system

Abstract

We provide the system. [Solution] A means for the user to input a question, A means by which the terminal obtains the question entered by the user and sends it to the server, A means for providing a server with questions it has acquired to a generative artificial intelligence system, and for generating answers to those questions, A means of returning the generated response to the user via the server, A means of displaying the response received by the terminal to the user, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, the method including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern highly informationized societies, users often seek quick and accurate answers to a wide variety of questions and problems. However, in conventional support systems, problems exist such as the time taken to generate answers and the lack of consistency in the quality of answers. In particular, it is difficult for users to directly input questions and obtain appropriate answers in real time. In such situations, users feel frustrated and may consequently refrain from using the service. Therefore, there is a need to provide a support system that can provide quick and high-quality answers.

Means for Solving the Problems

[0005] The present invention provides a system in which a user inputs a question through a terminal, and a server generates an appropriate answer using generative artificial intelligence and sends it back to the user. Specifically, the system includes means for the user to input a question, means for the terminal to acquire the question input by the user and send it to the server, means for the server to provide the acquired question to the generative artificial intelligence and have it generate an answer to the question, means for sending the generated answer back to the user via the server, and means for the terminal to display the received answer to the user. In this system, the server formats the response from the generative artificial intelligence into JSON format, and by using an HTTP POST request when the terminal sends the user's question, it is possible to provide a fast and high-quality answer.

[0006] A "user" is a person or entity that uses the system to input questions and receive answers.

[0007] A "terminal" is a device that a user uses to input questions and communicate with a server. Examples include computers, smartphones, and tablets.

[0008] A "server" is a central processing unit that receives questions sent from terminals, provides them to a generative artificial intelligence system to generate answers, and sends the generated answers back to the terminals.

[0009] A "question" is the content of an inquiry that a user enters into the system via their device.

[0010] "Generative artificial intelligence" refers to artificial intelligence technology that generates appropriate answers to given inputs (questions). For example, AI models that utilize natural language processing technology fall into this category.

[0011] "Answer" refers to the response generated by a generative artificial intelligence system in response to a user's question.

[0012] "Means of acquisition" refers to the method or mechanism by which the terminal acquires the question entered by the user.

[0013] "Means of transmission" refers to the method or mechanism for sending the question acquired by the terminal to the server.

[0014] "Means of provision" refers to a method or mechanism for passing questions acquired by the server to a generative artificial intelligence.

[0015] "Generative means" refers to a method or mechanism by which a generative artificial intelligence generates an answer based on a user's question.

[0016] "Means of return" refers to the method or mechanism by which the server sends the generated response back to the terminal.

[0017] "Means of display" refers to a method or mechanism for a terminal to display the response received from the server to the user.

[0018] "Formatting method" refers to a method or mechanism by which a server converts a response from a generative artificial intelligence into JSON format.

[0019] An "HTTP POST request" is a method of the HTTP protocol used by a device to send data to a server. [Brief explanation of the drawing]

[0020] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Embodiments for Carrying Out the Invention

[0021] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0024] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0025] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0026] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0027] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0028] [First Embodiment]

[0029] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0030] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0031] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0033] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0036] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0038] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0039] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0040] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0041] This invention relates to a system in which, when a user inputs a question through a terminal, a server uses generative artificial intelligence to generate an appropriate answer to that question and sends it back to the user.

[0042] System Overview

[0043] This system includes means for a user to input a question, means for a terminal to send a question to a server, means for the server to receive the question and provide it to a generative artificial intelligence, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0044] Operation of each component

[0045] 1. User actions:

[0046] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0047] 2. Obtaining and submitting questions:

[0048] The terminal uses a script such as JavaScript (registered trademark) to retrieve the question entered by the user. It then sends this question to the server as an HTTP POST request.

[0049] 3. Receiving the question:

[0050] The server receives an HTTP POST request sent from the terminal. This request arrives at the server as data in JSON format.

[0051] 4. Provision to generative artificial intelligence:

[0052] The server passes the received question as a prompt to the generative artificial intelligence. Based on this prompt, the generative AI generates an appropriate answer.

[0053] 5. Generating the answer:

[0054] Generative artificial intelligence generates answers to questions in text format. This generation process is carried out using a pre-trained model.

[0055] 6. Return your response:

[0056] The server formats the response received from the generative artificial intelligence into JSON format. Then, it sends this JSON-formatted response back to the terminal as an HTTP response.

[0057] 7. Display the answer:

[0058] The terminal receives an HTTP response from the server and extracts the answer from the JSON-formatted data. The extracted answer text is then displayed on the user's screen.

[0059] Specific examples

[0060] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is sent to the server, and a generative artificial intelligence generates an answer. The generated answer is displayed on the user's device as specific and practical advice, such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0061] Technical effects

[0062] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality.

[0063] The specific operation and utilization techniques of each means in this invention can be modified as appropriate based on the system design and implementation, and this flexibility is also one of the advantages of this invention.

[0064] The following describes the processing flow.

[0065] Step 1:

[0066] The user enters a question into the terminal's text field. The terminal provides an interface for the user to enter a question.

[0067] Step 2:

[0068] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user.

[0069] Step 3:

[0070] The device serializes the question it obtains into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content.

[0071] Step 4:

[0072] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content from the request body.

[0073] Step 5:

[0074] The server provides the question content as a prompt to the generative artificial intelligence. The generative artificial intelligence then performs text generation processing based on the given prompt.

[0075] Step 6:

[0076] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[0077] Step 7:

[0078] The server formats the response text received from the generative artificial intelligence into JSON format. The formatted JSON data is then sent to the terminal as an HTTP response.

[0079] Step 8:

[0080] The terminal receives an HTTP response from the server. The JSON data is parsed from the response body, and the generated response text is extracted.

[0081] Step 9:

[0082] The device displays the extracted answer text to the user. The user can then review the answer displayed on the screen.

[0083] (Example 1)

[0084] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0085] Traditional systems often involved long waiting times between a user entering a question and receiving an answer. Furthermore, their reliance on manual responses meant inconsistent and unpredictable response quality. Additionally, mechanisms for quickly generating appropriate answers were inadequately developed.

[0086] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0087] In this invention, the server includes means for providing acquired questions to a generative artificial intelligence model to generate answers to those questions, means for formatting the response from the generative artificial intelligence model into a data format, and means for using a data transmission request when a terminal sends a user's question. This makes it possible to provide users with fast, consistent, and high-quality answers.

[0088] A "user" is an individual or organization that uses this system to input questions and receive answers.

[0089] A "terminal" is a device used by users to input questions and send and receive data to and from a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0090] A "server" is a central system that receives questions sent from terminals, provides them as prompts to generative artificial intelligence models, and sends the generated answers back to the terminals.

[0091] A "generative artificial intelligence model" is a pre-trained deep learning model or algorithm that generates appropriate answers based on received prompts (questions).

[0092] A "prompt" is the text of a question or instruction that is input to a generative artificial intelligence model.

[0093] "Data format" refers to the structure and format of the data that the server uses to organize the response from a generative artificial intelligence model and send it back to the terminal.

[0094] A "data transmission request" refers to a communication protocol, such as an HTTP POST request, used to send a user's question from their device to a server.

[0095] The present invention relates to a system in which a user inputs a question through a terminal, and a server generates an appropriate answer to that question using a generative artificial intelligence model and sends it back to the user. This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to the generative artificial intelligence model, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0096] The user opens a web browser on their device (e.g., personal computer, smartphone, tablet) and enters a question in the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" When the user clicks the "Submit Question" button, the device retrieves the question and sends it to the server as an HTTP POST request using JavaScript. The data is sent in JSON format. The programming languages ​​and tools used are JavaScript, HTML, and HTTP.

[0097] The server listens for HTTP POST requests at a configured endpoint and parses the JSON data in the request body. The server provides the received question as a prompt to a generative artificial intelligence model, which then generates an appropriate answer. This generative AI model could be a general deep learning model (e.g., GPT-3®, BERT). These models are pre-trained on large amounts of text data and have the ability to generate highly accurate answers. The server accesses these generative AI models using a programming language such as Python.

[0098] Once a generative artificial intelligence model generates a response, the server formats the response into a data format and sends it back to the terminal as an HTTP response. For example, the reformatted data is often in JSON format. The server runs on a web server (e.g., Apache®, Nginx) and uses languages ​​such as Python or Node.js.

[0099] The terminal receives an HTTP response from the server and extracts the answer text from the JSON data. Then, it uses JavaScript in the web browser to display the answer on the user's screen. For example, it might display specific and practical advice such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0100] This system allows users to obtain fast, consistent, and high-quality answers. While traditional methods required manual responses from human staff, the use of generative artificial intelligence models enables instant responses, significantly improving the user experience. Furthermore, the consistent quality of responses is ensured by the generative AI models.

[0101] The embodiments of this invention are configured flexibly and can be modified as appropriate based on specific system designs and implementations.

[0102] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0103] Step 1:

[0104] The user enters a question.

[0105] In terms of the specific operation, the user opens a web browser on their device (PC, smartphone, or tablet) and enters a question into the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" The input is saved as text data on the device.

[0106] Step 2:

[0107] The device retrieves and sends the question.

[0108] Specifically, when the user clicks the "Submit Question" button, the device uses JavaScript to retrieve the question from the text field. This question data is converted to JSON format and sent to the server as an HTTP POST request. The input is the user's question, and the output is the HTTP POST request to the server.

[0109] Step 3:

[0110] The server receives the question.

[0111] In terms of operation, the server listens for HTTP POST requests at the configured endpoint. Upon receiving a request sent from the terminal, the server parses the JSON data in the request body and extracts the question text. The input is the HTTP POST request, and the output is the parsed question text.

[0112] Step 4:

[0113] The server provides prompts to the generative artificial intelligence.

[0114] In terms of operation, the analyzed question text is provided to a generative artificial intelligence model as a prompt. The server generates an API request and sends it to the generative AI model. The generative AI model used is pre-trained on large amounts of text data (e.g., GPT-3, BERT). The input is the question text, and the output is the API request to the generative AI model.

[0115] Step 5:

[0116] A generative artificial intelligence generates the answer.

[0117] In terms of operation, a generative artificial intelligence model generates an appropriate response based on the input prompt. This response process is carried out via a deep learning algorithm. The generated response is returned to the server in text format. The input is the prompt, and the output is the response in text format.

[0118] Step 6:

[0119] The server formats the response and sends it back.

[0120] In terms of operation, the server formats the response received from the generative artificial intelligence model into JSON format and sends it back to the terminal as an HTTP response. The input is a text-formatted response, and the output is an HTTP response (in JSON format) sent to the terminal.

[0121] Step 7:

[0122] The device will display the answer.

[0123] In terms of specific operation, the terminal receives an HTTP response from the server and extracts the answer text from the JSON data. JavaScript in the web browser is then used to display the answer on the user's screen. For example, specific and practical advice such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have your connection speed checked," might be displayed. The input is the HTTP response, and the output is the displayed text.

[0124] (Application Example 1)

[0125] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0126] In recent years, there has been a growing demand for faster and more efficient customer support in virtual stores. However, traditional systems require staff to manually search for and provide answers to customer questions, often resulting in long response times. This has led to decreased customer satisfaction. Furthermore, there has been a lack of technology to enable natural conversations using voice input.

[0127] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0128] In this invention, the server includes means for the user to input a question, means for a terminal to acquire the question input by the user and send it to the server, means for the server to provide the acquired question to a generative artificial intelligence to generate an answer to the question, means for sending the generated answer back to the user via the server, means for the terminal to display the received answer to the user, means for a smart device to acquire a question through voice input, and means for displaying the generated answer on the smart device's display. This makes it possible to provide quick and accurate answers to customer questions in a virtual store.

[0129] A "user" is someone who uses the system to input questions and receive the generated answers.

[0130] A "terminal" is a device operated by the user, which is used for inputting, retrieving, and sending questions to the server, as well as receiving and displaying answers from the server.

[0131] A "server" is a device that receives questions sent from a terminal and provides them to a generative artificial intelligence system, and is responsible for sending the generated answers back to the user.

[0132] "Generative artificial intelligence" is an artificial intelligence technology that generates appropriate answers based on a given question.

[0133] An "answer" is a response to a user's question, generated by a generative artificial intelligence system.

[0134] A "smart device" is an advanced device that has the function of obtaining questions through voice input and displaying the generated answers on a screen.

[0135] "Voice input" is a method of acquiring the user's voice through the microphone of a smart device and converting that voice data into text format.

[0136] A "display" is the screen installed in a smart device that visually presents the generated response to the user.

[0137] An "HTTP POST request" is one of the internet communication protocols used to send data from a terminal to a server.

[0138] The system based on this invention allows the user to input a question via a terminal, and provides an appropriate answer using generative artificial intelligence. The following hardware and software are used to realize this system.

[0139] First, the user inputs a question using a smart device (e.g., smart glasses). This question is captured as voice input and converted into text format using a speech recognition library. Specifically, the speech_recognition library is used. The smart device includes a microphone for capturing voice input and a display for showing the captured response.

[0140] The terminal converts the question into text format and then sends the data to the server. This transmission uses the HTTP POST request, an internet communication protocol. The sent question arrives at the server as JSON data.

[0141] The server provides the received question as a prompt to a generative artificial intelligence (AI). This AI uses an advanced language model (e.g., GPT-3). The AI ​​generates an appropriate response to the received prompt and sends that response back to the server.

[0142] The server formats the generated response into JSON format and sends it back to the device as an HTTP response. The device receives the response from the server, extracts the answer from the JSON data, and displays it on the smart device's display.

[0143] As a concrete example, if a user asks, "Is this item in stock?", this question is picked up through the smart glasses' microphone and converted into text using speech recognition. The converted text is then sent to a server, where generative artificial intelligence generates an answer. The generated answer, "This item is in stock. You can purchase it now," is displayed on the smart glasses' screen and provided to the user.

[0144] This system enables the provision of quick and accurate answers in virtual stores, significantly improving customer satisfaction.

[0145] The following are examples of prompts provided to generative artificial intelligence:

[0146] "A customer asked, 'Do you have this item in stock?' Please provide the best possible answer."

[0147] This prompt can be used by a generative artificial intelligence to generate the optimal answer to the user's question.

[0148] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0149] Step 1:

[0150] The user inputs a question using a smart device (e.g., smart glasses). This question is entered in voice format. Voice data is captured through the smart device's microphone. This is the input for Step 1. This voice data is then passed on to the subsequent speech recognition process.

[0151] Step 2:

[0152] The smart device converts the acquired audio data into text format using a speech recognition library. The library used in this step is speech_recognition. The speech recognition library converts the audio data into text data, and the converted text becomes the output of step 2.

[0153] Step 3:

[0154] The terminal sends the question, converted to text format, to the server via an HTTP POST request. This text data is packaged in JSON format and sent to the server over the internet. The sent JSON data is the output of step 3.

[0155] Step 4:

[0156] The server receives an HTTP POST request from the terminal. This request contains the user's question in JSON format. The server parses this JSON data and extracts the question. The extracted question is the output of step 4.

