] 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.

[0262] 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.

[0263] 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.

[0264] [Second embodiment]

[0265] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0266] 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.

[0267] 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).

[0268] 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.

[0269] 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.

[0270] 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).

[0271] 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.

[0272] 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.

[0273] 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.

[0274] 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.

[0275] 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.

[0276] 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."

[0277] The present invention is a system that enables two-way communication by registering an account for an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses that are sent back to the user.

[0278] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0279] A user sends a direct message to the generated AI model's account on a social networking site using their device. For example, the user sends a message such as "What's the weather like today?" This message is transmitted to the server via the social networking site platform.

[0280] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are analyzed within the server and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message content.

[0281] The server receives an appropriate answer from the generated AI model, such as "It's sunny in Tokyo today." The server then organizes this answer, formats it in a way that's easy for the user to understand, and sends it back to the user as a direct message.

[0282] Users can get appropriate answers to their questions by receiving replies from the generative AI model. In addition, comments and questions on content posted by the generative AI model's account are also processed in the same way.

[0283] As a concrete example, if a user sends a direct message to a generative AI model's account saying, "Tell me the latest news," the server receives this and queries the generative AI model for information about news. The generative AI model generates a response containing appropriate news topics, and the server sends that response to the user. In this way, users can easily obtain the latest information.

[0284] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information that interests them.

[0285] This system enables efficient and natural communication between users and generative artificial intelligence models.

[0286] The processing flow will be explained below.

[0287] Step 1:

[0288] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0289] Step 2:

[0290] The user uses their device to send a direct message to the generative AI model's account on social media, asking a question such as, "What day is it today?"

[0291] Step 3:

[0292] The server receives direct messages sent by users using webhooks from the social networking platform, and obtains the sender ID and message content of the message.

[0293] Step 4:

[0294] The server analyzes the received message, extracts the necessary information, and prepares the message content appropriately to create a request to pass to the generative AI model.

[0295] Step 5:

[0296] The server sends a request to a generative AI model (e.g., OpenAI's GPT-3) asking it to generate an appropriate answer to the user's question.

[0297] Step 6:

[0298] The generative AI model receives requests from the server and generates a response based on the question, which is then returned to the server in text format.

[0299] Step 7:

[0300] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0301] Step 8:

[0302] The server then sends the prepared answer as a direct message to the user, so the user receives the answer to their question.

[0303] Step 9:

[0304] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0305] Step 10:

[0306] When a user replies to a post made by the generative AI model, the server receives the message again, analyzes it, and passes it to the generative AI model, which then generates a new response, which the server sends back to the user, thus realizing two-way communication.

[0307] Through the above steps, the system of the present invention realizes efficient and natural communication between the user and the generative AI model.

[0308] Example 1

[0309] 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."

[0310] To achieve natural, two-way communication between users and AI models on social media, it is necessary to receive messages in real time, analyze them appropriately, and quickly generate and reply to them. However, conventional systems have been inefficient in receiving and analyzing messages, resulting in delays in generating and replying to responses. Furthermore, there is a lack of a way to securely manage the account information of generated AI models.

[0311] 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.

[0312] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving direct messages sent by users to the account, means for analyzing the received messages and generating responses using the generative AI model, means for replying to the user with the generated responses as direct messages, means for securely managing account information of the generated AI model in a database, means for receiving messages in real time using a webhook function, means for analyzing the content of the messages and understanding their intent using analysis software, and means for sending requests to the generative AI model and receiving responses, thereby enabling the server to receive user messages in real time, analyze their content, and quickly generate and reply to appropriate responses.

[0313] An "artificial intelligence model" is an algorithm or system that uses natural language processing and machine learning techniques to generate appropriate answers or analytical results based on input data.

[0314] "Account" means an identifier and related information that individually identifies a user or system on a social networking platform.

[0315] "Direct Message" means a private message exchanged directly between specific users or accounts on a social media platform.

[0316] "Receiving" means the act of the server obtaining messages sent by users or other accounts from the SNS platform.

[0317] "Analysis" is the process of understanding the content of a received message and extracting its intent and meaning.

[0318] The "webhook function" is a function that sends notifications to a server when a specific event occurs, and is used to receive data in real time.

[0319] "Means for generating an answer" refers to the process of using an artificial intelligence model to create an appropriate answer for input data, as well as the system or technology for doing so.

[0320] "Reply" is the act of sending the generated answer to the user in response.

[0321] A "database" is a system for efficiently managing and storing account information, message data, etc.

[0322] "Analysis software" means programs or tools used to analyze the content of received messages.

[0323] "Submitting a request" is the process of making a specific request or query to an artificial intelligence model.

[0324] "Means for receiving a response" refers to the process and system for receiving answers or information to a request from an artificial intelligence model.

[0325] The present invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking service, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses and returning them to the users. Specific embodiments are described below.

[0326] The server first registers an account for the generated AI model using the API of the social media platform. This account information is stored and securely managed in a database. For example, a bot account is created using the Twitter API, authentication is performed using the API key and secret, and the account information is saved in the database.

[0327] The user uses a device to send a direct message to the generated AI model's account on a social networking site. The device can be a regular smartphone or tablet, and uses a dedicated application (e.g., the Twitter app) to access the social networking site. Specifically, the user opens the Twitter app on their smartphone and sends a message such as "What's the weather like today?" to the generated AI model's account.

[0328] The server uses the webhook function of the social media platform to receive messages sent by users in real time. For example, a Twitter webhook is set up to process the received messages in real time. The received messages are analyzed using analysis software (such as NLTK, a natural language processing library) to extract their intent and meaning. Based on the analysis results, a request is sent to a generative AI model (such as OpenAI's GPT-4) to generate an appropriate response.

[0329] The server receives appropriate answers from the generated AI model and organizes them. For example, when a user sends a message asking, "What's the weather like today?", the generated AI model generates an answer such as, "It's sunny in Tokyo today." The server then organizes this answer into a format that is easy for the user to understand and sends it back to the user as a direct message.

[0330] Users can get appropriate answers to their questions by receiving replies from the generative AI model. Furthermore, comments and questions on content posted by the generative AI model's account are also processed in the same manner. For example, if a user sends a direct message to the AI ​​model's account saying, "Tell me about the latest news," the server receives this and queries the generative AI model for information about the news. The generative AI model generates an answer containing appropriate news topics, and the server sends the answer to the user.

[0331] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information they are interested in.

[0332] This system enables efficient and natural communication between users and generative AI models.

[0333] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0334] Step 1:

[0335] The server uses the API of the social media platform to register the account of the generated artificial intelligence model. This account information is securely managed in a database. The input requires the API key and authentication information of the social media platform, and the generated account information is obtained as output. Specifically, the server creates a bot account using the Twitter API, authenticates using the API key and secret, and stores the account information in the database.

[0336] Step 2:

[0337] A user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the user's message (e.g., "What's the weather like today?"), and the output is the message sent to the social networking site. Specifically, the user opens the Twitter app on their smartphone, enters a message to the generative AI model's account, and clicks the send button.

[0338] Step 3:

[0339] The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is messages from the SNS platform, and the output is the received messages. Specifically, it sets up a Twitter WebHook and processes the received messages in real time.

[0340] Step 4:

[0341] The server analyzes the received message. This analysis extracts the intent and meaning of the message. The received message is the input, and the analysis results are the output. Specifically, the server analyzes the content of the message using analysis software (e.g., NLTK).

[0342] Step 5:

[0343] The server sends a request to the generative AI model based on the analysis results. The analysis results are the input, and the response from the generative AI model is the output. Specifically, it sends an API request to a generative AI model such as GPT-4 based on the analyzed content.

[0344] Step 6:

[0345] The server receives the appropriate answer from the generative AI model. The input is a response from the generative AI model, and the output is an appropriate answer. Specifically, it receives an answer such as "It's sunny in Tokyo today" from GPT-4.

[0346] Step 7:

[0347] The server organizes the received answers and formats them in a way that is easy for the user to understand. The input is the answer from the generative AI model, and the output is the formatted answer. Specifically, the server formats the answer and converts it into the SNS direct message format.

[0348] Step 8:

[0349] The server then returns the formatted response to the user as a direct message. The input is the formatted response, and the output is a reply to the user. Specifically, the server uses the Twitter API to send a direct message to the user.

[0350] This allows users to have natural, two-way communication with generative AI models in real time.

[0351] (Application example 1)

[0352] 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."

[0353] In conventional content distribution services, it is difficult for users to easily find movies and TV shows that suit their preferences, and there is a lack of systems that can recommend appropriate content, resulting in low user satisfaction.In addition, there is no established technology that can recommend appropriate content while enabling two-way communication through social networking services, so user convenience has not been sufficiently improved.

[0354] 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.

[0355] In this invention, the server includes means for registering an account of the generated AI model on the SNS, means for receiving direct messages sent by users to the account, means for analyzing the received message and generating a response using the generating AI model, means for returning the generated response to the user as a direct message, means for recommending content based on the user's message, and means for organizing the recommended content and providing it to the user, thereby enabling users to engage in two-way communication through the SNS and easily find content that suits their preferences.

[0356] "SNS" refers to social networking services, which are online platforms that allow users to exchange information and communicate with each other via the Internet.

[0357] An "artificial intelligence model" refers to a computer program that uses algorithms such as machine learning and deep learning to automatically perform pattern recognition, data analysis, and natural language understanding.

[0358] "Account Registration" refers to the process by which a user or system establishes and records the unique authentication information required to use a particular service.

[0359] "Direct messages" refer to private messages sent and received directly by users to each other on social media.

[0360] "Message analysis" is the process of understanding the content of a received message using natural language processing technology and extracting its intent and important information.

[0361] A "generative artificial intelligence model" refers to a system that uses artificial intelligence technologies such as large-scale language models to automatically generate responses to user inquiries and requests.

[0362] "Content recommendation" is the process of suggesting content such as movies, TV shows, and music that a user might like based on their interests and past behavior.

[0363] A "webhook" is a mechanism that sends an HTTP request to a pre-defined URL when a specific event occurs.

[0364] A system for realizing this invention includes a means for registering an account of a generated artificial intelligence model on a social networking site, a means for receiving direct messages sent by users to the account, a means for analyzing the received message and generating a response using the generated artificial intelligence model, a means for replying to the user with the generated response as a direct message, a means for recommending content based on the user's message, a means for organizing the recommended content and providing it to the user, and a means having a web hook for obtaining data on received user messages.

[0365] The server uses the API of the social media platform to register an account for the generated AI model. This account information is managed securely on the server side. The user uses their device to send a direct message to the generated AI model's account on the social media platform. For example, the user sends a message such as, "What recent sci-fi movies do you recommend?" This message is transmitted to the server via the social media platform.

[0366] The server uses the webhook function from the social media platform to receive messages sent by users in real time. The received messages are analyzed within the server, and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message's content. The server receives an appropriate answer from the generated artificial intelligence model. For example, the server can get an answer such as, "Recommended recent science fiction movies are 'Inception' and 'Interstellar'."