[0157] Step 5:

[0158] The server provides the extracted questions as prompts to the generative artificial intelligence. This generative AI uses an advanced language model (e.g., GPT-3). By passing the questions as prompts to the AI, the AI ​​generates the optimal answer. The generated answer is the output of step 5.

[0159] Step 6:

[0160] The server formats the response received from the generative artificial intelligence into JSON format. The formatted JSON data is prepared for return to the user's terminal. This formatted JSON data is the output of step 6.

[0161] Step 7:

[0162] The terminal receives an HTTP response from the server. This response contains the answer generated by the generative artificial intelligence in JSON format. The terminal parses this JSON data and extracts the answer. The extracted answer is the output of step 7.

[0163] Step 8:

[0164] The smart device displays the extracted answers on its screen, allowing the user to visually confirm the answers to the questions. The answers displayed on the screen are the output of step 8.

[0165] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0166] This invention relates to a system in which, when a user inputs a question through a terminal, a server generates an appropriate answer to that question using generative artificial intelligence and an emotion engine, adjusts it according to the user's emotions, and then sends a response to the user.

[0167] System Overview

[0168] This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to a generative artificial intelligence and an emotion engine, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user. Furthermore, it also includes means for using the emotion engine to analyze the user's emotions and adjusting the answer based on the results.

[0169] Operation of each component

[0170] 1. User actions:

[0171] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0172] 2. Obtaining and submitting questions:

[0173] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, it uses an emotion engine to analyze the user's emotions and retrieves the results. Finally, it serializes the question content and emotion data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[0174] 3. Receiving the question:

[0175] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body.

[0176] 4. Provisions to generative artificial intelligence and emotion engines:

[0177] The server provides the received question content as a prompt to the generative artificial intelligence. The generative AI performs text generation processing based on this prompt. At the same time, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[0178] 5. Generating and refining responses:

[0179] A generative artificial intelligence generates answers based on the provided questions. Furthermore, the server appropriately adjusts the generated answers based on sentiment data analyzed by an emotion engine.

[0180] 6. Return your response:

[0181] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response.

[0182] 7. Display the answer:

[0183] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen.

[0184] Specific examples

[0185] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is analyzed by an emotion engine before being sent to the server. If the emotion engine detects the user's frustration, the generative artificial intelligence generates a response that is specific and practical advice, such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed," and it is delivered in a friendly tone that is adjusted according to the user's emotions. In this way, the user experience is improved.

[0186] Technical effects

[0187] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality. Additionally, responses that consider the user's emotions are provided, increasing user satisfaction.

[0188] The following describes the processing flow.

[0189] Step 1:

[0190] The user enters the question into the terminal's text field. The terminal provides an interface for the user to enter the question.

[0191] Step 2:

[0192] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user. At this point, the emotion engine also analyzes the user's facial expressions and voice tone using the device's camera and microphone.

[0193] Step 3:

[0194] The emotion engine generates emotional data from the user's input, facial expressions, and tone of voice. This emotional data includes whether the user is feeling stress, anxiety, joy, etc.

[0195] Step 4:

[0196] The device serializes the acquired question and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content and sentiment data.

[0197] Step 5:

[0198] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content and sentiment data from the request body.

[0199] Step 6:

[0200] The server extracts questions and provides them as prompts to the generative artificial intelligence. The generative AI then uses these prompts to perform text generation processing.

[0201] Step 7:

[0202] The server provides emotional data to the emotion engine, which further analyzes the user's emotional state. The emotion engine processes the emotional data and generates the emotional analysis results.

[0203] Step 8:

[0204] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[0205] Step 9:

[0206] The server combines the response text received from the generative artificial intelligence with the results of the emotion engine's analysis. Based on the emotion analysis results, the response is appropriately adjusted. For example, if the user is feeling stressed, the response will be made more polite and kind.

[0207] Step 10:

[0208] The server formats the adjusted response into JSON format. Then, it sends the JSON data containing the adjusted response to the terminal as an HTTP response.

[0209] Step 11:

[0210] The terminal receives an HTTP response from the server. It then parses the JSON data from the response body and extracts the generated response text.

[0211] Step 12:

[0212] The device displays the extracted response text to the user. The user can then see the response, which has been adjusted according to their emotions.

[0213] (Example 2)

[0214] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0215] Traditional response generation systems often provided answers without considering the user's emotions, resulting in a poor user experience. In particular, it was difficult to provide appropriate answers when users were feeling anxious or frustrated. Furthermore, the quality of responses was often inconsistent, leading to decreased user satisfaction.

[0216] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0217] In this invention, the server includes means for providing a question to a generative artificial intelligence and generating an answer to the question, means for adjusting the generated answer based on the user's emotions using an emotion engine, and means for returning the adjusted answer to the user via the server. This makes it possible to provide consistent, high-quality answers that take the user's emotions into consideration.

[0218] A "user" is an individual or organization that uses this system to input questions and receive answers.

[0219] A "device" is a device used by a user to input questions or view answers, and includes PCs, smartphones, tablets, and other similar devices.

[0220] A "server" is a central processing unit that receives user questions, generates and refines answers using generative artificial intelligence and an emotion engine, and sends them back to the user.

[0221] "Generative artificial intelligence" refers to artificial intelligence models that can generate answers in natural language to user questions. Examples include GPT-3.

[0222] An "emotion engine" is software or an algorithm that analyzes emotional data obtained from users and adjusts the responses generated based on the results.

[0223] JSON format is a lightweight data exchange format for storing and transferring data as text, and it is an abbreviation for JavaScript Object Notation.

[0224] An "HTTP POST request" is one of the HTTP methods used to send and receive data between a server and another server.

[0225] "Emotional data" refers to the analysis results that indicate the user's emotional state, including, for example, whether the user is feeling frustrated.

[0226] A "prompt" is an input sentence that provides information, such as the content of a question, to a generative artificial intelligence system in order to generate a specific answer.

[0227] "Answer" refers to information or advice generated by a generative artificial intelligence system based on the user's question.

[0228] This invention is a system in which, when a user inputs a question, a server uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusts it according to the user's emotions, and then sends a response to the user.

[0229] This system uses the following hardware and software:

[0230] A device (PC, smartphone, tablet, etc.) for the user to enter questions.

[0231] A server that receives and processes question and sentiment data.

[0232] Generative artificial intelligence for generating answers (e.g., GPT-3)

[0233] An emotion engine that analyzes user emotions and adjusts responses accordingly.

[0234] A means of communication for exchanging data (HTTP POST request)

[0235] The user enters a question into a text field on their device and clicks the "Submit Question" button. At this point, a script on the device, such as JavaScript, retrieves the question entered by the user and analyzes the user's emotions using an emotion engine.

[0236] The analysis results and question content are serialized in JSON format and sent as an HTTP POST request to a specific API endpoint on the server. The server receives this request, analyzes its contents, and extracts the question and sentiment data.

[0237] The server provides the question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the results of the emotion analysis.

[0238] For example, if a user types "My internet connection is slow, what should I do?", the emotion engine might detect the user's frustration. The generative AI would respond to this prompt as follows:

[0239] "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed."

[0240] The server formats the generated responses into JSON format and adjusts them based on the analysis results from the sentiment engine. The adjusted responses are sent to the terminal as an HTTP response. The terminal receives this HTTP response, extracts the response text from the JSON data, and displays it on the user's screen.

[0241] This allows users to receive quick, high-quality answers, and because those answers take into account specific emotional states, the user experience is significantly improved.

[0242] The above describes specific embodiments for carrying out this invention.

[0243] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0244] Step 1:

[0245] The user enters their question in the text field on their device and clicks the "Submit Question" button.

[0246] Input: User-entered question text (e.g., "My internet connection is slow, what should I do?")

[0247] Output: The terminal detects the user's question submission operation.

[0248] Step 2:

[0249] The device uses scripts such as JavaScript to retrieve questions entered by the user. It also uses an emotion engine to analyze the user's emotions.

[0250] Input: Question text entered by the user

[0251] Output: Question text and sentiment data (e.g., "frustration")

[0252] Specific operation: The terminal captures text from the user's question input field and calls the sentiment engine to analyze the sentiment. After obtaining the analysis results, it serializes the question content and sentiment data into JSON format.

[0253] Step 3:

[0254] The device serializes the question content and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[0255] Input: Question text and sentiment data (in JSON format)

[0256] Output: HTTP POST request to the server

[0257] Specific operation: The terminal creates an HTTP POST request, including the question content and sentiment data in the request body. The request is sent to a specific API endpoint on the server.

[0258] Step 4:

[0259] The server receives an HTTP POST request sent from the terminal. It extracts the question content and sentiment data from the request body.

[0260] Input: HTTP POST request

[0261] Output: Questionnaire text and sentiment data

[0262] Specific operation: The server parses the body of the received request and extracts the question content and sentiment data sent in JSON format. This data is stored internally.

[0263] Step 5:

[0264] The server provides the received question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[0265] Input: Question text, sentiment data

[0266] Output: Responses from generative artificial intelligence, analysis results from the emotion engine.

[0267] Specific operation: The server passes the question content to the generative artificial intelligence, providing a prompt such as "User question: My internet connection is slow, what should I do?". The generative AI generates an answer based on this prompt. Meanwhile, the server provides sentiment data to the sentiment engine and obtains the sentiment analysis results.

[0268] Step 6:

[0269] The server adjusts the generated responses based on the results of the sentiment engine and formats the adjusted responses into JSON format.

[0270] Input: Response from generative artificial intelligence, emotion analysis results

[0271] Output: Adjusted response in JSON format

[0272] Specific operation: The system adjusts the response generated by the generative AI (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have them check your connection speed.") and formats the result into JSON format.

[0273] Step 7:

[0274] The server sends the adjusted response in JSON format to the terminal as an HTTP response.

[0275] Input: Adjusted response (JSON format)

[0276] Output: HTTP response to the terminal

[0277] Specific operation: The server includes JSON data containing the adjusted response in the HTTP response and sends it to the terminal.

[0278] Step 8:

[0279] The terminal receives the HTTP response from the server, analyzes the JSON data from the response body, and extracts the response text generated thereby. The terminal displays the extracted response text on the user's screen.

[0280] Input: HTTP response

[0281] Output: Response text displayed to the user

[0282] Specific operation: The terminal analyzes the response from the server, extracts the response text (e.g., "First, try restarting the router. If the speed does not improve further, we recommend contacting your Internet service provider to check the line speed.") generated from the JSON data, and displays it on the user's screen.

[0283] (Application Example 2)

[0284] Next, Application Example 2 will be described. In the following description, the data processing apparatus 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0285] In a conventional question-and-answer system, since the generated answer does not consider the user's emotions, it may be difficult to provide a prompt and appropriate response. In particular, in fields where the user has a high level of anxiety, such as security services, adjustment based on emotions is important. However, such an emotion adjustment function is lacking in the current system, and an improvement in the user experience is required.

[0286] The specific processing by the specific processing unit 290 of the data processing apparatus 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for analyzing the user's emotions using an emotion engine and adjusting the answer based on the result, means for formatting the response from the generative artificial intelligence into JSON format, and means for using an HTTP POST request when the terminal sends the user's question. Thereby, it becomes possible to provide an appropriate and prompt answer considering the user's emotions.

[0287] "User" refers to a person who uses the system.

[0288] "Means for inputting a question" refers to an interface for a user to input a question as text.

[0289] "Terminal" refers to a computer device used by a user to input a question, including a PC, smartphone, tablet, etc.

[0290] "Means for the terminal to acquire the question input by the user and transmit it to the server" refers to software or a protocol for transferring the question input by the user from the terminal to the server.

[0291] "Server" refers to a computer device for receiving and processing questions.

[0292] "Generative artificial intelligence" refers to an artificial intelligence model for generating an appropriate answer to a provided question.

[0293] "Means for providing to the generative artificial intelligence" refers to the process for the server to distribute the question received from the user to the generative artificial intelligence.

[0294] "Emotion engine" refers to an algorithm or software for analyzing the user's emotion and adjusting the answer based on the result.

[0295] "Means for analyzing the user's emotion using the emotion engine and adjusting the answer based on the result" refers to a mechanism for modifying the generated answer based on the user's emotion.

[0296] "Means for returning the generated answer to the user via the server" refers to a process for returning the generated answer to the terminal via the server.

[0297] "Means of displaying the response received by the device to the user" refers to the process of displaying the response received by the device on the user's screen.

[0298] "Methods for formatting into JSON format" refers to software processing for converting the generated response into JSON (JavaScript Object Notation) format.

[0299] "Using an HTTP POST request" refers to the process of sending user query data to a server using the POST method of the HTTP protocol.

[0300] This invention is a system that, upon receiving a question from a user, uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusting it according to the user's emotions before responding. This invention is particularly intended for application in the field of security services, enabling a rapid and appropriate response to user anxieties and questions.

[0301] System Overview

[0302] User:

[0303] Users enter their questions into a text field from devices such as PCs, smartphones, and tablets. For example, a user might enter the question, "I've been receiving a lot of phishing emails lately; what should I do about it?"

[0304] Terminal:

[0305] The terminal uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, each terminal has an emotion engine built in to analyze the user's emotions. As a result, the question content and emotion data are serialized in JSON format and an HTTP POST request is sent to a specific API endpoint on the server.

[0306] server:

[0307] The server receives the HTTP POST request sent from the terminal and extracts the question content and sentiment data from the request body. The extracted question content is provided as a prompt to the generative artificial intelligence, and the generative artificial intelligence performs text generation processing based on the prompt. As the generative artificial intelligence, generally used APIs (e.g., GPT model of OpenAI (registered trademark)) can be used.

[0308] Furthermore, an emotion engine is incorporated into the server, and the response is adjusted based on the result of analyzing the sentiment data. At this time, software such as EmotionEngine is used to modify the tone and content suitable for the user's emotion.

[0309] Generation and adjustment of responses:

[0310] The generative artificial intelligence generates a response based on the provided question. Then, the emotion engine adjusts the response according to the user's emotional state and formats it into an optimal text. For example, when the user feels anxious, the response is modified to a more kind and polite expression.

[0311] Return and display of responses:

[0312] The server formats the generated response text into JSON format, combines the result adjusted by the emotion engine, and sends the JSON data to the terminal as an HTTP response. The terminal receives the HTTP response from the server, analyzes the JSON data from the response body, extracts the generated response text, and displays it on the user's screen.

[0313] Specific examples

[0314] The user uses a smartphone to enter the following question into a dedicated application: "I've been receiving a lot of phishing emails lately. What should I do?"

[0315] This question is first sent from the device to the server. During transmission, the emotion engine detects the user's anxiety, and this information is also sent along with the question.

[0316] The server provides question and sentiment data to a generative artificial intelligence. For example, OpenAI's GPT model is used.

[0317] • Generative artificial intelligence generates answers to questions. Then, an emotion engine modifies the answers to make them kind and polite.

[0318] The corrected response is formatted in JSON format and sent back to the terminal as an HTTP response.

[0319] • Finally, the device displays the received response on the user's screen. For example, a response might be displayed such as, "First, it's important not to open emails from unknown senders. Also, avoid clicking on links in emails. Furthermore, we recommend reporting phishing emails to your ISP or security provider."

[0320] This system allows users to receive quick and appropriate answers, particularly addressing security-related concerns.

[0321] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0322] Step 1:

[0323] The user enters their question into the text field on their device and clicks the "Submit Question" button. The input here is the user entering a specific question as text.

[0324] Step 2:

[0325] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, the device's built-in sentiment engine analyzes the user's emotions and retrieves sentiment data. This question content and sentiment data are serialized into JSON format, and an HTTP POST request is sent to a specific API endpoint on the server. Specifically, the input is the user's question text and the sentiment analysis results, while the output is the data sent to the server.

[0326] Step 3:

[0327] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body. Specifically, it parses the question text and sentiment data from the JSON data and converts them into a usable format.

[0328] Step 4:

[0329] The server provides the received question content as a prompt to the generative artificial intelligence (AI). The generative AI uses this prompt to perform text generation processing and generate the answer text. For example, an open AI API such as GPT-3 is used as the generative AI. The input for this step is the question text, and the output is the generated answer text.

[0330] Step 5:

[0331] The server provides sentiment data to the sentiment engine and retrieves the sentiment analysis results again. The sentiment engine adjusts the generated response based on this data, modifying it to match the user's sentiment. The input for this step is the generated response text and sentiment data, and the output is the adjusted response text.

[0332] Step 6:

[0333] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response. The input for this step is the adjusted response text, and the output is the JSON data response from the server to the terminal.

[0334] Step 7:

[0335] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen. The input for this step is the response data in JSON format, and the output is the response text displayed on the user's screen.

[0336] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0337] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0338] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0339] [Second Embodiment]

[0340] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0341] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0342] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0343] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0344] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0345] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0346] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0347] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0348] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0349] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0350] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0351] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0352] This invention relates to a system in which, when a user inputs a question through a terminal, a server uses generative artificial intelligence to generate an appropriate answer to that question and sends it back to the user.

[0353] System Overview

[0354] This system includes means for a user to input a question, means for a terminal to send a question to a server, means for the server to receive the question and provide it to a generative artificial intelligence, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0355] Operation of each component

[0356] 1. User actions:

[0357] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0358] 2. Obtaining and submitting questions:

[0359] The terminal uses a script such as JavaScript to retrieve the question entered by the user. It then sends this question to the server as an HTTP POST request.

[0360] 3. Receiving the question:

[0361] The server receives an HTTP POST request sent from the terminal. This request arrives at the server as data in JSON format.

[0362] 4. Provision to generative artificial intelligence:

[0363] The server passes the received question as a prompt to the generative artificial intelligence. Based on this prompt, the generative AI generates an appropriate answer.

[0364] 5. Generating the answer:

[0365] Generative artificial intelligence generates answers to questions in text format. This generation process is carried out using a pre-trained model.

[0366] 6. Return your response:

[0367] The server formats the response received from the generative artificial intelligence into JSON format. Then, it sends this JSON-formatted response back to the terminal as an HTTP response.

[0368] 7. Display the answer:

[0369] The terminal receives an HTTP response from the server and extracts the answer from the JSON-formatted data. The extracted answer text is then displayed on the user's screen.

[0370] Specific examples

[0371] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is sent to the server, and a generative artificial intelligence generates an answer. The generated answer is displayed on the user's device as specific and practical advice, such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0372] Technical effects

[0373] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality.

[0374] The specific operation and utilization techniques of each means in this invention can be modified as appropriate based on the system design and implementation, and this flexibility is also one of the advantages of this invention.

[0375] The following describes the processing flow.

[0376] Step 1:

[0377] The user enters a question into the terminal's text field. The terminal provides an interface for the user to enter a question.

[0378] Step 2:

[0379] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user.

[0380] Step 3:

[0381] The device serializes the question it obtains into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content.

[0382] Step 4:

[0383] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content from the request body.

[0384] Step 5:

[0385] The server provides the question content as a prompt to the generative artificial intelligence. The generative artificial intelligence then performs text generation processing based on the given prompt.

[0386] Step 6:

[0387] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[0388] Step 7:

[0389] The server formats the response text received from the generative artificial intelligence into JSON format. The formatted JSON data is then sent to the terminal as an HTTP response.

[0390] Step 8:

[0391] The terminal receives an HTTP response from the server. The JSON data is parsed from the response body, and the generated response text is extracted.

[0392] Step 9:

[0393] The device displays the extracted answer text to the user. The user can then review the answer displayed on the screen.

[0394] (Example 1)

[0395] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0396] Traditional systems often involved long waiting times between a user entering a question and receiving an answer. Furthermore, their reliance on manual responses meant inconsistent and unpredictable response quality. Additionally, mechanisms for quickly generating appropriate answers were inadequately developed.

[0397] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0398] In this invention, the server includes means for providing acquired questions to a generative artificial intelligence model to generate answers to those questions, means for formatting the response from the generative artificial intelligence model into a data format, and means for using a data transmission request when a terminal sends a user's question. This makes it possible to provide users with fast, consistent, and high-quality answers.

[0399] A "user" is an individual or organization that uses this system to input questions and receive answers.

[0400] A "terminal" is a device used by users to input questions and send and receive data to and from a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0401] A "server" is a central system that receives questions sent from terminals, provides them as prompts to generative artificial intelligence models, and sends the generated answers back to the terminals.

[0402] A "generative artificial intelligence model" is a pre-trained deep learning model or algorithm that generates appropriate answers based on received prompts (questions).

[0403] A "prompt" is the text of a question or instruction that is input to a generative artificial intelligence model.

[0404] "Data format" refers to the structure and format of the data that the server uses to organize the response from a generative artificial intelligence model and send it back to the terminal.

[0405] A "data transmission request" refers to a communication protocol, such as an HTTP POST request, used to send a user's question from their device to a server.

[0406] The present invention relates to a system in which a user inputs a question through a terminal, and a server generates an appropriate answer to that question using a generative artificial intelligence model and sends it back to the user. This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to the generative artificial intelligence model, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0407] The user opens a web browser on their device (e.g., personal computer, smartphone, tablet) and enters a question in the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" When the user clicks the "Submit Question" button, the device retrieves the question and sends it to the server as an HTTP POST request using JavaScript. The data is sent in JSON format. The programming languages ​​and tools used are JavaScript, HTML, and HTTP.

[0408] The server listens for HTTP POST requests at a configured endpoint and parses the JSON data in the request body. The server provides the retrieved question as a prompt to a generative artificial intelligence model, which then generates an appropriate answer. This generative AI model could be a general deep learning model (e.g., GPT-3, BERT). These models are pre-trained on large amounts of text data and have the ability to generate highly accurate answers. The server accesses these generative AI models using a programming language such as Python.

[0409] Once a generative artificial intelligence model generates a response, the server formats the response into a data format and sends it back to the terminal as an HTTP response. For example, the reformatted data is often in JSON format. The server runs on a web server (e.g., Apache, Nginx) and uses languages ​​such as Python or Node.js.

[0410] The terminal receives an HTTP response from the server and extracts the answer text from the JSON data. Then, it uses JavaScript in the web browser to display the answer on the user's screen. For example, it might display specific and practical advice such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0411] This system allows users to obtain fast, consistent, and high-quality answers. While traditional methods required manual responses from human staff, the use of generative artificial intelligence models enables instant responses, significantly improving the user experience. Furthermore, the consistent quality of responses is ensured by the generative AI models.

[0412] The embodiments of this invention are configured flexibly and can be modified as appropriate based on specific system designs and implementations.

[0413] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0414] Step 1:

[0415] The user enters a question.

[0416] In terms of the specific operation, the user opens a web browser on their device (PC, smartphone, or tablet) and enters a question into the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" The input is saved as text data on the device.

[0417] Step 2:

[0418] The device retrieves and sends the question.

[0419] Specifically, when the user clicks the "Submit Question" button, the device uses JavaScript to retrieve the question from the text field. This question data is converted to JSON format and sent to the server as an HTTP POST request. The input is the user's question, and the output is the HTTP POST request to the server.

[0420] Step 3:

[0421] The server receives the question.

[0422] In terms of operation, the server listens for HTTP POST requests at the configured endpoint. Upon receiving a request sent from the terminal, the server parses the JSON data in the request body and extracts the question text. The input is the HTTP POST request, and the output is the parsed question text.

[0423] Step 4:

[0424] The server provides prompts to the generative artificial intelligence.

[0425] In terms of operation, the analyzed question text is provided to a generative artificial intelligence model as a prompt. The server generates an API request and sends it to the generative AI model. The generative AI model used is pre-trained on large amounts of text data (e.g., GPT-3, BERT). The input is the question text, and the output is the API request to the generative AI model.

[0426] Step 5:

[0427] A generative artificial intelligence generates the answer.

[0428] In terms of operation, a generative artificial intelligence model generates an appropriate response based on the input prompt. This response process is carried out via a deep learning algorithm. The generated response is returned to the server in text format. The input is the prompt, and the output is the response in text format.

[0429] Step 6:

[0430] The server formats the response and sends it back.

[0431] In terms of operation, the server formats the response received from the generative artificial intelligence model into JSON format and sends it back to the terminal as an HTTP response. The input is a text-formatted response, and the output is an HTTP response (in JSON format) sent to the terminal.

[0432] Step 7:

[0433] The device will display the answer.

[0434] In terms of specific operation, the terminal receives an HTTP response from the server and extracts the answer text from the JSON data. JavaScript in the web browser is then used to display the answer on the user's screen. For example, specific and practical advice such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have your connection speed checked," might be displayed. The input is the HTTP response, and the output is the displayed text.

[0435] (Application Example 1)

[0436] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0437] In recent years, there has been a growing demand for faster and more efficient customer support in virtual stores. However, traditional systems require staff to manually search for and provide answers to customer questions, often resulting in long response times. This has led to decreased customer satisfaction. Furthermore, there has been a lack of technology to enable natural conversations using voice input.

[0438] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0439] In this invention, the server includes means for the user to input a question, means for a terminal to acquire the question input by the user and send it to the server, means for the server to provide the acquired question to a generative artificial intelligence to generate an answer to the question, means for sending the generated answer back to the user via the server, means for the terminal to display the received answer to the user, means for a smart device to acquire a question through voice input, and means for displaying the generated answer on the smart device's display. This makes it possible to provide quick and accurate answers to customer questions in a virtual store.

[0440] A "user" is someone who uses the system to input questions and receive the generated answers.

[0441] A "terminal" is a device operated by the user, which is used for inputting, retrieving, and sending questions to the server, as well as receiving and displaying answers from the server.

[0442] A "server" is a device that receives questions sent from a terminal and provides them to a generative artificial intelligence system, and is responsible for sending the generated answers back to the user.

[0443] "Generative artificial intelligence" is an artificial intelligence technology that generates appropriate answers based on a given question.

[0444] An "answer" is a response to a user's question, generated by a generative artificial intelligence system.

[0445] A "smart device" is an advanced device that has the function of obtaining questions through voice input and displaying the generated answers on a screen.

[0446] "Voice input" is a method of acquiring the user's voice through the microphone of a smart device and converting that voice data into text format.

[0447] A "display" is the screen installed in a smart device that visually presents the generated response to the user.

[0448] An "HTTP POST request" is one of the internet communication protocols used to send data from a terminal to a server.

[0449] The system based on this invention allows the user to input a question via a terminal, and provides an appropriate answer using generative artificial intelligence. The following hardware and software are used to realize this system.

[0450] First, the user inputs a question using a smart device (e.g., smart glasses). This question is captured as voice input and converted into text format using a speech recognition library. Specifically, the speech_recognition library is used. The smart device includes a microphone for capturing voice input and a display for showing the captured response.

[0451] The terminal converts the question into text format and then sends the data to the server. This transmission uses the HTTP POST request, an internet communication protocol. The sent question arrives at the server as JSON data.

[0452] The server provides the received question as a prompt to a generative artificial intelligence (AI). This AI uses an advanced language model (e.g., GPT-3). The AI ​​generates an appropriate response to the received prompt and sends that response back to the server.

[0453] The server formats the generated response into JSON format and sends it back to the device as an HTTP response. The device receives the response from the server, extracts the answer from the JSON data, and displays it on the smart device's display.

[0454] As a concrete example, if a user asks, "Is this item in stock?", this question is picked up through the smart glasses' microphone and converted into text using speech recognition. The converted text is then sent to a server, where generative artificial intelligence generates an answer. The generated answer, "This item is in stock. You can purchase it now," is displayed on the smart glasses' screen and provided to the user.

[0455] This system enables the provision of quick and accurate answers in virtual stores, significantly improving customer satisfaction.

[0456] The following are examples of prompts provided to generative artificial intelligence:

[0457] "A customer asked, 'Do you have this item in stock?' Please provide the best possible answer."

[0458] This prompt can be used by a generative artificial intelligence to generate the optimal answer to the user's question.

[0459] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0460] Step 1:

[0461] The user inputs a question using a smart device (e.g., smart glasses). This question is entered in voice format. Voice data is captured through the smart device's microphone. This is the input for Step 1. This voice data is then passed on to the subsequent speech recognition process.

[0462] Step 2:

[0463] The smart device converts the acquired audio data into text format using a speech recognition library. The library used in this step is speech_recognition. The speech recognition library converts the audio data into text data, and the converted text becomes the output of step 2.

[0464] Step 3:

[0465] The terminal sends the question, converted to text format, to the server via an HTTP POST request. This text data is packaged in JSON format and sent to the server over the internet. The sent JSON data is the output of step 3.

[0466] Step 4:

[0467] The server receives an HTTP POST request from the terminal. This request contains the user's question in JSON format. The server parses this JSON data and extracts the question. The extracted question is the output of step 4.

[0468] Step 5:

[0469] The server provides the extracted questions as prompts to the generative artificial intelligence. This generative AI uses an advanced language model (e.g., GPT-3). By passing the questions as prompts to the AI, the AI ​​generates the optimal answer. The generated answer is the output of step 5.

[0470] Step 6:

[0471] The server formats the response received from the generative artificial intelligence into JSON format. The formatted JSON data is prepared for return to the user's terminal. This formatted JSON data is the output of step 6.

[0472] Step 7:

[0473] The terminal receives an HTTP response from the server. This response contains the answer generated by the generative artificial intelligence in JSON format. The terminal parses this JSON data and extracts the answer. The extracted answer is the output of step 7.

[0474] Step 8:

[0475] The smart device displays the extracted answers on its screen, allowing the user to visually confirm the answers to the questions. The answers displayed on the screen are the output of step 8.

[0476] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0477] This invention relates to a system in which, when a user inputs a question through a terminal, a server generates an appropriate answer to that question using generative artificial intelligence and an emotion engine, adjusts it according to the user's emotions, and then sends a response to the user.

[0478] System Overview

[0479] This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to a generative artificial intelligence and an emotion engine, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user. Furthermore, it also includes means for using the emotion engine to analyze the user's emotions and adjusting the answer based on the results.