[0367] The server then organizes the answers, formats them in a way that is easy for the user to understand, and sends them back to the user as a direct message. By receiving a reply from the generative AI model, the user can get a proper answer to their question. Furthermore, based on the user's message, the AI ​​model can recommend related content.

[0368] For example, if a user sends a direct message asking, "What recent superhero movies do you recommend?", the server receives the message and queries the generative AI model for information about superhero movies. The generative AI model generates a response containing appropriate movie recommendations, and the server sends the response to the user. In this way, users can easily obtain recommended content in areas and genres that interest them.

[0369] Example prompt sentence:

[0370] User: Recommend movies based on "What are some recent superhero movies you recommend?"

[0371] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0372] Step 1:

[0373] A user sends a direct message to the generative AI model's account on a social networking site using a device. For example, the user might type a message like, "What recent sci-fi movies do you recommend?" The input data is the user's message, which is then sent to the server via the social networking site platform.

[0374] Step 2:

[0375] The server receives direct messages sent by users in real time using the webhook function of the SNS platform. The input data is the user's message from the SNS platform. The server extracts text data from the received message to analyze it.

[0376] Step 3:

[0377] The server analyzes the received message and generates a prompt to send a request to a generative AI model (e.g., a large-scale language model). The input data is the extracted text of the user message, and data processing and calculations are performed during the analysis and prompt generation process. The output data is the generated prompt.

[0378] Step 4:

[0379] The server sends a request to the generative AI model using the generated prompt. The input data is the generated prompt. The generative AI model generates an answer based on the prompt and returns it to the server. The output data is the answer text from the generative AI model.

[0380] Step 5:

[0381] The server receives the answer from the generative AI model and organizes it into a format that is easy for the user to understand. The input data is the answer text from the generative AI model, and the answer is organized through data processing and calculation. The output data is the organized answer text.

[0382] Step 6:

[0383] The server sends the organized answer back to the user as a direct message. The input data is the organized answer text, which is sent to the user via the SNS platform. The output data is the answer message displayed on the user's device.

[0384] Step 7:

[0385] Once the user receives the answer, they can then send a new direct message asking a related question, starting a feedback loop that allows the user to continually receive content recommendations via the generative AI model. The input data is the new user message, which is then sent back to the server.

[0386] 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.

[0387] This invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate replies to the users. This system is combined with an emotion engine that recognizes the user's emotions, adding a function that provides more natural and emotionally appropriate responses.

[0388] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0389] The user sends a direct message to the generative AI model's account on a social networking site using their device, such as "I'm very tired today." This message is then transmitted to the server via the social networking site.

[0390] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are passed to the emotion engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0391] Specifically, the emotion engine analyzes the message "I'm very tired today" and recognizes emotions such as fatigue and sadness. Based on this analysis, the server makes a request to the generative AI model, asking it to generate an answer appropriate to the emotion.

[0392] The server receives an appropriate answer from the generative AI model. For example, it might say, "Thank you for your hard work. Please take a good rest today." This answer is tailored based on the emotional data analyzed by the emotion engine.

[0393] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0394] If a user replies to a post by the generative AI model by saying, "I'd like to learn more about this topic," the process is similar. The server receives the message again, analyzes it, and passes it on to the generative AI model. The generative AI model generates a new response, which the server sends back to the user. This allows for natural, emotionally sensitive two-way communication.

[0395] As a concrete example, consider the case where a user sends a direct message saying, "Please tell me the latest news." The emotion engine analyzes this message as indicating the emotion of "curiosity." Based on this, the server instructs the generative AI model to generate detailed and interesting news information and provides the results to the user. For example, it might send a response to the user such as, "In the latest technology news, a next-generation smartphone has been announced. This technology is..."

[0396] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0397] The processing flow will be explained below.

[0398] Step 1:

[0399] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0400] Step 2:

[0401] The user uses the device to send a direct message to the generative AI model's account on social media, such as "I'm very tired today."

[0402] Step 3:

[0403] The server receives direct messages sent by users in real time using webhooks from the social media platform, and obtains the sender ID and message content of the message.

[0404] Step 4:

[0405] The server passes the received message to the emotion engine, which analyzes the emotions (e.g., joy, sadness, anger, etc.) contained in the message. Specifically, for a message like "I'm very tired today," it recognizes emotions such as fatigue and sadness.

[0406] Step 5:

[0407] Based on the analysis results of the emotion engine, the server creates an appropriate request to the generative AI model, which includes the user's message content and emotion data.

[0408] Step 6:

[0409] The server sends a request to the generative AI model, asking it to generate an emotionally relevant answer, for example, generating an appropriate response for the emotional data "I'm very tired today."

[0410] Step 7:

[0411] The generative AI model receives requests from the server and generates a response based on the question and emotion data, such as "Thank you for your hard work. Please take a good rest today."

[0412] Step 8:

[0413] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0414] Step 9:

[0415] The server then sends the prepared response as a direct message to the user, allowing the user to receive a response that is in tune with their emotions.

[0416] Step 10:

[0417] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0418] Step 11:

[0419] A similar process occurs when a user replies to a post made by the generative AI model. The server receives the message again, analyzes it through the emotion engine, and then asks the generative AI model to generate a response. This process ensures two-way communication in a natural and emotionally relevant way.

[0420] In this way, this system achieves efficient and natural communication between the user and the generative AI model that reflects emotions. As a specific example, if a user sends a direct message saying, "Please tell me the latest news," the emotion engine recognizes the emotion "curiosity." Based on this, the server has the generative AI model generate interesting news and provide that content to the user. In this way, it is possible to provide information that is in line with the user's emotions.

[0421] Example 2

[0422] 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."

[0423] In the past, it was difficult to realize natural, emotional interactions through automated responses in two-way communication on social networking sites. There was also a need for systems that could properly recognize users' emotions and provide responses based on those emotions. Furthermore, there was a need for systems that could respond in real time and provide detailed information.

[0424] 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.

[0425] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received messages and recognizing emotions using an emotion analysis engine, means for sending prompts to the generated AI model based on the emotion analysis results and generating an answer, and means for sending the generated answer back to the user as a message, thereby enabling natural and efficient two-way communication that is in line with emotions between the user and the AI ​​model.

[0426] "SNS" is an abbreviation for Social Networking Service, an online service that allows people to communicate over the Internet.

[0427] An "artificial intelligence model" is a computer program that can learn from data and make inferences and judgments like a human.

[0428] "Account" means the credentials and corresponding profile required for a particular User to access the Online Services.

[0429] A "message" is a short message or piece of information that a user sends to another user or system.

[0430] An "emotion analysis engine" is software or an algorithm that analyzes data such as text or voice and recognizes the emotions contained in that data.

[0431] A "prompt" is a text input that instructs an artificial intelligence model to respond or act in a particular way.

[0432] A "webhook" is a mechanism or technology for sending notifications to external systems when specific events occur.

[0433] This invention is a system for realizing natural and emotional two-way communication between users and AI models on social networking sites. Specific implementation methods for this system are described below.

[0434] System configuration

[0435] The server registers an account for the generated AI model using the API of the social media platform. This account information is managed on the server side while ensuring appropriate security.

[0436] The user sends a direct message to the account of the generated AI model on a social networking site using their device, and the message is transmitted to the server via the social networking site platform.

[0437] The server receives messages sent by users in real time using the webhook function of the social media platform. The received messages are passed to an emotion analysis engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0438] The sentiment analysis engine can be implemented using external services such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the analysis results, the server makes a request to a generative AI model, such as OpenAI or other natural language generation models, to generate an emotionally relevant answer.

[0439] The server receives an appropriate response from the generative AI model, which is adjusted based on sentiment analysis data. For example, a message like "I'm very tired today" can be answered with "Thank you for your hard work. Please take a good rest today."

[0440] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0441] Specific examples

[0442] Consider a scenario where a user uses their smartphone to send a direct message saying, "I'm so tired today." This message is received by the server via a webhook, and the emotion analysis engine recognizes emotions like "fatigue" and "sadness."

[0443] Based on the analysis results, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0444] The generative AI model generates a response such as, "Thank you for your hard work. Please take a good rest today." This response is organized by the server and sent back to the user as a direct message.

[0445] Prompt Sentence Examples

[0446] Sample prompt 1: "The user says, 'I'm very tired today.' Please generate a comforting response to this message."

[0447] Sample prompt 2: "The user says, 'What's the latest news?' Please respond with a detailed description of the latest technology news."

[0448] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0449] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0450] Step 1:

[0451] The server registers a social media account. The server registers an account for the generated artificial intelligence model using the API of the social media platform. This operation saves the API key and secret on the server. The input is the authentication information provided by the API of the social media platform, and the output is the registered account information. For example, consider the case where the server creates a new bot account using the API of a specific social media platform.

[0452] Step 2:

[0453] A user sends a message. The user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the message typed by the user on the device, and the output is the message sent to the social networking site. For example, a user might send the message "I'm very tired today."

[0454] Step 3:

[0455] The server receives the message. The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is the notification from the SNS platform, and the output is the received message data. By configuring the webhook, the server is established to receive messages at a specific URL.

[0456] Step 4:

[0457] The server performs sentiment analysis. The server passes the message received via webhook to a sentiment analysis engine, which analyzes the emotions contained in the message. The input is the message data received via webhook, and the output is the sentiment analysis result. For example, the server sends the message "I'm very tired today" to the sentiment analysis engine, and the resulting emotion data is "fatigue" or "sadness."

[0458] Step 5:

[0459] The server makes a request to the generative AI model. Based on the results of the sentiment analysis engine, the server sends a prompt to the generative AI model to generate an answer that is in line with the emotion. The input is the sentiment analysis result, and the output is a prompt request to the generative AI model. For example, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0460] Step 6:

[0461] The generative AI model generates an answer. The generative AI model generates an appropriate answer based on the prompt it receives. The input is the prompt request to the generative AI model, and the output is the generated answer data. For example, the generative AI model generates the message, "Thank you for your hard work. Please take a good rest today."

[0462] Step 7:

[0463] The server sends a response to the user. The server organizes the response received from the generative AI model, formats it in a format that is easy for the user to understand, and sends it back to the user as a direct message. The input is the generated response data, and the output is a direct message to the user. For example, consider the case where the server sends a response to the user with the message, "Thank you for your hard work. Please take a good rest today."

[0464] The above are the specific processing steps of the system.

[0465] (Application example 2)

[0466] 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."

[0467] Traditional customer service in brick-and-mortar stores relies on the experience and knowledge of store staff, making it difficult to maintain consistent customer service quality. It is also difficult to provide responses that reflect the customer's emotions, making improving customer satisfaction a challenge. Furthermore, there is a lack of ways to utilize rapidly advancing information technology to streamline communication between customers and store staff. To solve these issues, a new system is needed that utilizes AI technology to provide customer service that is sensitive to their emotions.