[0480] Operation of each component

[0481] 1. User actions:

[0482] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0483] 2. Obtaining and submitting questions:

[0484] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, it uses an emotion engine to analyze the user's emotions and retrieves the results. Finally, it serializes the question content and emotion data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[0485] 3. Receiving the question:

[0486] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body.

[0487] 4. Provisions to generative artificial intelligence and emotion engines:

[0488] The server provides the received question content as a prompt to the generative artificial intelligence. The generative AI performs text generation processing based on this prompt. At the same time, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[0489] 5. Generating and refining responses:

[0490] A generative artificial intelligence generates answers based on the provided questions. Furthermore, the server appropriately adjusts the generated answers based on sentiment data analyzed by an emotion engine.

[0491] 6. Return your response:

[0492] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response.

[0493] 7. Display the answer:

[0494] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen.

[0495] Specific examples

[0496] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is analyzed by an emotion engine before being sent to the server. If the emotion engine detects the user's frustration, the generative artificial intelligence generates a response that is specific and practical advice, such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed," and it is delivered in a friendly tone that is adjusted according to the user's emotions. In this way, the user experience is improved.

[0497] Technical effects

[0498] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality. Additionally, responses that consider the user's emotions are provided, increasing user satisfaction.

[0499] The following describes the processing flow.

[0500] Step 1:

[0501] The user enters the question into the terminal's text field. The terminal provides an interface for the user to enter the question.

[0502] Step 2:

[0503] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user. At this point, the emotion engine also analyzes the user's facial expressions and voice tone using the device's camera and microphone.

[0504] Step 3:

[0505] The emotion engine generates emotional data from the user's input, facial expressions, and tone of voice. This emotional data includes whether the user is feeling stress, anxiety, joy, etc.

[0506] Step 4:

[0507] The device serializes the acquired question and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content and sentiment data.

[0508] Step 5:

[0509] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content and sentiment data from the request body.

[0510] Step 6:

[0511] The server extracts questions and provides them as prompts to the generative artificial intelligence. The generative AI then uses these prompts to perform text generation processing.

[0512] Step 7:

[0513] The server provides emotional data to the emotion engine, which further analyzes the user's emotional state. The emotion engine processes the emotional data and generates the emotional analysis results.

[0514] Step 8:

[0515] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[0516] Step 9:

[0517] The server combines the response text received from the generative artificial intelligence with the results of the emotion engine's analysis. Based on the emotion analysis results, the response is appropriately adjusted. For example, if the user is feeling stressed, the response will be made more polite and kind.

[0518] Step 10:

[0519] The server formats the adjusted response into JSON format. Then, it sends the JSON data containing the adjusted response to the terminal as an HTTP response.

[0520] Step 11:

[0521] The terminal receives an HTTP response from the server. It then parses the JSON data from the response body and extracts the generated response text.

[0522] Step 12:

[0523] The device displays the extracted response text to the user. The user can then see the response, which has been adjusted according to their emotions.

[0524] (Example 2)

[0525] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0526] Traditional response generation systems often provided answers without considering the user's emotions, resulting in a poor user experience. In particular, it was difficult to provide appropriate answers when users were feeling anxious or frustrated. Furthermore, the quality of responses was often inconsistent, leading to decreased user satisfaction.

[0527] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0528] In this invention, the server includes means for providing a question to a generative artificial intelligence and generating an answer to the question, means for adjusting the generated answer based on the user's emotions using an emotion engine, and means for returning the adjusted answer to the user via the server. This makes it possible to provide consistent, high-quality answers that take the user's emotions into consideration.

[0529] A "user" is an individual or organization that uses this system to input questions and receive answers.

[0530] A "device" is a device used by a user to input questions or view answers, and includes PCs, smartphones, tablets, and other similar devices.

[0531] A "server" is a central processing unit that receives user questions, generates and refines answers using generative artificial intelligence and an emotion engine, and sends them back to the user.

[0532] "Generative artificial intelligence" refers to artificial intelligence models that can generate answers in natural language to user questions. Examples include GPT-3.

[0533] An "emotion engine" is software or an algorithm that analyzes emotional data obtained from users and adjusts the responses generated based on the results.

[0534] JSON format is a lightweight data exchange format for storing and transferring data as text, and it is an abbreviation for JavaScript Object Notation.

[0535] An "HTTP POST request" is one of the HTTP methods used to send and receive data between a server and another server.

[0536] "Emotional data" refers to the analysis results that indicate the user's emotional state, including, for example, whether the user is feeling frustrated.

[0537] A "prompt" is an input sentence that provides information, such as the content of a question, to a generative artificial intelligence system in order to generate a specific answer.

[0538] "Answer" refers to information or advice generated by a generative artificial intelligence system based on the user's question.

[0539] This invention is a system in which, when a user inputs a question, a server uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusts it according to the user's emotions, and then sends a response to the user.

[0540] This system uses the following hardware and software:

[0541] A device (PC, smartphone, tablet, etc.) for the user to enter questions.

[0542] A server that receives and processes question and sentiment data.

[0543] Generative artificial intelligence for generating answers (e.g., GPT-3)

[0544] An emotion engine that analyzes user emotions and adjusts responses accordingly.

[0545] A means of communication for exchanging data (HTTP POST request)

[0546] The user enters a question into a text field on their device and clicks the "Submit Question" button. At this point, a script on the device, such as JavaScript, retrieves the question entered by the user and analyzes the user's emotions using an emotion engine.

[0547] The analysis results and question content are serialized in JSON format and sent as an HTTP POST request to a specific API endpoint on the server. The server receives this request, analyzes its contents, and extracts the question and sentiment data.

[0548] The server provides the question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the results of the emotion analysis.

[0549] For example, if a user types "My internet connection is slow, what should I do?", the emotion engine might detect the user's frustration. The generative AI would respond to this prompt as follows:

[0550] "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed."

[0551] The server formats the generated responses into JSON format and adjusts them based on the analysis results from the sentiment engine. The adjusted responses are sent to the terminal as an HTTP response. The terminal receives this HTTP response, extracts the response text from the JSON data, and displays it on the user's screen.

[0552] This allows users to receive quick, high-quality answers, and because those answers take into account specific emotional states, the user experience is significantly improved.

[0553] The above describes specific embodiments for carrying out this invention.

[0554] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0555] Step 1:

[0556] The user enters their question in the text field on their device and clicks the "Submit Question" button.

[0557] Input: User-entered question text (e.g., "My internet connection is slow, what should I do?")

[0558] Output: The terminal detects the user's question submission operation.

[0559] Step 2:

[0560] The device uses scripts such as JavaScript to retrieve questions entered by the user. It also uses an emotion engine to analyze the user's emotions.

[0561] Input: Question text entered by the user

[0562] Output: Question text and sentiment data (e.g., "frustration")

[0563] Specific operation: The terminal captures text from the user's question input field and calls the sentiment engine to analyze the sentiment. After obtaining the analysis results, it serializes the question content and sentiment data into JSON format.

[0564] Step 3:

[0565] The device serializes the question content and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[0566] Input: Question text and sentiment data (in JSON format)

[0567] Output: HTTP POST request to the server

[0568] Specific operation: The terminal creates an HTTP POST request, including the question content and sentiment data in the request body. The request is sent to a specific API endpoint on the server.

[0569] Step 4:

[0570] The server receives an HTTP POST request sent from the terminal. It extracts the question content and sentiment data from the request body.

[0571] Input: HTTP POST request

[0572] Output: Questionnaire text and sentiment data

[0573] Specific operation: The server parses the body of the received request and extracts the question content and sentiment data sent in JSON format. This data is stored internally.

[0574] Step 5:

[0575] The server provides the received question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[0576] Input: Question text, sentiment data

[0577] Output: Responses from generative artificial intelligence, analysis results from the emotion engine.

[0578] Specific operation: The server passes the question content to the generative artificial intelligence, providing a prompt such as "User question: My internet connection is slow, what should I do?". The generative AI generates an answer based on this prompt. Meanwhile, the server provides sentiment data to the sentiment engine and obtains the sentiment analysis results.

[0579] Step 6:

[0580] The server adjusts the generated responses based on the results of the sentiment engine and formats the adjusted responses into JSON format.

[0581] Input: Response from generative artificial intelligence, emotion analysis results

[0582] Output: Adjusted response in JSON format

[0583] Specific operation: The system adjusts the response generated by the generative AI (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have them check your connection speed.") and formats the result into JSON format.

[0584] Step 7:

[0585] The server sends the adjusted response in JSON format to the terminal as an HTTP response.

[0586] Input: Adjusted response (JSON format)

[0587] Output: HTTP response to the terminal

[0588] Specific operation: The server includes JSON data containing the adjusted response in the HTTP response and sends it to the terminal.

[0589] Step 8:

[0590] The terminal receives an HTTP response from the server, parses the JSON data from the response body, and extracts the generated response text. The terminal then displays the extracted response text on the user's screen.

[0591] Input: HTTP response

[0592] Output: Response text displayed to the user

[0593] Specific operation: The terminal analyzes the response from the server, extracts the response text generated from the JSON data (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have your connection speed checked."), and displays it on the user's screen.

[0594] (Application Example 2)

[0595] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0596] Conventional question answering systems often fail to consider user emotions when generating responses, making it difficult to provide quick and appropriate answers. This is especially true in areas where user anxiety is high, such as security services, where emotion-based adjustments are crucial. However, current systems lack such emotion-adjusting capabilities, highlighting the need for improved user experience.

[0597] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing the user's emotions using an emotion engine and adjusting the response based on the results, means for formatting the response from the generative artificial intelligence into JSON format, and means for using an HTTP POST request when the terminal sends the user's question. This makes it possible to provide an appropriate and prompt response that takes the user's emotions into consideration.

[0598] A "user" refers to a person who uses the system.

[0599] "Means for entering questions" refers to an interface for users to enter questions as text.

[0600] A "terminal" refers to a computing device used by a user to input questions, and this includes PCs, smartphones, tablets, and other similar devices.

[0601] "Means by which a terminal obtains user-entered questions and sends them to a server" refers to software or a protocol for transferring user-entered questions from the terminal to the server.

[0602] A "server" refers to a computer device that receives and processes queries.

[0603] "Generative artificial intelligence" refers to an artificial intelligence model that generates appropriate answers to given questions.

[0604] "Means of providing information to a generative artificial intelligence" refers to the process by which a server distributes questions received from a user to a generative artificial intelligence.

[0605] An "emotion engine" refers to an algorithm or software that analyzes a user's emotions and adjusts responses based on the results.

[0606] "A means of analyzing a user's emotions using an emotion engine and adjusting the response based on the results" refers to a mechanism that modifies the generated response based on the user's emotions.

[0607] "Means of returning the generated response to the user via the server" refers to the process of returning the generated response to the terminal via the server.

[0608] "Means of displaying the response received by the device to the user" refers to the process of displaying the response received by the device on the user's screen.

[0609] "Methods for formatting into JSON format" refers to software processing for converting the generated response into JSON (JavaScript Object Notation) format.

[0610] "Using an HTTP POST request" refers to the process of sending user query data to a server using the POST method of the HTTP protocol.

[0611] This invention is a system that, upon receiving a question from a user, uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusting it according to the user's emotions before responding. This invention is particularly intended for application in the field of security services, enabling a rapid and appropriate response to user anxieties and questions.

[0612] System Overview

[0613] User:

[0614] Users enter their questions into a text field from devices such as PCs, smartphones, and tablets. For example, a user might enter the question, "I've been receiving a lot of phishing emails lately; what should I do about it?"

[0615] Terminal:

[0616] The terminal uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, each terminal has an emotion engine built in to analyze the user's emotions. As a result, the question content and emotion data are serialized in JSON format and an HTTP POST request is sent to a specific API endpoint on the server.

[0617] server:

[0618] The server receives an HTTP POST request sent from the terminal and extracts the question content and sentiment data from the request body. The extracted question content is provided as a prompt to the generative artificial intelligence, which then performs text generation processing based on that prompt. Commonly used APIs (e.g., OpenAI's GPT model) can be used as the generative AI.

[0619] Furthermore, the server incorporates an emotion engine that adjusts responses based on the results of analyzing emotional data. This adjustment uses software like EmotionEngine to modify the tone and content to suit the user's emotions.

[0620] Generating and refining responses:

[0621] Generative artificial intelligence generates answers based on the provided questions. Then, an emotion engine adjusts those answers to match the user's emotional state, formatting them into the most appropriate wording. For example, if the user is feeling anxious, the answer will be revised to be more kind and polite.

[0622] Sending and displaying responses:

[0623] The server formats the generated response text into JSON format, combines it with the results adjusted by the sentiment engine, and sends the JSON data to the terminal as an HTTP response. The terminal receives the HTTP response from the server, parses the JSON data from the response body, extracts the generated response text, and displays it on the user's screen.

[0624] Specific examples

[0625] The user uses their smartphone to enter the following question into a dedicated application: "I've been receiving a lot of phishing emails lately. How should I deal with them?"

[0626] This question is first sent from the device to the server. During transmission, the emotion engine detects the user's anxiety, and this information is also sent along with the question.

[0627] The server provides question and sentiment data to a generative artificial intelligence. For example, OpenAI's GPT model is used.

[0628] • Generative artificial intelligence generates answers to questions. Then, an emotion engine modifies the answers to make them kind and polite.

[0629] The corrected response is formatted in JSON format and sent back to the terminal as an HTTP response.

[0630] • Finally, the device displays the received response on the user's screen. For example, a response might be displayed such as, "First, it's important not to open emails from unknown senders. Also, avoid clicking on links in emails. Furthermore, we recommend reporting phishing emails to your ISP or security provider."

[0631] This system allows users to receive quick and appropriate answers, particularly addressing security-related concerns.

[0632] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0633] Step 1:

[0634] The user enters their question into the text field on their device and clicks the "Submit Question" button. The input here is the user entering a specific question as text.

[0635] Step 2:

[0636] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, the device's built-in sentiment engine analyzes the user's emotions and retrieves sentiment data. This question content and sentiment data are serialized into JSON format, and an HTTP POST request is sent to a specific API endpoint on the server. Specifically, the input is the user's question text and the sentiment analysis results, while the output is the data sent to the server.

[0637] Step 3:

[0638] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body. Specifically, it parses the question text and sentiment data from the JSON data and converts them into a usable format.

[0639] Step 4:

[0640] The server provides the received question content as a prompt to the generative artificial intelligence (AI). The generative AI uses this prompt to perform text generation processing and generate the answer text. For example, an open AI API such as GPT-3 is used as the generative AI. The input for this step is the question text, and the output is the generated answer text.

[0641] Step 5:

[0642] The server provides sentiment data to the sentiment engine and retrieves the sentiment analysis results again. The sentiment engine adjusts the generated response based on this data, modifying it to match the user's sentiment. The input for this step is the generated response text and sentiment data, and the output is the adjusted response text.

[0643] Step 6:

[0644] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response. The input for this step is the adjusted response text, and the output is the JSON data response from the server to the terminal.