[0468] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0469] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received message and detecting the user's emotion, means for generating a response using the generative AI model based on the detected emotion, means for returning the generated response to the user as a message, and means for displaying the generated response on a staff member's terminal and providing the response, thereby enabling the provision of consistent, high-quality customer service that is sensitive to the emotions of customers.

[0470] "SNS" is an abbreviation for social network service, an online platform where users can share information and content and communicate with each other.

[0471] A "generated artificial intelligence model" is an AI system designed and trained for a specific application or service, capable of generating appropriate responses or actions based on user input.

[0472] "Account" means authentication information that uniquely identifies and grants access to a specific user or system on an SNS.

[0473] "User" refers to an individual user of a social media platform, who performs actions such as sending and receiving messages.

[0474] A "direct message" is a private message sent only to a specific person on a social media platform.

[0475] "Means for detecting emotions" refers to algorithms or technologies that analyze the content of messages sent by users and identify the emotional elements contained therein (such as joy, sadness, or anger).

[0476] "Answer generation means" refers to an AI system or algorithm that creates and provides an appropriate response to the user based on the results of sentiment analysis.

[0477] A "terminal" is a hardware device for information processing and communication, and specifically includes smartphones and tablets.

[0478] "Staff" refers to employees working in physical stores who are responsible for providing products and services to customers.

[0479] This invention is a system that uses an account of an artificial intelligence model generated on a social networking site to realize two-way communication that is sensitive to the user's emotions. This system is mainly composed of a social networking site platform, an emotion analysis engine, a generative AI model, a smartphone, etc.

[0480] The server first registers an account for the AI ​​model created using the API of the social media platform. This account is managed in a secure environment. Users use their smartphones to send direct messages to the AI ​​model's account on the social media platform. For example, if a user sends a message saying, "Please tell me how to use this product," the message is transmitted to the server using the webhook function of the social media platform.

[0481] The server sends the received message to a sentiment analysis engine, which analyzes the user's emotions (e.g., confusion, curiosity) from the message's content. Specifically, sentiment analysis is performed using a natural language processing library such as TextBlob. Based on the results of this analysis, the server creates a prompt for the generative AI model to generate an appropriate response. The prompt might be in the format, for example, "Emotion: curiosity, Message: 'Please tell me how to use this product.'"

[0482] The generative AI model generates an appropriate response based on this prompt, such as "Please turn on this product first, then..." This response is then sent back to the server, which then sends it back to the user as a direct message.

[0483] Furthermore, the generated answer is also displayed on the smartphone of the store staff, who can use the answer to provide appropriate support to the user. In this way, the system enables consistent responses that are sensitive to the customer's emotions, contributing to improved customer satisfaction.

[0484] As a concrete example, if a user sends a direct message saying, "Please tell me how to use this product," the server uses an emotion analysis engine to detect the emotion "curiosity" and generates the prompt "Emotion: curiosity, Message: 'Please tell me how to use this product.'" Based on this prompt, the generative AI model generates an answer such as "First, turn on this product, then..." and displays this on the smartphones of the user and store staff. In this way, customer service in physical stores is enhanced.

[0485] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0486] Step 1:

[0487] The server registers the account of the generated AI model using the API of the social media platform. Specifically, it sends an API request to obtain account information. The obtained account information is then stored in a secure database. The input is the API request, and the output is the obtained account information.

[0488] Step 2:

[0489] A user uses a smartphone to send a message to the account of the generated AI model on a social networking site. For example, the user sends a message such as "Please tell me how to use this product." This message is transmitted to the server via the social networking site platform. The input is the user's message, and the output is the data sent to the server via the social networking site platform.

[0490] Step 3:

[0491] The server receives messages sent by users in real time using the webhook function of the SNS platform. These messages are sent to the server in JSON format, which the server interprets and passes to the sentiment analysis engine. The input is the user's message, and the output is the message data passed to the analysis engine.

[0492] Step 4:

[0493] The server sends the received message to a sentiment analysis engine, which analyzes the emotions contained in the message. Specifically, it uses a natural language processing library such as TextBlob to classify the emotion of the message into categories such as "curiosity" or "confusion." The input is the user's message, and the output is the analyzed emotional data.

[0494] Step 5:

[0495] The server creates a prompt for the generative AI model based on the analysis results. For example, it generates a prompt in the format "Emotion: curiosity, Message: 'Please tell me how to use this product.'" The input is the analyzed emotion data and the user's message, and the output is the generated prompt.

[0496] Step 6:

[0497] The server sends the generated prompt sentence to the generative AI model and requests it to generate an appropriate response. The generative AI model generates a response based on the prompt and returns it to the server. The input is the generated prompt sentence, and the output is the generated response.

[0498] Step 7:

[0499] The server receives the generated response, converts it into an appropriate format, and returns it to the user as a direct message. Specifically, it formats the response text. The input is the generated response, and the output is the direct message sent to the user.

[0500] Step 8:

[0501] The server simultaneously sends the generated response to the store staff's smartphone device. Based on this information, the staff can provide more detailed and accurate support to the user. The input is the generated response, and the output is the response displayed on the staff's device.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] [Third embodiment]

[0506] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0507] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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."

[0518] The present invention is a system that enables two-way communication by registering an account for an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses that are sent back to the user.

[0519] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0520] A user sends a direct message to the generated AI model's account on a social networking site using their device. For example, the user sends a message such as "What's the weather like today?" This message is transmitted to the server via the social networking site platform.

[0521] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are analyzed within the server and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message content.

[0522] The server receives an appropriate answer from the generated AI model, such as "It's sunny in Tokyo today." The server then organizes this answer, formats it in a way that's easy for the user to understand, and sends it back to the user as a direct message.

[0523] Users can get appropriate answers to their questions by receiving replies from the generative AI model. In addition, comments and questions on content posted by the generative AI model's account are also processed in the same way.

[0524] As a concrete example, if a user sends a direct message to a generative AI model's account saying, "Tell me the latest news," the server receives this and queries the generative AI model for information about news. The generative AI model generates a response containing appropriate news topics, and the server sends that response to the user. In this way, users can easily obtain the latest information.

[0525] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information that interests them.

[0526] This system enables efficient and natural communication between users and generative artificial intelligence models.

[0527] The processing flow will be explained below.

[0528] Step 1:

[0529] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0530] Step 2:

[0531] The user uses their device to send a direct message to the generative AI model's account on social media, asking a question such as, "What day is it today?"

[0532] Step 3:

[0533] The server receives direct messages sent by users using webhooks from the social networking platform, and obtains the sender ID and message content of the message.

[0534] Step 4:

[0535] The server analyzes the received message, extracts the necessary information, and prepares the message content appropriately to create a request to pass to the generative AI model.

[0536] Step 5:

[0537] The server sends a request to a generative AI model (e.g., OpenAI's GPT-3) asking it to generate an appropriate answer to the user's question.

[0538] Step 6:

[0539] The generative AI model receives requests from the server and generates a response based on the question, which is then returned to the server in text format.

[0540] Step 7:

[0541] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0542] Step 8:

[0543] The server then sends the prepared answer as a direct message to the user, so the user receives the answer to their question.

[0544] Step 9:

[0545] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0546] Step 10:

[0547] When a user replies to a post made by the generative AI model, the server receives the message again, analyzes it, and passes it to the generative AI model, which then generates a new response, which the server sends back to the user, thus realizing two-way communication.

[0548] Through the above steps, the system of the present invention realizes efficient and natural communication between the user and the generative AI model.

[0549] Example 1

[0550] 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."

[0551] To achieve natural, two-way communication between users and AI models on social media, it is necessary to receive messages in real time, analyze them appropriately, and quickly generate and reply to them. However, conventional systems have been inefficient in receiving and analyzing messages, resulting in delays in generating and replying to responses. Furthermore, there is a lack of a way to securely manage the account information of generated AI models.

[0552] 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.

[0553] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving direct messages sent by users to the account, means for analyzing the received messages and generating responses using the generative AI model, means for replying to the user with the generated responses as direct messages, means for securely managing account information of the generated AI model in a database, means for receiving messages in real time using a webhook function, means for analyzing the content of the messages and understanding their intent using analysis software, and means for sending requests to the generative AI model and receiving responses, thereby enabling the server to receive user messages in real time, analyze their content, and quickly generate and reply to appropriate responses.

[0554] An "artificial intelligence model" is an algorithm or system that uses natural language processing and machine learning techniques to generate appropriate answers or analytical results based on input data.

[0555] "Account" means an identifier and related information that individually identifies a user or system on a social networking platform.

[0556] "Direct Message" means a private message exchanged directly between specific users or accounts on a social media platform.

[0557] "Receiving" means the act of the server obtaining messages sent by users or other accounts from the SNS platform.

[0558] "Analysis" is the process of understanding the content of a received message and extracting its intent and meaning.

[0559] The "webhook function" is a function that sends notifications to a server when a specific event occurs, and is used to receive data in real time.

[0560] "Means for generating an answer" refers to the process of using an artificial intelligence model to create an appropriate answer for input data, as well as the system or technology for doing so.

[0561] "Reply" is the act of sending the generated answer to the user in response.

[0562] A "database" is a system for efficiently managing and storing account information, message data, etc.

[0563] "Analysis software" means programs or tools used to analyze the content of received messages.

[0564] "Submitting a request" is the process of making a specific request or query to an artificial intelligence model.

[0565] "Means for receiving a response" refers to the process and system for receiving answers or information to a request from an artificial intelligence model.

[0566] The present invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking service, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses and returning them to the users. Specific embodiments are described below.

[0567] The server first registers an account for the generated AI model using the API of the social media platform. This account information is stored and securely managed in a database. For example, a bot account is created using the Twitter API, authentication is performed using the API key and secret, and the account information is saved in the database.

[0568] The user uses a device to send a direct message to the generated AI model's account on a social networking site. The device can be a regular smartphone or tablet, and uses a dedicated application (e.g., the Twitter app) to access the social networking site. Specifically, the user opens the Twitter app on their smartphone and sends a message such as "What's the weather like today?" to the generated AI model's account.

[0569] The server uses the webhook function of the social media platform to receive messages sent by users in real time. For example, a Twitter webhook is set up to process the received messages in real time. The received messages are analyzed using analysis software (such as NLTK, a natural language processing library) to extract their intent and meaning. Based on the analysis results, a request is sent to a generative AI model (such as OpenAI's GPT-4) to generate an appropriate response.

[0570] The server receives appropriate answers from the generated AI model and organizes them. For example, when a user sends a message asking, "What's the weather like today?", the generated AI model generates an answer such as, "It's sunny in Tokyo today." The server then organizes this answer into a format that is easy for the user to understand and sends it back to the user as a direct message.

[0571] Users can get appropriate answers to their questions by receiving replies from the generative AI model. Furthermore, comments and questions on content posted by the generative AI model's account are also processed in the same manner. For example, if a user sends a direct message to the AI ​​model's account saying, "Tell me about the latest news," the server receives this and queries the generative AI model for information about the news. The generative AI model generates an answer containing appropriate news topics, and the server sends the answer to the user.

[0572] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information they are interested in.

[0573] This system enables efficient and natural communication between users and generative AI models.

[0574] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0575] Step 1:

[0576] The server uses the API of the social media platform to register the account of the generated artificial intelligence model. This account information is securely managed in a database. The input requires the API key and authentication information of the social media platform, and the generated account information is obtained as output. Specifically, the server creates a bot account using the Twitter API, authenticates using the API key and secret, and stores the account information in the database.

[0577] Step 2:

[0578] A user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the user's message (e.g., "What's the weather like today?"), and the output is the message sent to the social networking site. Specifically, the user opens the Twitter app on their smartphone, enters a message to the generative AI model's account, and clicks the send button.

[0579] Step 3:

[0580] The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is messages from the SNS platform, and the output is the received messages. Specifically, it sets up a Twitter WebHook and processes the received messages in real time.

[0581] Step 4:

[0582] The server analyzes the received message. This analysis extracts the intent and meaning of the message. The received message is the input, and the analysis results are the output. Specifically, the server analyzes the content of the message using analysis software (e.g., NLTK).

[0583] Step 5:

[0584] The server sends a request to the generative AI model based on the analysis results. The analysis results are the input, and the response from the generative AI model is the output. Specifically, it sends an API request to a generative AI model such as GPT-4 based on the analyzed content.

[0585] Step 6:

[0586] The server receives the appropriate answer from the generative AI model. The input is a response from the generative AI model, and the output is an appropriate answer. Specifically, it receives an answer such as "It's sunny in Tokyo today" from GPT-4.

[0587] Step 7:

[0588] The server organizes the received answers and formats them in a way that is easy for the user to understand. The input is the answer from the generative AI model, and the output is the formatted answer. Specifically, the server formats the answer and converts it into the SNS direct message format.

[0589] Step 8:

[0590] The server then returns the formatted response to the user as a direct message. The input is the formatted response, and the output is a reply to the user. Specifically, the server uses the Twitter API to send a direct message to the user.

[0591] This allows users to have natural, two-way communication with generative AI models in real time.

[0592] (Application example 1)

[0593] 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."

[0594] In conventional content distribution services, it is difficult for users to easily find movies and TV shows that suit their preferences, and there is a lack of systems that can recommend appropriate content, resulting in low user satisfaction.In addition, there is no established technology that can recommend appropriate content while enabling two-way communication through social networking services, so user convenience has not been sufficiently improved.

[0595] 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.

[0596] In this invention, the server includes means for registering an account of the generated AI model on the SNS, means for receiving direct messages sent by users to the account, means for analyzing the received message and generating a response using the generating AI model, means for returning the generated response to the user as a direct message, means for recommending content based on the user's message, and means for organizing the recommended content and providing it to the user, thereby enabling users to engage in two-way communication through the SNS and easily find content that suits their preferences.

[0597] "SNS" refers to social networking services, which are online platforms that allow users to exchange information and communicate with each other via the Internet.

[0598] An "artificial intelligence model" refers to a computer program that uses algorithms such as machine learning and deep learning to automatically perform pattern recognition, data analysis, and natural language understanding.

[0599] "Account Registration" refers to the process by which a user or system establishes and records the unique authentication information required to use a particular service.

[0600] "Direct messages" refer to private messages sent and received directly by users to each other on social media.

[0601] "Message analysis" is the process of understanding the content of a received message using natural language processing technology and extracting its intent and important information.

[0602] A "generative artificial intelligence model" refers to a system that uses artificial intelligence technologies such as large-scale language models to automatically generate responses to user inquiries and requests.

[0603] "Content recommendation" is the process of suggesting content such as movies, TV shows, and music that a user might like based on their interests and past behavior.

[0604] A "webhook" is a mechanism that sends an HTTP request to a pre-defined URL when a specific event occurs.

[0605] A system for realizing this invention includes a means for registering an account of a generated artificial intelligence model on a social networking site, a means for receiving direct messages sent by users to the account, a means for analyzing the received message and generating a response using the generated artificial intelligence model, a means for replying to the user with the generated response as a direct message, a means for recommending content based on the user's message, a means for organizing the recommended content and providing it to the user, and a means having a web hook for obtaining data on received user messages.

[0606] The server uses the API of the social media platform to register an account for the generated AI model. This account information is managed securely on the server side. The user uses their device to send a direct message to the generated AI model's account on the social media platform. For example, the user sends a message such as, "What recent sci-fi movies do you recommend?" This message is transmitted to the server via the social media platform.

[0607] The server uses the webhook function from the social media platform to receive messages sent by users in real time. The received messages are analyzed within the server, and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message's content. The server receives an appropriate answer from the generated artificial intelligence model. For example, the server can get an answer such as, "Recommended recent science fiction movies are 'Inception' and 'Interstellar'."

[0608] The server then organizes the answers, formats them in a way that is easy for the user to understand, and sends them back to the user as a direct message. By receiving a reply from the generative AI model, the user can get a proper answer to their question. Furthermore, based on the user's message, the AI ​​model can recommend related content.

[0609] For example, if a user sends a direct message asking, "What recent superhero movies do you recommend?", the server receives the message and queries the generative AI model for information about superhero movies. The generative AI model generates a response containing appropriate movie recommendations, and the server sends the response to the user. In this way, users can easily obtain recommended content in areas and genres that interest them.

[0610] Example prompt sentence:

[0611] User: Recommend movies based on "What are some recent superhero movies you recommend?"

[0612] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0613] Step 1:

[0614] A user sends a direct message to the generative AI model's account on a social networking site using a device. For example, the user might type a message like, "What recent sci-fi movies do you recommend?" The input data is the user's message, which is then sent to the server via the social networking site platform.

[0615] Step 2:

[0616] The server receives direct messages sent by users in real time using the webhook function of the SNS platform. The input data is the user's message from the SNS platform. The server extracts text data from the received message to analyze it.

[0617] Step 3:

[0618] The server analyzes the received message and generates a prompt to send a request to a generative AI model (e.g., a large-scale language model). The input data is the extracted text of the user message, and data processing and calculations are performed during the analysis and prompt generation process. The output data is the generated prompt.

[0619] Step 4:

[0620] The server sends a request to the generative AI model using the generated prompt. The input data is the generated prompt. The generative AI model generates an answer based on the prompt and returns it to the server. The output data is the answer text from the generative AI model.

[0621] Step 5:

[0622] The server receives the answer from the generative AI model and organizes it into a format that is easy for the user to understand. The input data is the answer text from the generative AI model, and the answer is organized through data processing and calculation. The output data is the organized answer text.

[0623] Step 6:

[0624] The server sends the organized answer back to the user as a direct message. The input data is the organized answer text, which is sent to the user via the SNS platform. The output data is the answer message displayed on the user's device.

[0625] Step 7:

[0626] Once the user receives the answer, they can then send a new direct message asking a related question, starting a feedback loop that allows the user to continually receive content recommendations via the generative AI model. The input data is the new user message, which is then sent back to the server.

[0627] 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.

[0628] This invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate replies to the users. This system is combined with an emotion engine that recognizes the user's emotions, adding a function that provides more natural and emotionally appropriate responses.

[0629] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0630] The user sends a direct message to the generative AI model's account on a social networking site using their device, such as "I'm very tired today." This message is then transmitted to the server via the social networking site.

[0631] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are passed to the emotion engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0632] Specifically, the emotion engine analyzes the message "I'm very tired today" and recognizes emotions such as fatigue and sadness. Based on this analysis, the server makes a request to the generative AI model, asking it to generate an answer appropriate to the emotion.

[0633] The server receives an appropriate answer from the generative AI model. For example, it might say, "Thank you for your hard work. Please take a good rest today." This answer is tailored based on the emotional data analyzed by the emotion engine.

[0634] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0635] If a user replies to a post by the generative AI model by saying, "I'd like to learn more about this topic," the process is similar. The server receives the message again, analyzes it, and passes it on to the generative AI model. The generative AI model generates a new response, which the server sends back to the user. This allows for natural, emotionally sensitive two-way communication.

[0636] As a concrete example, consider the case where a user sends a direct message saying, "Please tell me the latest news." The emotion engine analyzes this message as indicating the emotion of "curiosity." Based on this, the server instructs the generative AI model to generate detailed and interesting news information and provides the results to the user. For example, it might send a response to the user such as, "In the latest technology news, a next-generation smartphone has been announced. This technology is..."

[0637] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0638] The processing flow will be explained below.

[0639] Step 1:

[0640] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0641] Step 2:

[0642] The user uses the device to send a direct message to the generative AI model's account on social media, such as "I'm very tired today."

[0643] Step 3:

[0644] The server receives direct messages sent by users in real time using webhooks from the social media platform, and obtains the sender ID and message content of the message.

[0645] Step 4:

[0646] The server passes the received message to the emotion engine, which analyzes the emotions (e.g., joy, sadness, anger, etc.) contained in the message. Specifically, for a message like "I'm very tired today," it recognizes emotions such as fatigue and sadness.

[0647] Step 5:

[0648] Based on the analysis results of the emotion engine, the server creates an appropriate request to the generative AI model, which includes the user's message content and emotion data.

[0649] Step 6:

[0650] The server sends a request to the generative AI model, asking it to generate an emotionally relevant answer, for example, generating an appropriate response for the emotional data "I'm very tired today."

[0651] Step 7:

[0652] The generative AI model receives requests from the server and generates a response based on the question and emotion data, such as "Thank you for your hard work. Please take a good rest today."

[0653] Step 8:

[0654] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0655] Step 9:

[0656] The server then sends the prepared response as a direct message to the user, allowing the user to receive a response that is in tune with their emotions.

[0657] Step 10:

[0658] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0659] Step 11:

[0660] A similar process occurs when a user replies to a post made by the generative AI model. The server receives the message again, analyzes it through the emotion engine, and then asks the generative AI model to generate a response. This process ensures two-way communication in a natural and emotionally relevant way.

[0661] In this way, this system achieves efficient and natural communication between the user and the generative AI model that reflects emotions. As a specific example, if a user sends a direct message saying, "Please tell me the latest news," the emotion engine recognizes the emotion "curiosity." Based on this, the server has the generative AI model generate interesting news and provide that content to the user. In this way, it is possible to provide information that is in line with the user's emotions.

[0662] Example 2

[0663] 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."

[0664] In the past, it was difficult to realize natural, emotional interactions through automated responses in two-way communication on social networking sites. There was also a need for systems that could properly recognize users' emotions and provide responses based on those emotions. Furthermore, there was a need for systems that could respond in real time and provide detailed information.