[0645] Step 7:

[0646] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen. The input for this step is the response data in JSON format, and the output is the response text displayed on the user's screen.

[0647] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0648] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0649] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0650] [Third Embodiment]

[0651] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0652] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0653] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0654] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0655] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0656] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0657] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0658] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0659] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0660] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0661] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0662] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0663] This invention relates to a system in which, when a user inputs a question through a terminal, a server uses generative artificial intelligence to generate an appropriate answer to that question and sends it back to the user.

[0664] System Overview

[0665] This system includes means for a user to input a question, means for a terminal to send a question to a server, means for the server to receive the question and provide it to a generative artificial intelligence, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0666] Operation of each component

[0667] 1. User actions:

[0668] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0669] 2. Obtaining and submitting questions:

[0670] The terminal uses a script such as JavaScript to retrieve the question entered by the user. It then sends this question to the server as an HTTP POST request.

[0671] 3. Receiving the question:

[0672] The server receives an HTTP POST request sent from the terminal. This request arrives at the server as data in JSON format.

[0673] 4. Provision to generative artificial intelligence:

[0674] The server passes the received question as a prompt to the generative artificial intelligence. Based on this prompt, the generative AI generates an appropriate answer.

[0675] 5. Generating the answer:

[0676] Generative artificial intelligence generates answers to questions in text format. This generation process is carried out using a pre-trained model.

[0677] 6. Return your response:

[0678] The server formats the response received from the generative artificial intelligence into JSON format. Then, it sends this JSON-formatted response back to the terminal as an HTTP response.

[0679] 7. Display the answer:

[0680] The terminal receives an HTTP response from the server and extracts the answer from the JSON-formatted data. The extracted answer text is then displayed on the user's screen.

[0681] Specific examples

[0682] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is sent to the server, and a generative artificial intelligence generates an answer. The generated answer is displayed on the user's device as specific and practical advice, such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0683] Technical effects

[0684] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality.

[0685] The specific operation and utilization techniques of each means in this invention can be modified as appropriate based on the system design and implementation, and this flexibility is also one of the advantages of this invention.

[0686] The following describes the processing flow.

[0687] Step 1:

[0688] The user enters a question into the terminal's text field. The terminal provides an interface for the user to enter a question.

[0689] Step 2:

[0690] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user.

[0691] Step 3:

[0692] The device serializes the question it obtains into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content.

[0693] Step 4:

[0694] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content from the request body.

[0695] Step 5:

[0696] The server provides the question content as a prompt to the generative artificial intelligence. The generative artificial intelligence then performs text generation processing based on the given prompt.

[0697] Step 6:

[0698] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[0699] Step 7:

[0700] The server formats the response text received from the generative artificial intelligence into JSON format. The formatted JSON data is then sent to the terminal as an HTTP response.

[0701] Step 8:

[0702] The terminal receives an HTTP response from the server. The JSON data is parsed from the response body, and the generated response text is extracted.

[0703] Step 9:

[0704] The device displays the extracted answer text to the user. The user can then review the answer displayed on the screen.

[0705] (Example 1)

[0706] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0707] Traditional systems often involved long waiting times between a user entering a question and receiving an answer. Furthermore, their reliance on manual responses meant inconsistent and unpredictable response quality. Additionally, mechanisms for quickly generating appropriate answers were inadequately developed.

[0708] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0709] In this invention, the server includes means for providing acquired questions to a generative artificial intelligence model to generate answers to those questions, means for formatting the response from the generative artificial intelligence model into a data format, and means for using a data transmission request when a terminal sends a user's question. This makes it possible to provide users with fast, consistent, and high-quality answers.

[0710] A "user" is an individual or organization that uses this system to input questions and receive answers.

[0711] A "terminal" is a device used by users to input questions and send and receive data to and from a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0712] A "server" is a central system that receives questions sent from terminals, provides them as prompts to generative artificial intelligence models, and sends the generated answers back to the terminals.

[0713] A "generative artificial intelligence model" is a pre-trained deep learning model or algorithm that generates appropriate answers based on received prompts (questions).

[0714] A "prompt" is the text of a question or instruction that is input to a generative artificial intelligence model.

[0715] "Data format" refers to the structure and format of the data that the server uses to organize the response from a generative artificial intelligence model and send it back to the terminal.

[0716] A "data transmission request" refers to a communication protocol, such as an HTTP POST request, used to send a user's question from their device to a server.

[0717] The present invention relates to a system in which a user inputs a question through a terminal, and a server generates an appropriate answer to that question using a generative artificial intelligence model and sends it back to the user. This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to the generative artificial intelligence model, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0718] The user opens a web browser on their device (e.g., personal computer, smartphone, tablet) and enters a question in the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" When the user clicks the "Submit Question" button, the device retrieves the question and sends it to the server as an HTTP POST request using JavaScript. The data is sent in JSON format. The programming languages ​​and tools used are JavaScript, HTML, and HTTP.

[0719] The server listens for HTTP POST requests at a configured endpoint and parses the JSON data in the request body. The server provides the retrieved question as a prompt to a generative artificial intelligence model, which then generates an appropriate answer. This generative AI model could be a general deep learning model (e.g., GPT-3, BERT). These models are pre-trained on large amounts of text data and have the ability to generate highly accurate answers. The server accesses these generative AI models using a programming language such as Python.

[0720] Once a generative artificial intelligence model generates a response, the server formats the response into a data format and sends it back to the terminal as an HTTP response. For example, the reformatted data is often in JSON format. The server runs on a web server (e.g., Apache, Nginx) and uses languages ​​such as Python or Node.js.

[0721] The terminal receives an HTTP response from the server and extracts the answer text from the JSON data. Then, it uses JavaScript in the web browser to display the answer on the user's screen. For example, it might display specific and practical advice such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0722] This system allows users to obtain fast, consistent, and high-quality answers. While traditional methods required manual responses from human staff, the use of generative artificial intelligence models enables instant responses, significantly improving the user experience. Furthermore, the consistent quality of responses is ensured by the generative AI models.

[0723] The embodiments of this invention are configured flexibly and can be modified as appropriate based on specific system designs and implementations.

[0724] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0725] Step 1:

[0726] The user enters a question.

[0727] In terms of the specific operation, the user opens a web browser on their device (PC, smartphone, or tablet) and enters a question into the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" The input is saved as text data on the device.

[0728] Step 2:

[0729] The device retrieves and sends the question.

[0730] Specifically, when the user clicks the "Submit Question" button, the device uses JavaScript to retrieve the question from the text field. This question data is converted to JSON format and sent to the server as an HTTP POST request. The input is the user's question, and the output is the HTTP POST request to the server.

[0731] Step 3:

[0732] The server receives the question.

[0733] In terms of operation, the server listens for HTTP POST requests at the configured endpoint. Upon receiving a request sent from the terminal, the server parses the JSON data in the request body and extracts the question text. The input is the HTTP POST request, and the output is the parsed question text.

[0734] Step 4:

[0735] The server provides prompts to the generative artificial intelligence.

[0736] In terms of operation, the analyzed question text is provided to a generative artificial intelligence model as a prompt. The server generates an API request and sends it to the generative AI model. The generative AI model used is pre-trained on large amounts of text data (e.g., GPT-3, BERT). The input is the question text, and the output is the API request to the generative AI model.

[0737] Step 5:

[0738] A generative artificial intelligence generates the answer.

[0739] In terms of operation, a generative artificial intelligence model generates an appropriate response based on the input prompt. This response process is carried out via a deep learning algorithm. The generated response is returned to the server in text format. The input is the prompt, and the output is the response in text format.

[0740] Step 6:

[0741] The server formats the response and sends it back.

[0742] In terms of operation, the server formats the response received from the generative artificial intelligence model into JSON format and sends it back to the terminal as an HTTP response. The input is a text-formatted response, and the output is an HTTP response (in JSON format) sent to the terminal.

[0743] Step 7:

[0744] The device will display the answer.

[0745] In terms of specific operation, the terminal receives an HTTP response from the server and extracts the answer text from the JSON data. JavaScript in the web browser is then used to display the answer on the user's screen. For example, specific and practical advice such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have your connection speed checked," might be displayed. The input is the HTTP response, and the output is the displayed text.

[0746] (Application Example 1)

[0747] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0748] In recent years, there has been a growing demand for faster and more efficient customer support in virtual stores. However, traditional systems require staff to manually search for and provide answers to customer questions, often resulting in long response times. This has led to decreased customer satisfaction. Furthermore, there has been a lack of technology to enable natural conversations using voice input.

[0749] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0750] In this invention, the server includes means for the user to input a question, means for a terminal to acquire the question input by the user and send it to the server, means for the server to provide the acquired question to a generative artificial intelligence to generate an answer to the question, means for sending the generated answer back to the user via the server, means for the terminal to display the received answer to the user, means for a smart device to acquire a question through voice input, and means for displaying the generated answer on the smart device's display. This makes it possible to provide quick and accurate answers to customer questions in a virtual store.

[0751] A "user" is someone who uses the system to input questions and receive the generated answers.

[0752] A "terminal" is a device operated by the user, which is used for inputting, retrieving, and sending questions to the server, as well as receiving and displaying answers from the server.

[0753] A "server" is a device that receives questions sent from a terminal and provides them to a generative artificial intelligence system, and is responsible for sending the generated answers back to the user.

[0754] "Generative artificial intelligence" is an artificial intelligence technology that generates appropriate answers based on a given question.

[0755] An "answer" is a response to a user's question, generated by a generative artificial intelligence system.

[0756] A "smart device" is an advanced device that has the function of obtaining questions through voice input and displaying the generated answers on a screen.

[0757] "Voice input" is a method of acquiring the user's voice through the microphone of a smart device and converting that voice data into text format.

[0758] A "display" is the screen installed in a smart device that visually presents the generated response to the user.

[0759] An "HTTP POST request" is one of the internet communication protocols used to send data from a terminal to a server.

[0760] The system based on this invention allows the user to input a question via a terminal, and provides an appropriate answer using generative artificial intelligence. The following hardware and software are used to realize this system.

[0761] First, the user inputs a question using a smart device (e.g., smart glasses). This question is captured as voice input and converted into text format using a speech recognition library. Specifically, the speech_recognition library is used. The smart device includes a microphone for capturing voice input and a display for showing the captured response.

[0762] The terminal converts the question into text format and then sends the data to the server. This transmission uses the HTTP POST request, an internet communication protocol. The sent question arrives at the server as JSON data.

[0763] The server provides the received question as a prompt to a generative artificial intelligence (AI). This AI uses an advanced language model (e.g., GPT-3). The AI ​​generates an appropriate response to the received prompt and sends that response back to the server.

[0764] The server formats the generated response into JSON format and sends it back to the device as an HTTP response. The device receives the response from the server, extracts the answer from the JSON data, and displays it on the smart device's display.

[0765] As a concrete example, if a user asks, "Is this item in stock?", this question is picked up through the smart glasses' microphone and converted into text using speech recognition. The converted text is then sent to a server, where generative artificial intelligence generates an answer. The generated answer, "This item is in stock. You can purchase it now," is displayed on the smart glasses' screen and provided to the user.

[0766] This system enables the provision of quick and accurate answers in virtual stores, significantly improving customer satisfaction.

[0767] The following are examples of prompts provided to generative artificial intelligence:

[0768] "A customer asked, 'Do you have this item in stock?' Please provide the best possible answer."

[0769] This prompt can be used by a generative artificial intelligence to generate the optimal answer to the user's question.

[0770] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0771] Step 1:

[0772] The user inputs a question using a smart device (e.g., smart glasses). This question is entered in voice format. Voice data is captured through the smart device's microphone. This is the input for Step 1. This voice data is then passed on to the subsequent speech recognition process.

[0773] Step 2:

[0774] The smart device converts the acquired audio data into text format using a speech recognition library. The library used in this step is speech_recognition. The speech recognition library converts the audio data into text data, and the converted text becomes the output of step 2.

[0775] Step 3:

[0776] The terminal sends the question, converted to text format, to the server via an HTTP POST request. This text data is packaged in JSON format and sent to the server over the internet. The sent JSON data is the output of step 3.

[0777] Step 4:

[0778] The server receives an HTTP POST request from the terminal. This request contains the user's question in JSON format. The server parses this JSON data and extracts the question. The extracted question is the output of step 4.

[0779] Step 5:

[0780] The server provides the extracted questions as prompts to the generative artificial intelligence. This generative AI uses an advanced language model (e.g., GPT-3). By passing the questions as prompts to the AI, the AI ​​generates the optimal answer. The generated answer is the output of step 5.

[0781] Step 6:

[0782] The server formats the response received from the generative artificial intelligence into JSON format. The formatted JSON data is prepared for return to the user's terminal. This formatted JSON data is the output of step 6.

[0783] Step 7:

[0784] The terminal receives an HTTP response from the server. This response contains the answer generated by the generative artificial intelligence in JSON format. The terminal parses this JSON data and extracts the answer. The extracted answer is the output of step 7.

[0785] Step 8:

[0786] The smart device displays the extracted answers on its screen, allowing the user to visually confirm the answers to the questions. The answers displayed on the screen are the output of step 8.

[0787] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0788] This invention relates to a system in which, when a user inputs a question through a terminal, a server generates an appropriate answer to that question using generative artificial intelligence and an emotion engine, adjusts it according to the user's emotions, and then sends a response to the user.

[0789] System Overview

[0790] This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to a generative artificial intelligence and an emotion engine, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user. Furthermore, it also includes means for using the emotion engine to analyze the user's emotions and adjusting the answer based on the results.

[0791] Operation of each component

[0792] 1. User actions:

[0793] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0794] 2. Obtaining and submitting questions:

[0795] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, it uses an emotion engine to analyze the user's emotions and retrieves the results. Finally, it serializes the question content and emotion data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[0796] 3. Receiving the question:

[0797] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body.

[0798] 4. Provisions to generative artificial intelligence and emotion engines:

[0799] The server provides the received question content as a prompt to the generative artificial intelligence. The generative AI performs text generation processing based on this prompt. At the same time, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[0800] 5. Generating and refining responses:

[0801] A generative artificial intelligence generates answers based on the provided questions. Furthermore, the server appropriately adjusts the generated answers based on sentiment data analyzed by an emotion engine.

[0802] 6. Return your response:

[0803] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response.

[0804] 7. Display the answer:

[0805] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen.

[0806] Specific examples

[0807] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is analyzed by an emotion engine before being sent to the server. If the emotion engine detects the user's frustration, the generative artificial intelligence generates a response that is specific and practical advice, such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed," and it is delivered in a friendly tone that is adjusted according to the user's emotions. In this way, the user experience is improved.

[0808] Technical effects

[0809] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality. Additionally, responses that consider the user's emotions are provided, increasing user satisfaction.

[0810] The following describes the processing flow.

[0811] Step 1:

[0812] The user enters the question into the terminal's text field. The terminal provides an interface for the user to enter the question.

[0813] Step 2:

[0814] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user. At this point, the emotion engine also analyzes the user's facial expressions and voice tone using the device's camera and microphone.