[0665] 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.

[0666] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received messages and recognizing emotions using an emotion analysis engine, means for sending prompts to the generated AI model based on the emotion analysis results and generating an answer, and means for sending the generated answer back to the user as a message, thereby enabling natural and efficient two-way communication that is in line with emotions between the user and the AI ​​model.

[0667] "SNS" is an abbreviation for Social Networking Service, an online service that allows people to communicate over the Internet.

[0668] An "artificial intelligence model" is a computer program that can learn from data and make inferences and judgments like a human.

[0669] "Account" means the credentials and corresponding profile required for a particular User to access the Online Services.

[0670] A "message" is a short message or piece of information that a user sends to another user or system.

[0671] An "emotion analysis engine" is software or an algorithm that analyzes data such as text or voice and recognizes the emotions contained in that data.

[0672] A "prompt" is a text input that instructs an artificial intelligence model to respond or act in a particular way.

[0673] A "webhook" is a mechanism or technology for sending notifications to external systems when specific events occur.

[0674] This invention is a system for realizing natural and emotional two-way communication between users and AI models on social networking sites. Specific implementation methods for this system are described below.

[0675] System configuration

[0676] The server registers an account for the generated AI model using the API of the social media platform. This account information is managed on the server side while ensuring appropriate security.

[0677] The user sends a direct message to the account of the generated AI model on a social networking site using their device, and the message is transmitted to the server via the social networking site platform.

[0678] The server receives messages sent by users in real time using the webhook function of the social media platform. The received messages are passed to an emotion analysis engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0679] The sentiment analysis engine can be implemented using external services such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the analysis results, the server makes a request to a generative AI model, such as OpenAI or other natural language generation models, to generate an emotionally relevant answer.

[0680] The server receives an appropriate response from the generative AI model, which is adjusted based on sentiment analysis data. For example, a message like "I'm very tired today" can be answered with "Thank you for your hard work. Please take a good rest today."

[0681] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0682] Specific examples

[0683] Consider a scenario where a user uses their smartphone to send a direct message saying, "I'm so tired today." This message is received by the server via a webhook, and the emotion analysis engine recognizes emotions like "fatigue" and "sadness."

[0684] Based on the analysis results, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0685] The generative AI model generates a response such as, "Thank you for your hard work. Please take a good rest today." This response is organized by the server and sent back to the user as a direct message.

[0686] Prompt Sentence Examples

[0687] Sample prompt 1: "The user says, 'I'm very tired today.' Please generate a comforting response to this message."

[0688] Sample prompt 2: "The user says, 'What's the latest news?' Please respond with a detailed description of the latest technology news."

[0689] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0690] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0691] Step 1:

[0692] The server registers a social media account. The server registers an account for the generated artificial intelligence model using the API of the social media platform. This operation saves the API key and secret on the server. The input is the authentication information provided by the API of the social media platform, and the output is the registered account information. For example, consider the case where the server creates a new bot account using the API of a specific social media platform.

[0693] Step 2:

[0694] A user sends a message. The user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the message typed by the user on the device, and the output is the message sent to the social networking site. For example, a user might send the message "I'm very tired today."

[0695] Step 3:

[0696] The server receives the message. The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is the notification from the SNS platform, and the output is the received message data. By configuring the webhook, the server is established to receive messages at a specific URL.

[0697] Step 4:

[0698] The server performs sentiment analysis. The server passes the message received via webhook to a sentiment analysis engine, which analyzes the emotions contained in the message. The input is the message data received via webhook, and the output is the sentiment analysis result. For example, the server sends the message "I'm very tired today" to the sentiment analysis engine, and the resulting emotion data is "fatigue" or "sadness."

[0699] Step 5:

[0700] The server makes a request to the generative AI model. Based on the results of the sentiment analysis engine, the server sends a prompt to the generative AI model to generate an answer that is in line with the emotion. The input is the sentiment analysis result, and the output is a prompt request to the generative AI model. For example, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0701] Step 6:

[0702] The generative AI model generates an answer. The generative AI model generates an appropriate answer based on the prompt it receives. The input is the prompt request to the generative AI model, and the output is the generated answer data. For example, the generative AI model generates the message, "Thank you for your hard work. Please take a good rest today."

[0703] Step 7:

[0704] The server sends a response to the user. The server organizes the response received from the generative AI model, formats it in a format that is easy for the user to understand, and sends it back to the user as a direct message. The input is the generated response data, and the output is a direct message to the user. For example, consider the case where the server sends a response to the user with the message, "Thank you for your hard work. Please take a good rest today."

[0705] The above are the specific processing steps of the system.

[0706] (Application example 2)

[0707] 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."

[0708] Traditional customer service in brick-and-mortar stores relies on the experience and knowledge of store staff, making it difficult to maintain consistent customer service quality. It is also difficult to provide responses that reflect the customer's emotions, making improving customer satisfaction a challenge. Furthermore, there is a lack of ways to utilize rapidly advancing information technology to streamline communication between customers and store staff. To solve these issues, a new system is needed that utilizes AI technology to provide customer service that is sensitive to their emotions.

[0709] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0710] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received message and detecting the user's emotion, means for generating a response using the generative AI model based on the detected emotion, means for returning the generated response to the user as a message, and means for displaying the generated response on a staff member's terminal and providing the response, thereby enabling the provision of consistent, high-quality customer service that is sensitive to the emotions of customers.

[0711] "SNS" is an abbreviation for social network service, an online platform where users can share information and content and communicate with each other.

[0712] A "generated artificial intelligence model" is an AI system designed and trained for a specific application or service, capable of generating appropriate responses or actions based on user input.

[0713] "Account" means authentication information that uniquely identifies and grants access to a specific user or system on an SNS.

[0714] "User" refers to an individual user of a social media platform, who performs actions such as sending and receiving messages.

[0715] A "direct message" is a private message sent only to a specific person on a social media platform.

[0716] "Means for detecting emotions" refers to algorithms or technologies that analyze the content of messages sent by users and identify the emotional elements contained therein (such as joy, sadness, or anger).

[0717] "Answer generation means" refers to an AI system or algorithm that creates and provides an appropriate response to the user based on the results of sentiment analysis.

[0718] A "terminal" is a hardware device for information processing and communication, and specifically includes smartphones and tablets.

[0719] "Staff" refers to employees working in physical stores who are responsible for providing products and services to customers.

[0720] This invention is a system that uses an account of an artificial intelligence model generated on a social networking site to realize two-way communication that is sensitive to the user's emotions. This system is mainly composed of a social networking site platform, an emotion analysis engine, a generative AI model, a smartphone, etc.

[0721] The server first registers an account for the AI ​​model created using the API of the social media platform. This account is managed in a secure environment. Users use their smartphones to send direct messages to the AI ​​model's account on the social media platform. For example, if a user sends a message saying, "Please tell me how to use this product," the message is transmitted to the server using the webhook function of the social media platform.

[0722] The server sends the received message to a sentiment analysis engine, which analyzes the user's emotions (e.g., confusion, curiosity) from the message's content. Specifically, sentiment analysis is performed using a natural language processing library such as TextBlob. Based on the results of this analysis, the server creates a prompt for the generative AI model to generate an appropriate response. The prompt might be in the format, for example, "Emotion: curiosity, Message: 'Please tell me how to use this product.'"

[0723] The generative AI model generates an appropriate response based on this prompt, such as "Please turn on this product first, then..." This response is then sent back to the server, which then sends it back to the user as a direct message.

[0724] Furthermore, the generated answer is also displayed on the smartphone of the store staff, who can use the answer to provide appropriate support to the user. In this way, the system enables consistent responses that are sensitive to the customer's emotions, contributing to improved customer satisfaction.

[0725] As a concrete example, if a user sends a direct message saying, "Please tell me how to use this product," the server uses an emotion analysis engine to detect the emotion "curiosity" and generates the prompt "Emotion: curiosity, Message: 'Please tell me how to use this product.'" Based on this prompt, the generative AI model generates an answer such as "First, turn on this product, then..." and displays this on the smartphones of the user and store staff. In this way, customer service in physical stores is enhanced.

[0726] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0727] Step 1:

[0728] The server registers the account of the generated AI model using the API of the social media platform. Specifically, it sends an API request to obtain account information. The obtained account information is then stored in a secure database. The input is the API request, and the output is the obtained account information.

[0729] Step 2:

[0730] A user uses a smartphone to send a message to the account of the generated AI model on a social networking site. For example, the user sends a message such as "Please tell me how to use this product." This message is transmitted to the server via the social networking site platform. The input is the user's message, and the output is the data sent to the server via the social networking site platform.

[0731] Step 3:

[0732] The server receives messages sent by users in real time using the webhook function of the SNS platform. These messages are sent to the server in JSON format, which the server interprets and passes to the sentiment analysis engine. The input is the user's message, and the output is the message data passed to the analysis engine.

[0733] Step 4:

[0734] The server sends the received message to a sentiment analysis engine, which analyzes the emotions contained in the message. Specifically, it uses a natural language processing library such as TextBlob to classify the emotion of the message into categories such as "curiosity" or "confusion." The input is the user's message, and the output is the analyzed emotional data.

[0735] Step 5:

[0736] The server creates a prompt for the generative AI model based on the analysis results. For example, it generates a prompt in the format "Emotion: curiosity, Message: 'Please tell me how to use this product.'" The input is the analyzed emotion data and the user's message, and the output is the generated prompt.

[0737] Step 6:

[0738] The server sends the generated prompt sentence to the generative AI model and requests it to generate an appropriate response. The generative AI model generates a response based on the prompt and returns it to the server. The input is the generated prompt sentence, and the output is the generated response.

[0739] Step 7:

[0740] The server receives the generated response, converts it into an appropriate format, and returns it to the user as a direct message. Specifically, it formats the response text. The input is the generated response, and the output is the direct message sent to the user.

[0741] Step 8:

[0742] The server simultaneously sends the generated response to the store staff's smartphone device. Based on this information, the staff can provide more detailed and accurate support to the user. The input is the generated response, and the output is the response displayed on the staff's device.

[0743] 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.

[0744] 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.

[0745] 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.

[0746] [Fourth embodiment]

[0747] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0748] 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.

[0749] 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).

[0750] 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.

[0751] 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.

[0752] 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).

[0753] 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.

[0754] 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.

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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."

[0760] The present invention is a system that enables two-way communication by registering an account for an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses that are sent back to the user.

[0761] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0762] A user sends a direct message to the generated AI model's account on a social networking site using their device. For example, the user sends a message such as "What's the weather like today?" This message is transmitted to the server via the social networking site platform.

[0763] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are analyzed within the server and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message content.

[0764] The server receives an appropriate answer from the generated AI model, such as "It's sunny in Tokyo today." The server then organizes this answer, formats it in a way that's easy for the user to understand, and sends it back to the user as a direct message.

[0765] Users can get appropriate answers to their questions by receiving replies from the generative AI model. In addition, comments and questions on content posted by the generative AI model's account are also processed in the same way.

[0766] As a concrete example, if a user sends a direct message to a generative AI model's account saying, "Tell me the latest news," the server receives this and queries the generative AI model for information about news. The generative AI model generates a response containing appropriate news topics, and the server sends that response to the user. In this way, users can easily obtain the latest information.

[0767] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information that interests them.

[0768] This system enables efficient and natural communication between users and generative artificial intelligence models.

[0769] The processing flow will be explained below.

[0770] Step 1:

[0771] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0772] Step 2:

[0773] The user uses their device to send a direct message to the generative AI model's account on social media, asking a question such as, "What day is it today?"

[0774] Step 3:

[0775] The server receives direct messages sent by users using webhooks from the social networking platform, and obtains the sender ID and message content of the message.

[0776] Step 4:

[0777] The server analyzes the received message, extracts the necessary information, and prepares the message content appropriately to create a request to pass to the generative AI model.

[0778] Step 5:

[0779] The server sends a request to a generative AI model (e.g., OpenAI's GPT-3) asking it to generate an appropriate answer to the user's question.

[0780] Step 6:

[0781] The generative AI model receives requests from the server and generates a response based on the question, which is then returned to the server in text format.

[0782] Step 7:

[0783] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0784] Step 8:

[0785] The server then sends the prepared answer as a direct message to the user, so the user receives the answer to their question.

[0786] Step 9:

[0787] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0788] Step 10:

[0789] When a user replies to a post made by the generative AI model, the server receives the message again, analyzes it, and passes it to the generative AI model, which then generates a new response, which the server sends back to the user, thus realizing two-way communication.

[0790] Through the above steps, the system of the present invention realizes efficient and natural communication between the user and the generative AI model.

[0791] Example 1

[0792] 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."

[0793] To achieve natural, two-way communication between users and AI models on social media, it is necessary to receive messages in real time, analyze them appropriately, and quickly generate and reply to them. However, conventional systems have been inefficient in receiving and analyzing messages, resulting in delays in generating and replying to responses. Furthermore, there is a lack of a way to securely manage the account information of generated AI models.

[0794] 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.

[0795] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving direct messages sent by users to the account, means for analyzing the received messages and generating responses using the generative AI model, means for replying to the user with the generated responses as direct messages, means for securely managing account information of the generated AI model in a database, means for receiving messages in real time using a webhook function, means for analyzing the content of the messages and understanding their intent using analysis software, and means for sending requests to the generative AI model and receiving responses, thereby enabling the server to receive user messages in real time, analyze their content, and quickly generate and reply to appropriate responses.

[0796] An "artificial intelligence model" is an algorithm or system that uses natural language processing and machine learning techniques to generate appropriate answers or analytical results based on input data.

[0797] "Account" means an identifier and related information that individually identifies a user or system on a social networking platform.

[0798] "Direct Message" means a private message exchanged directly between specific users or accounts on a social media platform.

[0799] "Receiving" means the act of the server obtaining messages sent by users or other accounts from the SNS platform.

[0800] "Analysis" is the process of understanding the content of a received message and extracting its intent and meaning.

[0801] The "webhook function" is a function that sends notifications to a server when a specific event occurs, and is used to receive data in real time.

[0802] "Means for generating an answer" refers to the process of using an artificial intelligence model to create an appropriate answer for input data, as well as the system or technology for doing so.

[0803] "Reply" is the act of sending the generated answer to the user in response.

[0804] A "database" is a system for efficiently managing and storing account information, message data, etc.

[0805] "Analysis software" means programs or tools used to analyze the content of received messages.

[0806] "Submitting a request" is the process of making a specific request or query to an artificial intelligence model.

[0807] "Means for receiving a response" refers to the process and system for receiving answers or information to a request from an artificial intelligence model.

[0808] The present invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking service, receiving and analyzing direct messages sent by users to that account, and generating appropriate responses and returning them to the users. Specific embodiments are described below.

[0809] The server first registers an account for the generated AI model using the API of the social media platform. This account information is stored and securely managed in a database. For example, a bot account is created using the Twitter API, authentication is performed using the API key and secret, and the account information is saved in the database.

[0810] The user uses a device to send a direct message to the generated AI model's account on a social networking site. The device can be a regular smartphone or tablet, and uses a dedicated application (e.g., the Twitter app) to access the social networking site. Specifically, the user opens the Twitter app on their smartphone and sends a message such as "What's the weather like today?" to the generated AI model's account.

[0811] The server uses the webhook function of the social media platform to receive messages sent by users in real time. For example, a Twitter webhook is set up to process the received messages in real time. The received messages are analyzed using analysis software (such as NLTK, a natural language processing library) to extract their intent and meaning. Based on the analysis results, a request is sent to a generative AI model (such as OpenAI's GPT-4) to generate an appropriate response.

[0812] The server receives appropriate answers from the generated AI model and organizes them. For example, when a user sends a message asking, "What's the weather like today?", the generated AI model generates an answer such as, "It's sunny in Tokyo today." The server then organizes this answer into a format that is easy for the user to understand and sends it back to the user as a direct message.

[0813] Users can get appropriate answers to their questions by receiving replies from the generative AI model. Furthermore, comments and questions on content posted by the generative AI model's account are also processed in the same manner. For example, if a user sends a direct message to the AI ​​model's account saying, "Tell me about the latest news," the server receives this and queries the generative AI model for information about the news. The generative AI model generates an answer containing appropriate news topics, and the server sends the answer to the user.

[0814] In addition, if a user replies to a post by the generative AI model by saying, "I want to know more about this topic," the server receives the message and uses the generative AI model again to generate more detailed information and provide it to the user, allowing the user to learn more about the information they are interested in.

[0815] This system enables efficient and natural communication between users and generative AI models.

[0816] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0817] Step 1:

[0818] The server uses the API of the social media platform to register the account of the generated artificial intelligence model. This account information is securely managed in a database. The input requires the API key and authentication information of the social media platform, and the generated account information is obtained as output. Specifically, the server creates a bot account using the Twitter API, authenticates using the API key and secret, and stores the account information in the database.

[0819] Step 2:

[0820] A user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the user's message (e.g., "What's the weather like today?"), and the output is the message sent to the social networking site. Specifically, the user opens the Twitter app on their smartphone, enters a message to the generative AI model's account, and clicks the send button.

[0821] Step 3:

[0822] The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is messages from the SNS platform, and the output is the received messages. Specifically, it sets up a Twitter WebHook and processes the received messages in real time.

[0823] Step 4:

[0824] The server analyzes the received message. This analysis extracts the intent and meaning of the message. The received message is the input, and the analysis results are the output. Specifically, the server analyzes the content of the message using analysis software (e.g., NLTK).

[0825] Step 5:

[0826] The server sends a request to the generative AI model based on the analysis results. The analysis results are the input, and the response from the generative AI model is the output. Specifically, it sends an API request to a generative AI model such as GPT-4 based on the analyzed content.

[0827] Step 6:

[0828] The server receives the appropriate answer from the generative AI model. The input is a response from the generative AI model, and the output is an appropriate answer. Specifically, it receives an answer such as "It's sunny in Tokyo today" from GPT-4.

[0829] Step 7:

[0830] The server organizes the received answers and formats them in a way that is easy for the user to understand. The input is the answer from the generative AI model, and the output is the formatted answer. Specifically, the server formats the answer and converts it into the SNS direct message format.

[0831] Step 8:

[0832] The server then returns the formatted response to the user as a direct message. The input is the formatted response, and the output is a reply to the user. Specifically, the server uses the Twitter API to send a direct message to the user.

[0833] This allows users to have natural, two-way communication with generative AI models in real time.

[0834] (Application example 1)

[0835] 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."

[0836] In conventional content distribution services, it is difficult for users to easily find movies and TV shows that suit their preferences, and there is a lack of systems that can recommend appropriate content, resulting in low user satisfaction.In addition, there is no established technology that can recommend appropriate content while enabling two-way communication through social networking services, so user convenience has not been sufficiently improved.

[0837] 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.

[0838] In this invention, the server includes means for registering an account of the generated AI model on the SNS, means for receiving direct messages sent by users to the account, means for analyzing the received message and generating a response using the generating AI model, means for returning the generated response to the user as a direct message, means for recommending content based on the user's message, and means for organizing the recommended content and providing it to the user, thereby enabling users to engage in two-way communication through the SNS and easily find content that suits their preferences.

[0839] "SNS" refers to social networking services, which are online platforms that allow users to exchange information and communicate with each other via the Internet.

[0840] An "artificial intelligence model" refers to a computer program that uses algorithms such as machine learning and deep learning to automatically perform pattern recognition, data analysis, and natural language understanding.

[0841] "Account Registration" refers to the process by which a user or system establishes and records the unique authentication information required to use a particular service.

[0842] "Direct messages" refer to private messages sent and received directly by users to each other on social media.

[0843] "Message analysis" is the process of understanding the content of a received message using natural language processing technology and extracting its intent and important information.

[0844] A "generative artificial intelligence model" refers to a system that uses artificial intelligence technologies such as large-scale language models to automatically generate responses to user inquiries and requests.

[0845] "Content recommendation" is the process of suggesting content such as movies, TV shows, and music that a user might like based on their interests and past behavior.

[0846] A "webhook" is a mechanism that sends an HTTP request to a pre-defined URL when a specific event occurs.

[0847] A system for realizing this invention includes a means for registering an account of a generated artificial intelligence model on a social networking site, a means for receiving direct messages sent by users to the account, a means for analyzing the received message and generating a response using the generated artificial intelligence model, a means for replying to the user with the generated response as a direct message, a means for recommending content based on the user's message, a means for organizing the recommended content and providing it to the user, and a means having a web hook for obtaining data on received user messages.

[0848] The server uses the API of the social media platform to register an account for the generated AI model. This account information is managed securely on the server side. The user uses their device to send a direct message to the generated AI model's account on the social media platform. For example, the user sends a message such as, "What recent sci-fi movies do you recommend?" This message is transmitted to the server via the social media platform.

[0849] The server uses the webhook function from the social media platform to receive messages sent by users in real time. The received messages are analyzed within the server, and a request is sent to an artificial intelligence model (e.g., a large-scale language model) created based on the message's content. The server receives an appropriate answer from the generated artificial intelligence model. For example, the server can get an answer such as, "Recommended recent science fiction movies are 'Inception' and 'Interstellar'."

[0850] The server then organizes the answers, formats them in a way that is easy for the user to understand, and sends them back to the user as a direct message. By receiving a reply from the generative AI model, the user can get a proper answer to their question. Furthermore, based on the user's message, the AI ​​model can recommend related content.

[0851] For example, if a user sends a direct message asking, "What recent superhero movies do you recommend?", the server receives the message and queries the generative AI model for information about superhero movies. The generative AI model generates a response containing appropriate movie recommendations, and the server sends the response to the user. In this way, users can easily obtain recommended content in areas and genres that interest them.