[0815] Step 3:

[0816] The emotion engine generates emotional data from the user's input, facial expressions, and tone of voice. This emotional data includes whether the user is feeling stress, anxiety, joy, etc.

[0817] Step 4:

[0818] The device serializes the acquired question and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content and sentiment data.

[0819] Step 5:

[0820] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content and sentiment data from the request body.

[0821] Step 6:

[0822] The server extracts questions and provides them as prompts to the generative artificial intelligence. The generative AI then uses these prompts to perform text generation processing.

[0823] Step 7:

[0824] The server provides emotional data to the emotion engine, which further analyzes the user's emotional state. The emotion engine processes the emotional data and generates the emotional analysis results.

[0825] Step 8:

[0826] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[0827] Step 9:

[0828] The server combines the response text received from the generative artificial intelligence with the results of the emotion engine's analysis. Based on the emotion analysis results, the response is appropriately adjusted. For example, if the user is feeling stressed, the response will be made more polite and kind.

[0829] Step 10:

[0830] The server formats the adjusted response into JSON format. Then, it sends the JSON data containing the adjusted response to the terminal as an HTTP response.

[0831] Step 11:

[0832] The terminal receives an HTTP response from the server. It then parses the JSON data from the response body and extracts the generated response text.

[0833] Step 12:

[0834] The device displays the extracted response text to the user. The user can then see the response, which has been adjusted according to their emotions.

[0835] (Example 2)

[0836] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0837] Traditional response generation systems often provided answers without considering the user's emotions, resulting in a poor user experience. In particular, it was difficult to provide appropriate answers when users were feeling anxious or frustrated. Furthermore, the quality of responses was often inconsistent, leading to decreased user satisfaction.

[0838] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0839] In this invention, the server includes means for providing a question to a generative artificial intelligence and generating an answer to the question, means for adjusting the generated answer based on the user's emotions using an emotion engine, and means for returning the adjusted answer to the user via the server. This makes it possible to provide consistent, high-quality answers that take the user's emotions into consideration.

[0840] A "user" is an individual or organization that uses this system to input questions and receive answers.

[0841] A "device" is a device used by a user to input questions or view answers, and includes PCs, smartphones, tablets, and other similar devices.

[0842] A "server" is a central processing unit that receives user questions, generates and refines answers using generative artificial intelligence and an emotion engine, and sends them back to the user.

[0843] "Generative artificial intelligence" refers to artificial intelligence models that can generate answers in natural language to user questions. Examples include GPT-3.

[0844] An "emotion engine" is software or an algorithm that analyzes emotional data obtained from users and adjusts the responses generated based on the results.

[0845] JSON format is a lightweight data exchange format for storing and transferring data as text, and it is an abbreviation for JavaScript Object Notation.

[0846] An "HTTP POST request" is one of the HTTP methods used to send and receive data between a server and another server.

[0847] "Emotional data" refers to the analysis results that indicate the user's emotional state, including, for example, whether the user is feeling frustrated.

[0848] A "prompt" is an input sentence that provides information, such as the content of a question, to a generative artificial intelligence system in order to generate a specific answer.

[0849] "Answer" refers to information or advice generated by a generative artificial intelligence system based on the user's question.

[0850] This invention is a system in which, when a user inputs a question, a server uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusts it according to the user's emotions, and then sends a response to the user.

[0851] This system uses the following hardware and software:

[0852] A device (PC, smartphone, tablet, etc.) for the user to enter questions.

[0853] A server that receives and processes question and sentiment data.

[0854] Generative artificial intelligence for generating answers (e.g., GPT-3)

[0855] An emotion engine that analyzes user emotions and adjusts responses accordingly.

[0856] A means of communication for exchanging data (HTTP POST request)

[0857] The user enters a question into a text field on their device and clicks the "Submit Question" button. At this point, a script on the device, such as JavaScript, retrieves the question entered by the user and analyzes the user's emotions using an emotion engine.

[0858] The analysis results and question content are serialized in JSON format and sent as an HTTP POST request to a specific API endpoint on the server. The server receives this request, analyzes its contents, and extracts the question and sentiment data.

[0859] The server provides the question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the results of the emotion analysis.

[0860] For example, if a user types "My internet connection is slow, what should I do?", the emotion engine might detect the user's frustration. The generative AI would respond to this prompt as follows:

[0861] "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed."

[0862] The server formats the generated responses into JSON format and adjusts them based on the analysis results from the sentiment engine. The adjusted responses are sent to the terminal as an HTTP response. The terminal receives this HTTP response, extracts the response text from the JSON data, and displays it on the user's screen.

[0863] This allows users to receive quick, high-quality answers, and because those answers take into account specific emotional states, the user experience is significantly improved.

[0864] The above describes specific embodiments for carrying out this invention.

[0865] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0866] Step 1:

[0867] The user enters their question in the text field on their device and clicks the "Submit Question" button.

[0868] Input: User-entered question text (e.g., "My internet connection is slow, what should I do?")

[0869] Output: The terminal detects the user's question submission operation.

[0870] Step 2:

[0871] The device uses scripts such as JavaScript to retrieve questions entered by the user. It also uses an emotion engine to analyze the user's emotions.

[0872] Input: Question text entered by the user

[0873] Output: Question text and sentiment data (e.g., "frustration")

[0874] Specific operation: The terminal captures text from the user's question input field and calls the sentiment engine to analyze the sentiment. After obtaining the analysis results, it serializes the question content and sentiment data into JSON format.

[0875] Step 3:

[0876] The device serializes the question content and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[0877] Input: Question text and sentiment data (in JSON format)

[0878] Output: HTTP POST request to the server

[0879] Specific operation: The terminal creates an HTTP POST request, including the question content and sentiment data in the request body. The request is sent to a specific API endpoint on the server.

[0880] Step 4:

[0881] The server receives an HTTP POST request sent from the terminal. It extracts the question content and sentiment data from the request body.

[0882] Input: HTTP POST request

[0883] Output: Questionnaire text and sentiment data

[0884] Specific operation: The server parses the body of the received request and extracts the question content and sentiment data sent in JSON format. This data is stored internally.

[0885] Step 5:

[0886] The server provides the received question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[0887] Input: Question text, sentiment data

[0888] Output: Responses from generative artificial intelligence, analysis results from the emotion engine.

[0889] Specific operation: The server passes the question content to the generative artificial intelligence, providing a prompt such as "User question: My internet connection is slow, what should I do?". The generative AI generates an answer based on this prompt. Meanwhile, the server provides sentiment data to the sentiment engine and obtains the sentiment analysis results.

[0890] Step 6:

[0891] The server adjusts the generated responses based on the results of the sentiment engine and formats the adjusted responses into JSON format.

[0892] Input: Response from generative artificial intelligence, emotion analysis results

[0893] Output: Adjusted response in JSON format

[0894] Specific operation: The system adjusts the response generated by the generative AI (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have them check your connection speed.") and formats the result into JSON format.

[0895] Step 7:

[0896] The server sends the adjusted response in JSON format to the terminal as an HTTP response.

[0897] Input: Adjusted response (JSON format)

[0898] Output: HTTP response to the terminal

[0899] Specific operation: The server includes JSON data containing the adjusted response in the HTTP response and sends it to the terminal.

[0900] Step 8:

[0901] The terminal receives an HTTP response from the server, parses the JSON data from the response body, and extracts the generated response text. The terminal then displays the extracted response text on the user's screen.

[0902] Input: HTTP response

[0903] Output: Response text displayed to the user

[0904] Specific operation: The terminal analyzes the response from the server, extracts the response text generated from the JSON data (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have your connection speed checked."), and displays it on the user's screen.

[0905] (Application Example 2)

[0906] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0907] Conventional question answering systems often fail to consider user emotions when generating responses, making it difficult to provide quick and appropriate answers. This is especially true in areas where user anxiety is high, such as security services, where emotion-based adjustments are crucial. However, current systems lack such emotion-adjusting capabilities, highlighting the need for improved user experience.

[0908] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing the user's emotions using an emotion engine and adjusting the response based on the results, means for formatting the response from the generative artificial intelligence into JSON format, and means for using an HTTP POST request when the terminal sends the user's question. This makes it possible to provide an appropriate and prompt response that takes the user's emotions into consideration.

[0909] A "user" refers to a person who uses the system.

[0910] "Means for entering questions" refers to an interface for users to enter questions as text.

[0911] A "terminal" refers to a computing device used by a user to input questions, and this includes PCs, smartphones, tablets, and other similar devices.

[0912] "Means by which a terminal obtains user-entered questions and sends them to a server" refers to software or a protocol for transferring user-entered questions from the terminal to the server.

[0913] A "server" refers to a computer device that receives and processes queries.

[0914] "Generative artificial intelligence" refers to an artificial intelligence model that generates appropriate answers to given questions.

[0915] "Means of providing information to a generative artificial intelligence" refers to the process by which a server distributes questions received from a user to a generative artificial intelligence.

[0916] An "emotion engine" refers to an algorithm or software that analyzes a user's emotions and adjusts responses based on the results.

[0917] "A means of analyzing a user's emotions using an emotion engine and adjusting the response based on the results" refers to a mechanism that modifies the generated response based on the user's emotions.

[0918] "Means of returning the generated response to the user via the server" refers to the process of returning the generated response to the terminal via the server.

[0919] "Means of displaying the response received by the device to the user" refers to the process of displaying the response received by the device on the user's screen.

[0920] "Methods for formatting into JSON format" refers to software processing for converting the generated response into JSON (JavaScript Object Notation) format.

[0921] "Using an HTTP POST request" refers to the process of sending user query data to a server using the POST method of the HTTP protocol.

[0922] This invention is a system that, upon receiving a question from a user, uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusting it according to the user's emotions before responding. This invention is particularly intended for application in the field of security services, enabling a rapid and appropriate response to user anxieties and questions.

[0923] System Overview

[0924] User:

[0925] Users enter their questions into a text field from devices such as PCs, smartphones, and tablets. For example, a user might enter the question, "I've been receiving a lot of phishing emails lately; what should I do about it?"

[0926] Terminal:

[0927] The terminal uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, each terminal has an emotion engine built in to analyze the user's emotions. As a result, the question content and emotion data are serialized in JSON format and an HTTP POST request is sent to a specific API endpoint on the server.

[0928] server:

[0929] The server receives an HTTP POST request sent from the terminal and extracts the question content and sentiment data from the request body. The extracted question content is provided as a prompt to the generative artificial intelligence, which then performs text generation processing based on that prompt. Commonly used APIs (e.g., OpenAI's GPT model) can be used as the generative AI.

[0930] Furthermore, the server incorporates an emotion engine that adjusts responses based on the results of analyzing emotional data. This adjustment uses software like EmotionEngine to modify the tone and content to suit the user's emotions.

[0931] Generating and refining responses:

[0932] Generative artificial intelligence generates answers based on the provided questions. Then, an emotion engine adjusts those answers to match the user's emotional state, formatting them into the most appropriate wording. For example, if the user is feeling anxious, the answer will be revised to be more kind and polite.

[0933] Sending and displaying responses:

[0934] The server formats the generated response text into JSON format, combines it with the results adjusted by the sentiment engine, and sends the JSON data to the terminal as an HTTP response. The terminal receives the HTTP response from the server, parses the JSON data from the response body, extracts the generated response text, and displays it on the user's screen.

[0935] Specific examples

[0936] The user uses their smartphone to enter the following question into a dedicated application: "I've been receiving a lot of phishing emails lately. How should I deal with them?"

[0937] This question is first sent from the device to the server. During transmission, the emotion engine detects the user's anxiety, and this information is also sent along with the question.

[0938] The server provides question and sentiment data to a generative artificial intelligence. For example, OpenAI's GPT model is used.

[0939] • Generative artificial intelligence generates answers to questions. Then, an emotion engine modifies the answers to make them kind and polite.

[0940] The corrected response is formatted in JSON format and sent back to the terminal as an HTTP response.

[0941] • Finally, the device displays the received response on the user's screen. For example, a response might be displayed such as, "First, it's important not to open emails from unknown senders. Also, avoid clicking on links in emails. Furthermore, we recommend reporting phishing emails to your ISP or security provider."

[0942] This system allows users to receive quick and appropriate answers, particularly addressing security-related concerns.

[0943] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0944] Step 1:

[0945] The user enters their question into the text field on their device and clicks the "Submit Question" button. The input here is the user entering a specific question as text.

[0946] Step 2:

[0947] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, the device's built-in sentiment engine analyzes the user's emotions and retrieves sentiment data. This question content and sentiment data are serialized into JSON format, and an HTTP POST request is sent to a specific API endpoint on the server. Specifically, the input is the user's question text and the sentiment analysis results, while the output is the data sent to the server.

[0948] Step 3:

[0949] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body. Specifically, it parses the question text and sentiment data from the JSON data and converts them into a usable format.

[0950] Step 4:

[0951] The server provides the received question content as a prompt to the generative artificial intelligence (AI). The generative AI uses this prompt to perform text generation processing and generate the answer text. For example, an open AI API such as GPT-3 is used as the generative AI. The input for this step is the question text, and the output is the generated answer text.

[0952] Step 5:

[0953] The server provides sentiment data to the sentiment engine and retrieves the sentiment analysis results again. The sentiment engine adjusts the generated response based on this data, modifying it to match the user's sentiment. The input for this step is the generated response text and sentiment data, and the output is the adjusted response text.

[0954] Step 6:

[0955] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response. The input for this step is the adjusted response text, and the output is the JSON data response from the server to the terminal.

[0956] Step 7:

[0957] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen. The input for this step is the response data in JSON format, and the output is the response text displayed on the user's screen.

[0958] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0959] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0960] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0961] [Fourth Embodiment]

[0962] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0963] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0964] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0965] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0966] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0967] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0968] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0969] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0970] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0971] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0972] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0973] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0974] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0975] This invention relates to a system in which, when a user inputs a question through a terminal, a server uses generative artificial intelligence to generate an appropriate answer to that question and sends it back to the user.

[0976] System Overview

[0977] This system includes means for a user to input a question, means for a terminal to send a question to a server, means for the server to receive the question and provide it to a generative artificial intelligence, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[0978] Operation of each component

[0979] 1. User actions:

[0980] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[0981] 2. Obtaining and submitting questions:

[0982] The terminal uses a script such as JavaScript to retrieve the question entered by the user. It then sends this question to the server as an HTTP POST request.

[0983] 3. Receiving the question:

[0984] The server receives an HTTP POST request sent from the terminal. This request arrives at the server as data in JSON format.

[0985] 4. Provision to generative artificial intelligence:

[0986] The server passes the received question as a prompt to the generative artificial intelligence. Based on this prompt, the generative AI generates an appropriate answer.

[0987] 5. Generating the answer:

[0988] Generative artificial intelligence generates answers to questions in text format. This generation process is carried out using a pre-trained model.

[0989] 6. Return your response:

[0990] The server formats the response received from the generative artificial intelligence into JSON format. Then, it sends this JSON-formatted response back to the terminal as an HTTP response.