[0852] Example prompt sentence:

[0853] User: Recommend movies based on "What are some recent superhero movies you recommend?"

[0854] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0855] Step 1:

[0856] A user sends a direct message to the generative AI model's account on a social networking site using a device. For example, the user might type a message like, "What recent sci-fi movies do you recommend?" The input data is the user's message, which is then sent to the server via the social networking site platform.

[0857] Step 2:

[0858] The server receives direct messages sent by users in real time using the webhook function of the SNS platform. The input data is the user's message from the SNS platform. The server extracts text data from the received message to analyze it.

[0859] Step 3:

[0860] The server analyzes the received message and generates a prompt to send a request to a generative AI model (e.g., a large-scale language model). The input data is the extracted text of the user message, and data processing and calculations are performed during the analysis and prompt generation process. The output data is the generated prompt.

[0861] Step 4:

[0862] The server sends a request to the generative AI model using the generated prompt. The input data is the generated prompt. The generative AI model generates an answer based on the prompt and returns it to the server. The output data is the answer text from the generative AI model.

[0863] Step 5:

[0864] The server receives the answer from the generative AI model and organizes it into a format that is easy for the user to understand. The input data is the answer text from the generative AI model, and the answer is organized through data processing and calculation. The output data is the organized answer text.

[0865] Step 6:

[0866] The server sends the organized answer back to the user as a direct message. The input data is the organized answer text, which is sent to the user via the SNS platform. The output data is the answer message displayed on the user's device.

[0867] Step 7:

[0868] Once the user receives the answer, they can then send a new direct message asking a related question, starting a feedback loop that allows the user to continually receive content recommendations via the generative AI model. The input data is the new user message, which is then sent back to the server.

[0869] 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.

[0870] This invention is a system that enables two-way communication by registering an account of an artificial intelligence model generated on a social networking site, receiving and analyzing direct messages sent by users to that account, and generating appropriate replies to the users. This system is combined with an emotion engine that recognizes the user's emotions, adding a function that provides more natural and emotionally appropriate responses.

[0871] The server first registers an account for the AI ​​model generated using the API of the social media platform. This account information is managed securely on the server side.

[0872] The user sends a direct message to the generative AI model's account on a social networking site using their device, such as "I'm very tired today." This message is then transmitted to the server via the social networking site.

[0873] The server uses the webhook function of the social networking platform to receive messages sent by users in real time. The received messages are passed to the emotion engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0874] Specifically, the emotion engine analyzes the message "I'm very tired today" and recognizes emotions such as fatigue and sadness. Based on this analysis, the server makes a request to the generative AI model, asking it to generate an answer appropriate to the emotion.

[0875] The server receives an appropriate answer from the generative AI model. For example, it might say, "Thank you for your hard work. Please take a good rest today." This answer is tailored based on the emotional data analyzed by the emotion engine.

[0876] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0877] If a user replies to a post by the generative AI model by saying, "I'd like to learn more about this topic," the process is similar. The server receives the message again, analyzes it, and passes it on to the generative AI model. The generative AI model generates a new response, which the server sends back to the user. This allows for natural, emotionally sensitive two-way communication.

[0878] As a concrete example, consider the case where a user sends a direct message saying, "Please tell me the latest news." The emotion engine analyzes this message as indicating the emotion of "curiosity." Based on this, the server instructs the generative AI model to generate detailed and interesting news information and provides the results to the user. For example, it might send a response to the user such as, "In the latest technology news, a next-generation smartphone has been announced. This technology is..."

[0879] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0880] The processing flow will be explained below.

[0881] Step 1:

[0882] The server registers the account of the generated AI model using the API of the social media platform, and obtains and securely stores necessary authentication information such as a login authentication token and access key.

[0883] Step 2:

[0884] The user uses the device to send a direct message to the generative AI model's account on social media, such as "I'm very tired today."

[0885] Step 3:

[0886] The server receives direct messages sent by users in real time using webhooks from the social media platform, and obtains the sender ID and message content of the message.

[0887] Step 4:

[0888] The server passes the received message to the emotion engine, which analyzes the emotions (e.g., joy, sadness, anger, etc.) contained in the message. Specifically, for a message like "I'm very tired today," it recognizes emotions such as fatigue and sadness.

[0889] Step 5:

[0890] Based on the analysis results of the emotion engine, the server creates an appropriate request to the generative AI model, which includes the user's message content and emotion data.

[0891] Step 6:

[0892] The server sends a request to the generative AI model, asking it to generate an emotionally relevant answer, for example, generating an appropriate response for the emotional data "I'm very tired today."

[0893] Step 7:

[0894] The generative AI model receives requests from the server and generates a response based on the question and emotion data, such as "Thank you for your hard work. Please take a good rest today."

[0895] Step 8:

[0896] The server analyzes the answers received from the generative AI model and organizes them into a format that is easy for users to understand.

[0897] Step 9:

[0898] The server then sends the prepared response as a direct message to the user, allowing the user to receive a response that is in tune with their emotions.

[0899] Step 10:

[0900] Users receive answers from the generative AI model via direct message, and can send further questions or replies if desired.

[0901] Step 11:

[0902] A similar process occurs when a user replies to a post made by the generative AI model. The server receives the message again, analyzes it through the emotion engine, and then asks the generative AI model to generate a response. This process ensures two-way communication in a natural and emotionally relevant way.

[0903] In this way, this system achieves efficient and natural communication between the user and the generative AI model that reflects emotions. As a specific example, if a user sends a direct message saying, "Please tell me the latest news," the emotion engine recognizes the emotion "curiosity." Based on this, the server has the generative AI model generate interesting news and provide that content to the user. In this way, it is possible to provide information that is in line with the user's emotions.

[0904] Example 2

[0905] 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."

[0906] In the past, it was difficult to realize natural, emotional interactions through automated responses in two-way communication on social networking sites. There was also a need for systems that could properly recognize users' emotions and provide responses based on those emotions. Furthermore, there was a need for systems that could respond in real time and provide detailed information.

[0907] 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.

[0908] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received messages and recognizing emotions using an emotion analysis engine, means for sending prompts to the generated AI model based on the emotion analysis results and generating an answer, and means for sending the generated answer back to the user as a message, thereby enabling natural and efficient two-way communication that is in line with emotions between the user and the AI ​​model.

[0909] "SNS" is an abbreviation for Social Networking Service, an online service that allows people to communicate over the Internet.

[0910] An "artificial intelligence model" is a computer program that can learn from data and make inferences and judgments like a human.

[0911] "Account" means the credentials and corresponding profile required for a particular User to access the Online Services.

[0912] A "message" is a short message or piece of information that a user sends to another user or system.

[0913] An "emotion analysis engine" is software or an algorithm that analyzes data such as text or voice and recognizes the emotions contained in that data.

[0914] A "prompt" is a text input that instructs an artificial intelligence model to respond or act in a particular way.

[0915] A "webhook" is a mechanism or technology for sending notifications to external systems when specific events occur.

[0916] This invention is a system for realizing natural and emotional two-way communication between users and AI models on social networking sites. Specific implementation methods for this system are described below.

[0917] System configuration

[0918] The server registers an account for the generated AI model using the API of the social media platform. This account information is managed on the server side while ensuring appropriate security.

[0919] The user sends a direct message to the account of the generated AI model on a social networking site using their device, and the message is transmitted to the server via the social networking site platform.

[0920] The server receives messages sent by users in real time using the webhook function of the social media platform. The received messages are passed to an emotion analysis engine, which analyzes the emotions contained in the messages (e.g., joy, sadness, anger, etc.).

[0921] The sentiment analysis engine can be implemented using external services such as Google Cloud Natural Language API or IBM Watson Natural Language Understanding. Based on the analysis results, the server makes a request to a generative AI model, such as OpenAI or other natural language generation models, to generate an emotionally relevant answer.

[0922] The server receives an appropriate response from the generative AI model, which is adjusted based on sentiment analysis data. For example, a message like "I'm very tired today" can be answered with "Thank you for your hard work. Please take a good rest today."

[0923] The server then organizes the responses, formats them in a user-friendly format, and sends them back to the user as a direct message, ensuring the user receives a response that is relevant to their feelings.

[0924] Specific examples

[0925] Consider a scenario where a user uses their smartphone to send a direct message saying, "I'm so tired today." This message is received by the server via a webhook, and the emotion analysis engine recognizes emotions like "fatigue" and "sadness."

[0926] Based on the analysis results, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0927] The generative AI model generates a response such as, "Thank you for your hard work. Please take a good rest today." This response is organized by the server and sent back to the user as a direct message.

[0928] Prompt Sentence Examples

[0929] Sample prompt 1: "The user says, 'I'm very tired today.' Please generate a comforting response to this message."

[0930] Sample prompt 2: "The user says, 'What's the latest news?' Please respond with a detailed description of the latest technology news."

[0931] This system enables efficient, emotionally-driven, and natural communication between users and generative AI models.

[0932] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0933] Step 1:

[0934] The server registers a social media account. The server registers an account for the generated artificial intelligence model using the API of the social media platform. This operation saves the API key and secret on the server. The input is the authentication information provided by the API of the social media platform, and the output is the registered account information. For example, consider the case where the server creates a new bot account using the API of a specific social media platform.

[0935] Step 2:

[0936] A user sends a message. The user uses a device to send a direct message to the generative AI model's account on a social networking site. The input is the message typed by the user on the device, and the output is the message sent to the social networking site. For example, a user might send the message "I'm very tired today."

[0937] Step 3:

[0938] The server receives the message. The server uses the webhook function of the SNS platform to receive messages sent by users in real time. The input is the notification from the SNS platform, and the output is the received message data. By configuring the webhook, the server is established to receive messages at a specific URL.

[0939] Step 4:

[0940] The server performs sentiment analysis. The server passes the message received via webhook to a sentiment analysis engine, which analyzes the emotions contained in the message. The input is the message data received via webhook, and the output is the sentiment analysis result. For example, the server sends the message "I'm very tired today" to the sentiment analysis engine, and the resulting emotion data is "fatigue" or "sadness."

[0941] Step 5:

[0942] The server makes a request to the generative AI model. Based on the results of the sentiment analysis engine, the server sends a prompt to the generative AI model to generate an answer that is in line with the emotion. The input is the sentiment analysis result, and the output is a prompt request to the generative AI model. For example, the server sends a prompt to the generative AI model saying, "The user says, 'I'm very tired today.' Please generate comforting words in response to this message."

[0943] Step 6:

[0944] The generative AI model generates an answer. The generative AI model generates an appropriate answer based on the prompt it receives. The input is the prompt request to the generative AI model, and the output is the generated answer data. For example, the generative AI model generates the message, "Thank you for your hard work. Please take a good rest today."

[0945] Step 7:

[0946] The server sends a response to the user. The server organizes the response received from the generative AI model, formats it in a format that is easy for the user to understand, and sends it back to the user as a direct message. The input is the generated response data, and the output is a direct message to the user. For example, consider the case where the server sends a response to the user with the message, "Thank you for your hard work. Please take a good rest today."

[0947] The above are the specific processing steps of the system.

[0948] (Application example 2)

[0949] 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."

[0950] Traditional customer service in brick-and-mortar stores relies on the experience and knowledge of store staff, making it difficult to maintain consistent customer service quality. It is also difficult to provide responses that reflect the customer's emotions, making improving customer satisfaction a challenge. Furthermore, there is a lack of ways to utilize rapidly advancing information technology to streamline communication between customers and store staff. To solve these issues, a new system is needed that utilizes AI technology to provide customer service that is sensitive to their emotions.

[0951] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0952] In this invention, the server includes means for registering an account of the generated AI model on an SNS, means for receiving messages sent by users to the account, means for analyzing the received message and detecting the user's emotion, means for generating a response using the generative AI model based on the detected emotion, means for returning the generated response to the user as a message, and means for displaying the generated response on a staff member's terminal and providing the response, thereby enabling the provision of consistent, high-quality customer service that is sensitive to the emotions of customers.

[0953] "SNS" is an abbreviation for social network service, an online platform where users can share information and content and communicate with each other.

[0954] A "generated artificial intelligence model" is an AI system designed and trained for a specific application or service, capable of generating appropriate responses or actions based on user input.

[0955] "Account" means authentication information that uniquely identifies and grants access to a specific user or system on an SNS.

[0956] "User" refers to an individual user of a social media platform, who performs actions such as sending and receiving messages.

[0957] A "direct message" is a private message sent only to a specific person on a social media platform.

[0958] "Means for detecting emotions" refers to algorithms or technologies that analyze the content of messages sent by users and identify the emotional elements contained therein (such as joy, sadness, or anger).

[0959] "Answer generation means" refers to an AI system or algorithm that creates and provides an appropriate response to the user based on the results of sentiment analysis.

[0960] A "terminal" is a hardware device for information processing and communication, and specifically includes smartphones and tablets.

[0961] "Staff" refers to employees working in physical stores who are responsible for providing products and services to customers.

[0962] This invention is a system that uses an account of an artificial intelligence model generated on a social networking site to realize two-way communication that is sensitive to the user's emotions. This system is mainly composed of a social networking site platform, an emotion analysis engine, a generative AI model, a smartphone, etc.

[0963] The server first registers an account for the AI ​​model created using the API of the social media platform. This account is managed in a secure environment. Users use their smartphones to send direct messages to the AI ​​model's account on the social media platform. For example, if a user sends a message saying, "Please tell me how to use this product," the message is transmitted to the server using the webhook function of the social media platform.

[0964] The server sends the received message to a sentiment analysis engine, which analyzes the user's emotions (e.g., confusion, curiosity) from the message's content. Specifically, sentiment analysis is performed using a natural language processing library such as TextBlob. Based on the results of this analysis, the server creates a prompt for the generative AI model to generate an appropriate response. The prompt might be in the format, for example, "Emotion: curiosity, Message: 'Please tell me how to use this product.'"

[0965] The generative AI model generates an appropriate response based on this prompt, such as "Please turn on this product first, then..." This response is then sent back to the server, which then sends it back to the user as a direct message.

[0966] Furthermore, the generated answer is also displayed on the smartphone of the store staff, who can use the answer to provide appropriate support to the user. In this way, the system enables consistent responses that are sensitive to the customer's emotions, contributing to improved customer satisfaction.

[0967] As a concrete example, if a user sends a direct message saying, "Please tell me how to use this product," the server uses an emotion analysis engine to detect the emotion "curiosity" and generates the prompt "Emotion: curiosity, Message: 'Please tell me how to use this product.'" Based on this prompt, the generative AI model generates an answer such as "First, turn on this product, then..." and displays this on the smartphones of the user and store staff. In this way, customer service in physical stores is enhanced.

[0968] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0969] Step 1:

[0970] The server registers the account of the generated AI model using the API of the social media platform. Specifically, it sends an API request to obtain account information. The obtained account information is then stored in a secure database. The input is the API request, and the output is the obtained account information.

[0971] Step 2:

[0972] A user uses a smartphone to send a message to the account of the generated AI model on a social networking site. For example, the user sends a message such as "Please tell me how to use this product." This message is transmitted to the server via the social networking site platform. The input is the user's message, and the output is the data sent to the server via the social networking site platform.

[0973] Step 3:

[0974] The server receives messages sent by users in real time using the webhook function of the SNS platform. These messages are sent to the server in JSON format, which the server interprets and passes to the sentiment analysis engine. The input is the user's message, and the output is the message data passed to the analysis engine.

[0975] Step 4:

[0976] The server sends the received message to a sentiment analysis engine, which analyzes the emotions contained in the message. Specifically, it uses a natural language processing library such as TextBlob to classify the emotion of the message into categories such as "curiosity" or "confusion." The input is the user's message, and the output is the analyzed emotional data.

[0977] Step 5:

[0978] The server creates a prompt for the generative AI model based on the analysis results. For example, it generates a prompt in the format "Emotion: curiosity, Message: 'Please tell me how to use this product.'" The input is the analyzed emotion data and the user's message, and the output is the generated prompt.

[0979] Step 6:

[0980] The server sends the generated prompt sentence to the generative AI model and requests it to generate an appropriate response. The generative AI model generates a response based on the prompt and returns it to the server. The input is the generated prompt sentence, and the output is the generated response.

[0981] Step 7:

[0982] The server receives the generated response, converts it into an appropriate format, and returns it to the user as a direct message. Specifically, it formats the response text. The input is the generated response, and the output is the direct message sent to the user.

[0983] Step 8:

[0984] The server simultaneously sends the generated response to the store staff's smartphone device. Based on this information, the staff can provide more detailed and accurate support to the user. The input is the generated response, and the output is the response displayed on the staff's device.

[0985] 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.

[0986] 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.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] 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).

[0992] 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.

[0993] 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."

[0994] 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.

[0995] 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).

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] 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.

[1003] 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.

[1004] 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.

[1005] 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.

[1006] The following is further disclosed regarding the above embodiment.

[1007] (Claim 1)

[1008] A means of registering an account for the generated AI model on SNS;

[1009] A means for receiving direct messages sent by users to the account;

[1010] means for analyzing the received message and generating a response using a generative artificial intelligence model;

[1011] The system includes means for returning the generated answer to the user as a direct message.

[1012] (Claim 2)

[1013] The system of claim 1 further includes means for a user to reply to a post on the account of the generative artificial intelligence model, analyzing the reply message to the post, and again generating an answer using the generative artificial intelligence model, and means for replying to the generated answer to the user.

[1014] (Claim 3)

[1015] 10. The system of claim 1, further comprising means for providing a webhook for obtaining data of received user messages.

[1016] "Example 1"

[1017] (Claim 1)

[1018] A means of registering an account for the generated AI model on SNS;

[1019] A means for receiving direct messages sent by users to the account;

[1020] means for analyzing the received message and generating a response using a generative artificial intelligence model;

[1021] means for returning the generated answer to the user as a direct message;

[1022] A means for safely managing account information of the generated artificial intelligence model in a database;

[1023] A means to receive messages in real time using the webhook function,

[1024] A means of analyzing the content of the message using analytical software to understand its intent;

[1025] A system including means for sending requests to a generative artificial intelligence model and receiving responses.

[1026] (Claim 2)

[1027] The system of claim 1 further includes means for a user to reply to a post on the account of the generative artificial intelligence model, analyzing the reply message to the post, and again generating an answer using the generative artificial intelligence model, and means for replying to the generated answer to the user.

[1028] (Claim 3)

[1029] 10. The system of claim 1, further comprising means for providing a webhook for obtaining data of received user messages.

[1030] "Application Example 1"

[1031] (Claim 1)

[1032] A means of registering an account for the generated AI model on SNS;

[1033] A means for receiving direct messages sent by users to the account;

[1034] means for analyzing the received message and generating a response using a generative artificial intelligence model;

[1035] means for returning the generated answer to the user as a direct message;

[1036] A means of recommending content based on user messages;

[1037] The system includes a means for organizing the recommended content and providing it to the user.

[1038] (Claim 2)

[1039] The system of claim 1 further includes means for a user to reply to a post on the account of the generative artificial intelligence model, analyzing the reply message to the post, and again generating an answer using the generative artificial intelligence model, and means for replying to the generated answer to the user.

[1040] (Claim 3)

[1041] 10. The system of claim 1, further comprising means for providing a webhook for obtaining data of received user messages.

[1042] "Example 2: Combining Emotion Engines"

[1043] (Claim 1)

[1044] A means of registering an account for the generated AI model on SNS;

[1045] means for receiving messages sent by users to said account;

[1046] means for analyzing the received message and recognizing emotions using an emotion analysis engine;

[1047] means for sending a prompt to a generative artificial intelligence model based on the emotion-analyzed result to generate an answer;

[1048] means for sending the generated answer back to the user as a message;

[1049] A system including:

[1050] (Claim 2)

[1051] The system of claim 1 , further comprising means for a user to reply to a post of the generative artificial intelligence model's account, analyzing the reply message to the post, and again generating an answer using the generative artificial intelligence model.

[1052] (Claim 3)

[1053] 10. The system of claim 1, further comprising means for providing a webhook for obtaining data of received user messages.

[1054] "Application example 2 when combining emotion engines"

[1055] (Claim 1)

[1056] A means of registering an account for the generated AI model on SNS;

[1057] means for receiving messages sent by users to said account;

[1058] means for analyzing the received message and detecting a user's emotion;

[1059] means for generating an answer using a generative artificial intelligence model based on the detected emotion;

[1060] means for returning the generated answer to the user as a message;

[1061] The system includes a means for displaying the generated answer on a staff member's terminal and providing the answer.

[1062] (Claim 2)

[1063] The system of claim 1 , further comprising means for a user to reply to a post of the generative artificial intelligence model's account, analyzing the reply message to the post, and again generating an answer using the generative artificial intelligence model.

[1064] (Claim 3)

[1065] 10. The system of claim 1, further comprising means for providing a webhook for obtaining data of received user messages. [Explanation of symbols]

[1066] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for registering an account for the generated AI model on SNS; A means for receiving direct messages sent by users to the account; means for analyzing the received message and generating a response using a generative artificial intelligence model; The system includes means for returning the generated answer to the user as a direct message.

2. The system of claim 1 further includes means for a user to reply to a post on the account of the generative artificial intelligence model, analyzing the reply message to the post, and again generating an answer using the generative artificial intelligence model, and means for replying to the generated answer to the user.

3. The system of claim 1 , further comprising means for providing a web hook for obtaining data of received user messages.

Images