[0991] 7. Display the answer:

[0992] The terminal receives an HTTP response from the server and extracts the answer from the JSON-formatted data. The extracted answer text is then displayed on the user's screen.

[0993] Specific examples

[0994] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is sent to the server, and a generative artificial intelligence generates an answer. The generated answer is displayed on the user's device as specific and practical advice, such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[0995] Technical effects

[0996] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality.

[0997] The specific operation and utilization techniques of each means in this invention can be modified as appropriate based on the system design and implementation, and this flexibility is also one of the advantages of this invention.

[0998] The following describes the processing flow.

[0999] Step 1:

[1000] The user enters a question into the terminal's text field. The terminal provides an interface for the user to enter a question.

[1001] Step 2:

[1002] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user.

[1003] Step 3:

[1004] The device serializes the question it obtains into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content.

[1005] Step 4:

[1006] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content from the request body.

[1007] Step 5:

[1008] The server provides the question content as a prompt to the generative artificial intelligence. The generative artificial intelligence then performs text generation processing based on the given prompt.

[1009] Step 6:

[1010] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[1011] Step 7:

[1012] The server formats the response text received from the generative artificial intelligence into JSON format. The formatted JSON data is then sent to the terminal as an HTTP response.

[1013] Step 8:

[1014] The terminal receives an HTTP response from the server. The JSON data is parsed from the response body, and the generated response text is extracted.

[1015] Step 9:

[1016] The device displays the extracted answer text to the user. The user can then review the answer displayed on the screen.

[1017] (Example 1)

[1018] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1019] Traditional systems often involved long waiting times between a user entering a question and receiving an answer. Furthermore, their reliance on manual responses meant inconsistent and unpredictable response quality. Additionally, mechanisms for quickly generating appropriate answers were inadequately developed.

[1020] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1021] In this invention, the server includes means for providing acquired questions to a generative artificial intelligence model to generate answers to those questions, means for formatting the response from the generative artificial intelligence model into a data format, and means for using a data transmission request when a terminal sends a user's question. This makes it possible to provide users with fast, consistent, and high-quality answers.

[1022] A "user" is an individual or organization that uses this system to input questions and receive answers.

[1023] A "terminal" is a device used by users to input questions and send and receive data to and from a server, and includes personal computers, smartphones, tablets, and other similar devices.

[1024] A "server" is a central system that receives questions sent from terminals, provides them as prompts to generative artificial intelligence models, and sends the generated answers back to the terminals.

[1025] A "generative artificial intelligence model" is a pre-trained deep learning model or algorithm that generates appropriate answers based on received prompts (questions).

[1026] A "prompt" is the text of a question or instruction that is input to a generative artificial intelligence model.

[1027] "Data format" refers to the structure and format of the data that the server uses to organize the response from a generative artificial intelligence model and send it back to the terminal.

[1028] A "data transmission request" refers to a communication protocol, such as an HTTP POST request, used to send a user's question from their device to a server.

[1029] The present invention relates to a system in which a user inputs a question through a terminal, and a server generates an appropriate answer to that question using a generative artificial intelligence model and sends it back to the user. This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to the generative artificial intelligence model, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user.

[1030] The user opens a web browser on their device (e.g., personal computer, smartphone, tablet) and enters a question in the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" When the user clicks the "Submit Question" button, the device retrieves the question and sends it to the server as an HTTP POST request using JavaScript. The data is sent in JSON format. The programming languages ​​and tools used are JavaScript, HTML, and HTTP.

[1031] The server listens for HTTP POST requests at a configured endpoint and parses the JSON data in the request body. The server provides the retrieved question as a prompt to a generative artificial intelligence model, which then generates an appropriate answer. This generative AI model could be a general deep learning model (e.g., GPT-3, BERT). These models are pre-trained on large amounts of text data and have the ability to generate highly accurate answers. The server accesses these generative AI models using a programming language such as Python.

[1032] Once a generative artificial intelligence model generates a response, the server formats the response into a data format and sends it back to the terminal as an HTTP response. For example, the reformatted data is often in JSON format. The server runs on a web server (e.g., Apache, Nginx) and uses languages ​​such as Python or Node.js.

[1033] The terminal receives an HTTP response from the server and extracts the answer text from the JSON data. Then, it uses JavaScript in the web browser to display the answer on the user's screen. For example, it might display specific and practical advice such as, "First, try restarting your router. If the speed does not improve, we recommend contacting your internet provider to have them check your connection speed."

[1034] This system allows users to obtain fast, consistent, and high-quality answers. While traditional methods required manual responses from human staff, the use of generative artificial intelligence models enables instant responses, significantly improving the user experience. Furthermore, the consistent quality of responses is ensured by the generative AI models.

[1035] The embodiments of this invention are configured flexibly and can be modified as appropriate based on specific system designs and implementations.

[1036] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1037] Step 1:

[1038] The user enters a question.

[1039] In terms of the specific operation, the user opens a web browser on their device (PC, smartphone, or tablet) and enters a question into the provided text field. For example, they might enter, "My internet connection is slow, what should I do?" The input is saved as text data on the device.

[1040] Step 2:

[1041] The device retrieves and sends the question.

[1042] Specifically, when the user clicks the "Submit Question" button, the device uses JavaScript to retrieve the question from the text field. This question data is converted to JSON format and sent to the server as an HTTP POST request. The input is the user's question, and the output is the HTTP POST request to the server.

[1043] Step 3:

[1044] The server receives the question.

[1045] In terms of operation, the server listens for HTTP POST requests at the configured endpoint. Upon receiving a request sent from the terminal, the server parses the JSON data in the request body and extracts the question text. The input is the HTTP POST request, and the output is the parsed question text.

[1046] Step 4:

[1047] The server provides prompts to the generative artificial intelligence.

[1048] In terms of operation, the analyzed question text is provided to a generative artificial intelligence model as a prompt. The server generates an API request and sends it to the generative AI model. The generative AI model used is pre-trained on large amounts of text data (e.g., GPT-3, BERT). The input is the question text, and the output is the API request to the generative AI model.

[1049] Step 5:

[1050] A generative artificial intelligence generates the answer.

[1051] In terms of operation, a generative artificial intelligence model generates an appropriate response based on the input prompt. This response process is carried out via a deep learning algorithm. The generated response is returned to the server in text format. The input is the prompt, and the output is the response in text format.

[1052] Step 6:

[1053] The server formats the response and sends it back.

[1054] In terms of operation, the server formats the response received from the generative artificial intelligence model into JSON format and sends it back to the terminal as an HTTP response. The input is a text-formatted response, and the output is an HTTP response (in JSON format) sent to the terminal.

[1055] Step 7:

[1056] The device will display the answer.

[1057] In terms of specific operation, the terminal receives an HTTP response from the server and extracts the answer text from the JSON data. JavaScript in the web browser is then used to display the answer on the user's screen. For example, specific and practical advice such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have your connection speed checked," might be displayed. The input is the HTTP response, and the output is the displayed text.

[1058] (Application Example 1)

[1059] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1060] In recent years, there has been a growing demand for faster and more efficient customer support in virtual stores. However, traditional systems require staff to manually search for and provide answers to customer questions, often resulting in long response times. This has led to decreased customer satisfaction. Furthermore, there has been a lack of technology to enable natural conversations using voice input.

[1061] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1062] In this invention, the server includes means for the user to input a question, means for a terminal to acquire the question input by the user and send it to the server, means for the server to provide the acquired question to a generative artificial intelligence to generate an answer to the question, means for sending the generated answer back to the user via the server, means for the terminal to display the received answer to the user, means for a smart device to acquire a question through voice input, and means for displaying the generated answer on the smart device's display. This makes it possible to provide quick and accurate answers to customer questions in a virtual store.

[1063] A "user" is someone who uses the system to input questions and receive the generated answers.

[1064] A "terminal" is a device operated by the user, which is used for inputting, retrieving, and sending questions to the server, as well as receiving and displaying answers from the server.

[1065] A "server" is a device that receives questions sent from a terminal and provides them to a generative artificial intelligence system, and is responsible for sending the generated answers back to the user.

[1066] "Generative artificial intelligence" is an artificial intelligence technology that generates appropriate answers based on a given question.

[1067] An "answer" is a response to a user's question, generated by a generative artificial intelligence system.

[1068] A "smart device" is an advanced device that has the function of obtaining questions through voice input and displaying the generated answers on a screen.

[1069] "Voice input" is a method of acquiring the user's voice through the microphone of a smart device and converting that voice data into text format.

[1070] A "display" is the screen installed in a smart device that visually presents the generated response to the user.

[1071] An "HTTP POST request" is one of the internet communication protocols used to send data from a terminal to a server.

[1072] The system based on this invention allows the user to input a question via a terminal, and provides an appropriate answer using generative artificial intelligence. The following hardware and software are used to realize this system.

[1073] First, the user inputs a question using a smart device (e.g., smart glasses). This question is captured as voice input and converted into text format using a speech recognition library. Specifically, the speech_recognition library is used. The smart device includes a microphone for capturing voice input and a display for showing the captured response.

[1074] The terminal converts the question into text format and then sends the data to the server. This transmission uses the HTTP POST request, an internet communication protocol. The sent question arrives at the server as JSON data.

[1075] The server provides the received question as a prompt to a generative artificial intelligence (AI). This AI uses an advanced language model (e.g., GPT-3). The AI ​​generates an appropriate response to the received prompt and sends that response back to the server.

[1076] The server formats the generated response into JSON format and sends it back to the device as an HTTP response. The device receives the response from the server, extracts the answer from the JSON data, and displays it on the smart device's display.

[1077] As a concrete example, if a user asks, "Is this item in stock?", this question is picked up through the smart glasses' microphone and converted into text using speech recognition. The converted text is then sent to a server, where generative artificial intelligence generates an answer. The generated answer, "This item is in stock. You can purchase it now," is displayed on the smart glasses' screen and provided to the user.

[1078] This system enables the provision of quick and accurate answers in virtual stores, significantly improving customer satisfaction.

[1079] The following are examples of prompts provided to generative artificial intelligence:

[1080] "A customer asked, 'Do you have this item in stock?' Please provide the best possible answer."

[1081] This prompt can be used by a generative artificial intelligence to generate the optimal answer to the user's question.

[1082] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1083] Step 1:

[1084] The user inputs a question using a smart device (e.g., smart glasses). This question is entered in voice format. Voice data is captured through the smart device's microphone. This is the input for Step 1. This voice data is then passed on to the subsequent speech recognition process.

[1085] Step 2:

[1086] The smart device converts the acquired audio data into text format using a speech recognition library. The library used in this step is speech_recognition. The speech recognition library converts the audio data into text data, and the converted text becomes the output of step 2.

[1087] Step 3:

[1088] The terminal sends the question, converted to text format, to the server via an HTTP POST request. This text data is packaged in JSON format and sent to the server over the internet. The sent JSON data is the output of step 3.

[1089] Step 4:

[1090] The server receives an HTTP POST request from the terminal. This request contains the user's question in JSON format. The server parses this JSON data and extracts the question. The extracted question is the output of step 4.

[1091] Step 5:

[1092] The server provides the extracted questions as prompts to the generative artificial intelligence. This generative AI uses an advanced language model (e.g., GPT-3). By passing the questions as prompts to the AI, the AI ​​generates the optimal answer. The generated answer is the output of step 5.

[1093] Step 6:

[1094] The server formats the response received from the generative artificial intelligence into JSON format. The formatted JSON data is prepared for return to the user's terminal. This formatted JSON data is the output of step 6.

[1095] Step 7:

[1096] The terminal receives an HTTP response from the server. This response contains the answer generated by the generative artificial intelligence in JSON format. The terminal parses this JSON data and extracts the answer. The extracted answer is the output of step 7.

[1097] Step 8:

[1098] The smart device displays the extracted answers on its screen, allowing the user to visually confirm the answers to the questions. The answers displayed on the screen are the output of step 8.

[1099] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1100] This invention relates to a system in which, when a user inputs a question through a terminal, a server generates an appropriate answer to that question using generative artificial intelligence and an emotion engine, adjusts it according to the user's emotions, and then sends a response to the user.

[1101] System Overview

[1102] This system includes means for the user to input a question, means for the terminal to send the question to the server, means for the server to receive the question and provide it to a generative artificial intelligence and an emotion engine, means for the server to send the generated answer back to the user, and means for the terminal to display the received answer to the user. Furthermore, it also includes means for using the emotion engine to analyze the user's emotions and adjusting the answer based on the results.

[1103] Operation of each component

[1104] 1. User actions:

[1105] The user enters their question into a text field on their device and clicks the "Submit Question" button. This device includes PCs, smartphones, tablets, and other devices.

[1106] 2. Obtaining and submitting questions:

[1107] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, it uses an emotion engine to analyze the user's emotions and retrieves the results. Finally, it serializes the question content and emotion data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[1108] 3. Receiving the question:

[1109] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body.

[1110] 4. Provisions to generative artificial intelligence and emotion engines:

[1111] The server provides the received question content as a prompt to the generative artificial intelligence. The generative AI performs text generation processing based on this prompt. At the same time, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[1112] 5. Generating and refining responses:

[1113] A generative artificial intelligence generates answers based on the provided questions. Furthermore, the server appropriately adjusts the generated answers based on sentiment data analyzed by an emotion engine.

[1114] 6. Return your response:

[1115] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response.

[1116] 7. Display the answer:

[1117] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen.

[1118] Specific examples

[1119] For example, if a user enters the question, "My internet connection is slow, what should I do?", the question is analyzed by an emotion engine before being sent to the server. If the emotion engine detects the user's frustration, the generative artificial intelligence generates a response that is specific and practical advice, such as, "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed," and it is delivered in a friendly tone that is adjusted according to the user's emotions. In this way, the user experience is improved.

[1120] Technical effects

[1121] This system allows users to obtain quick and high-quality answers. Conventional methods required manual responses by staff, which could be time-consuming. However, by implementing this invention, immediate answers to user questions become possible, significantly improving the user experience. Furthermore, consistent answers are provided through generative artificial intelligence, ensuring stable response quality. Additionally, responses that consider the user's emotions are provided, increasing user satisfaction.

[1122] The following describes the processing flow.

[1123] Step 1:

[1124] The user enters the question into the terminal's text field. The terminal provides an interface for the user to enter the question.

[1125] Step 2:

[1126] The user clicks the "Submit Question" button. This executes JavaScript on the device, which retrieves the question entered by the user. At this point, the emotion engine also analyzes the user's facial expressions and voice tone using the device's camera and microphone.

[1127] Step 3:

[1128] The emotion engine generates emotional data from the user's input, facial expressions, and tone of voice. This emotional data includes whether the user is feeling stress, anxiety, joy, etc.

[1129] Step 4:

[1130] The device serializes the acquired question and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server. The HTTP request includes the question content and sentiment data.

[1131] Step 5:

[1132] The server receives an HTTP POST request. The server's API endpoint processes the request and extracts the question content and sentiment data from the request body.

[1133] Step 6:

[1134] The server extracts questions and provides them as prompts to the generative artificial intelligence. The generative AI then uses these prompts to perform text generation processing.

[1135] Step 7:

[1136] The server provides emotional data to the emotion engine, which further analyzes the user's emotional state. The emotion engine processes the emotional data and generates the emotional analysis results.

[1137] Step 8:

[1138] A generative artificial intelligence generates an answer based on the provided question. The generated answer is returned to the server as text data.

[1139] Step 9:

[1140] The server combines the response text received from the generative artificial intelligence with the results of the emotion engine's analysis. Based on the emotion analysis results, the response is appropriately adjusted. For example, if the user is feeling stressed, the response will be made more polite and kind.

[1141] Step 10:

[1142] The server formats the adjusted response into JSON format. Then, it sends the JSON data containing the adjusted response to the terminal as an HTTP response.

[1143] Step 11:

[1144] The terminal receives an HTTP response from the server. It then parses the JSON data from the response body and extracts the generated response text.

[1145] Step 12:

[1146] The device displays the extracted response text to the user. The user can then see the response, which has been adjusted according to their emotions.

[1147] (Example 2)

[1148] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1149] Traditional response generation systems often provided answers without considering the user's emotions, resulting in a poor user experience. In particular, it was difficult to provide appropriate answers when users were feeling anxious or frustrated. Furthermore, the quality of responses was often inconsistent, leading to decreased user satisfaction.

[1150] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1151] In this invention, the server includes means for providing a question to a generative artificial intelligence and generating an answer to the question, means for adjusting the generated answer based on the user's emotions using an emotion engine, and means for returning the adjusted answer to the user via the server. This makes it possible to provide consistent, high-quality answers that take the user's emotions into consideration.

[1152] A "user" is an individual or organization that uses this system to input questions and receive answers.

[1153] A "device" is a device used by a user to input questions or view answers, and includes PCs, smartphones, tablets, and other similar devices.

[1154] A "server" is a central processing unit that receives user questions, generates and refines answers using generative artificial intelligence and an emotion engine, and sends them back to the user.

[1155] "Generative artificial intelligence" refers to artificial intelligence models that can generate answers in natural language to user questions. Examples include GPT-3.

[1156] An "emotion engine" is software or an algorithm that analyzes emotional data obtained from users and adjusts the responses generated based on the results.

[1157] JSON format is a lightweight data exchange format for storing and transferring data as text, and it is an abbreviation for JavaScript Object Notation.

[1158] An "HTTP POST request" is one of the HTTP methods used to send and receive data between a server and another server.

[1159] "Emotional data" refers to the analysis results that indicate the user's emotional state, including, for example, whether the user is feeling frustrated.

[1160] A "prompt" is an input sentence that provides information, such as the content of a question, to a generative artificial intelligence system in order to generate a specific answer.

[1161] "Answer" refers to information or advice generated by a generative artificial intelligence system based on the user's question.

[1162] This invention is a system in which, when a user inputs a question, a server uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusts it according to the user's emotions, and then sends a response to the user.

[1163] This system uses the following hardware and software:

[1164] A device (PC, smartphone, tablet, etc.) for the user to enter questions.

[1165] A server that receives and processes question and sentiment data.

[1166] Generative artificial intelligence for generating answers (e.g., GPT-3)

[1167] An emotion engine that analyzes user emotions and adjusts responses accordingly.

[1168] A means of communication for exchanging data (HTTP POST request)

[1169] The user enters a question into a text field on their device and clicks the "Submit Question" button. At this point, a script on the device, such as JavaScript, retrieves the question entered by the user and analyzes the user's emotions using an emotion engine.

[1170] The analysis results and question content are serialized in JSON format and sent as an HTTP POST request to a specific API endpoint on the server. The server receives this request, analyzes its contents, and extracts the question and sentiment data.

[1171] The server provides the question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the results of the emotion analysis.

[1172] For example, if a user types "My internet connection is slow, what should I do?", the emotion engine might detect the user's frustration. The generative AI would respond to this prompt as follows:

[1173] "First, try restarting your router. If the speed doesn't improve, we recommend contacting your internet provider to have them check your connection speed."

[1174] The server formats the generated responses into JSON format and adjusts them based on the analysis results from the sentiment engine. The adjusted responses are sent to the terminal as an HTTP response. The terminal receives this HTTP response, extracts the response text from the JSON data, and displays it on the user's screen.

[1175] This allows users to receive quick, high-quality answers, and because those answers take into account specific emotional states, the user experience is significantly improved.

[1176] The above describes specific embodiments for carrying out this invention.

[1177] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1178] Step 1:

[1179] The user enters their question in the text field on their device and clicks the "Submit Question" button.

[1180] Input: User-entered question text (e.g., "My internet connection is slow, what should I do?")

[1181] Output: The terminal detects the user's question submission operation.

[1182] Step 2:

[1183] The device uses scripts such as JavaScript to retrieve questions entered by the user. It also uses an emotion engine to analyze the user's emotions.

[1184] Input: Question text entered by the user

[1185] Output: Question text and sentiment data (e.g., "frustration")

[1186] Specific operation: The terminal captures text from the user's question input field and calls the sentiment engine to analyze the sentiment. After obtaining the analysis results, it serializes the question content and sentiment data into JSON format.

[1187] Step 3:

[1188] The device serializes the question content and sentiment data into JSON format and sends an HTTP POST request to a specific API endpoint on the server.

[1189] Input: Question text and sentiment data (in JSON format)

[1190] Output: HTTP POST request to the server

[1191] Specific operation: The terminal creates an HTTP POST request, including the question content and sentiment data in the request body. The request is sent to a specific API endpoint on the server.

[1192] Step 4:

[1193] The server receives an HTTP POST request sent from the terminal. It extracts the question content and sentiment data from the request body.

[1194] Input: HTTP POST request

[1195] Output: Questionnaire text and sentiment data

[1196] Specific operation: The server parses the body of the received request and extracts the question content and sentiment data sent in JSON format. This data is stored internally.

[1197] Step 5:

[1198] The server provides the received question content as a prompt to the generative artificial intelligence, which then generates an answer based on this prompt. Simultaneously, the server provides emotion data to the emotion engine and obtains the emotion analysis results.

[1199] Input: Question text, sentiment data

[1200] Output: Responses from generative artificial intelligence, analysis results from the emotion engine.

[1201] Specific operation: The server passes the question content to the generative artificial intelligence, providing a prompt such as "User question: My internet connection is slow, what should I do?". The generative AI generates an answer based on this prompt. Meanwhile, the server provides sentiment data to the sentiment engine and obtains the sentiment analysis results.

[1202] Step 6:

[1203] The server adjusts the generated responses based on the results of the sentiment engine and formats the adjusted responses into JSON format.

[1204] Input: Response from generative artificial intelligence, emotion analysis results

[1205] Output: Adjusted response in JSON format

[1206] Specific operation: The system adjusts the response generated by the generative AI (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have them check your connection speed.") and formats the result into JSON format.

[1207] Step 7:

[1208] The server sends the adjusted response in JSON format to the terminal as an HTTP response.

[1209] Input: Adjusted response (JSON format)

[1210] Output: HTTP response to the terminal

[1211] Specific operation: The server includes JSON data containing the adjusted response in the HTTP response and sends it to the terminal.

[1212] Step 8:

[1213] The terminal receives an HTTP response from the server, parses the JSON data from the response body, and extracts the generated response text. The terminal then displays the extracted response text on the user's screen.

[1214] Input: HTTP response

[1215] Output: Response text displayed to the user

[1216] Specific operation: The terminal analyzes the response from the server, extracts the response text generated from the JSON data (e.g., "First, try restarting your router. If the speed does not improve further, we recommend contacting your internet provider to have your connection speed checked."), and displays it on the user's screen.

[1217] (Application Example 2)

[1218] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1219] Conventional question answering systems often fail to consider user emotions when generating responses, making it difficult to provide quick and appropriate answers. This is especially true in areas where user anxiety is high, such as security services, where emotion-based adjustments are crucial. However, current systems lack such emotion-adjusting capabilities, highlighting the need for improved user experience.

[1220] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for analyzing the user's emotions using an emotion engine and adjusting the response based on the results, means for formatting the response from the generative artificial intelligence into JSON format, and means for using an HTTP POST request when the terminal sends the user's question. This makes it possible to provide an appropriate and prompt response that takes the user's emotions into consideration.

[1221] A "user" refers to a person who uses the system.

[1222] "Means for entering questions" refers to an interface for users to enter questions as text.

[1223] A "terminal" refers to a computing device used by a user to input questions, and this includes PCs, smartphones, tablets, and other similar devices.

[1224] "Means by which a terminal obtains user-entered questions and sends them to a server" refers to software or a protocol for transferring user-entered questions from the terminal to the server.

[1225] A "server" refers to a computer device that receives and processes queries.

[1226] "Generative artificial intelligence" refers to an artificial intelligence model that generates appropriate answers to given questions.

[1227] "Means of providing information to a generative artificial intelligence" refers to the process by which a server distributes questions received from a user to a generative artificial intelligence.

[1228] An "emotion engine" refers to an algorithm or software that analyzes a user's emotions and adjusts responses based on the results.

[1229] "A means of analyzing a user's emotions using an emotion engine and adjusting the response based on the results" refers to a mechanism that modifies the generated response based on the user's emotions.

[1230] "Means of returning the generated response to the user via the server" refers to the process of returning the generated response to the terminal via the server.

[1231] "Means of displaying the response received by the device to the user" refers to the process of displaying the response received by the device on the user's screen.

[1232] "Methods for formatting into JSON format" refers to software processing for converting the generated response into JSON (JavaScript Object Notation) format.

[1233] "Using an HTTP POST request" refers to the process of sending user query data to a server using the POST method of the HTTP protocol.

[1234] This invention is a system that, upon receiving a question from a user, uses generative artificial intelligence and an emotion engine to generate an appropriate answer to that question, adjusting it according to the user's emotions before responding. This invention is particularly intended for application in the field of security services, enabling a rapid and appropriate response to user anxieties and questions.

[1235] System Overview

[1236] User:

[1237] Users enter their questions into a text field from devices such as PCs, smartphones, and tablets. For example, a user might enter the question, "I've been receiving a lot of phishing emails lately; what should I do about it?"

[1238] Terminal:

[1239] The terminal uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, each terminal has an emotion engine built in to analyze the user's emotions. As a result, the question content and emotion data are serialized in JSON format and an HTTP POST request is sent to a specific API endpoint on the server.

[1240] server:

[1241] The server receives an HTTP POST request sent from the terminal and extracts the question content and sentiment data from the request body. The extracted question content is provided as a prompt to the generative artificial intelligence, which then performs text generation processing based on that prompt. Commonly used APIs (e.g., OpenAI's GPT model) can be used as the generative AI.

[1242] Furthermore, the server incorporates an emotion engine that adjusts responses based on the results of analyzing emotional data. This adjustment uses software like EmotionEngine to modify the tone and content to suit the user's emotions.

[1243] Generating and refining responses:

[1244] Generative artificial intelligence generates answers based on the provided questions. Then, an emotion engine adjusts those answers to match the user's emotional state, formatting them into the most appropriate wording. For example, if the user is feeling anxious, the answer will be revised to be more kind and polite.

[1245] Sending and displaying responses:

[1246] The server formats the generated response text into JSON format, combines it with the results adjusted by the sentiment engine, and sends the JSON data to the terminal as an HTTP response. The terminal receives the HTTP response from the server, parses the JSON data from the response body, extracts the generated response text, and displays it on the user's screen.

[1247] Specific examples

[1248] The user uses their smartphone to enter the following question into a dedicated application: "I've been receiving a lot of phishing emails lately. How should I deal with them?"

[1249] This question is first sent from the device to the server. During transmission, the emotion engine detects the user's anxiety, and this information is also sent along with the question.

[1250] The server provides question and sentiment data to a generative artificial intelligence. For example, OpenAI's GPT model is used.

[1251] • Generative artificial intelligence generates answers to questions. Then, an emotion engine modifies the answers to make them kind and polite.

[1252] The corrected response is formatted in JSON format and sent back to the terminal as an HTTP response.

[1253] • Finally, the device displays the received response on the user's screen. For example, a response might be displayed such as, "First, it's important not to open emails from unknown senders. Also, avoid clicking on links in emails. Furthermore, we recommend reporting phishing emails to your ISP or security provider."

[1254] This system allows users to receive quick and appropriate answers, particularly addressing security-related concerns.

[1255] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1256] Step 1:

[1257] The user enters their question into the text field on their device and clicks the "Submit Question" button. The input here is the user entering a specific question as text.

[1258] Step 2:

[1259] The device uses scripts such as JavaScript to retrieve questions entered by the user. Furthermore, the device's built-in sentiment engine analyzes the user's emotions and retrieves sentiment data. This question content and sentiment data are serialized into JSON format, and an HTTP POST request is sent to a specific API endpoint on the server. Specifically, the input is the user's question text and the sentiment analysis results, while the output is the data sent to the server.

[1260] Step 3:

[1261] The server receives an HTTP POST request sent from the terminal. The server processes the request at its API endpoint and extracts the question content and sentiment data from the request body. Specifically, it parses the question text and sentiment data from the JSON data and converts them into a usable format.

[1262] Step 4:

[1263] The server provides the received question content as a prompt to the generative artificial intelligence (AI). The generative AI uses this prompt to perform text generation processing and generate the answer text. For example, an open AI API such as GPT-3 is used as the generative AI. The input for this step is the question text, and the output is the generated answer text.

[1264] Step 5:

[1265] The server provides sentiment data to the sentiment engine and retrieves the sentiment analysis results again. The sentiment engine adjusts the generated response based on this data, modifying it to match the user's sentiment. The input for this step is the generated response text and sentiment data, and the output is the adjusted response text.

[1266] Step 6:

[1267] The server formats the response text received from the generative artificial intelligence into JSON format and incorporates the results adjusted by the emotion engine. It then sends this JSON-formatted response to the terminal as an HTTP response. The input for this step is the adjusted response text, and the output is the JSON data response from the server to the terminal.

[1268] Step 7:

[1269] The terminal receives an HTTP response from the server. It parses the JSON data from the response body and extracts the generated response text. Then, it displays the extracted response text on the user's screen. The input for this step is the response data in JSON format, and the output is the response text displayed on the user's screen.

[1270] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1271] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1272] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1273] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1274] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1275] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1276] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1277] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1278] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1279] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1280] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1281] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1282] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1283] 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.

[1284] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1285] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1286] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1287] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1288] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1289] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1290] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1291] The following is further disclosed regarding the embodiments described above.

[1292] (Claim 1)

[1293] A means for the user to input a question,

[1294] A means by which the terminal obtains the question entered by the user and sends it to the server,

[1295] A means for providing a server with questions it has acquired to a generative artificial intelligence system, and for generating answers to those questions,

[1296] A means of returning the generated response to the user via the server,

[1297] A means of displaying the response received by the terminal to the user,

[1298] A system that includes this.

[1299] (Claim 2)

[1300] The system according to claim 1, further comprising means for the server to format the response from a generative artificial intelligence into JSON format.

[1301] (Claim 3)

[1302] The system according to claim 1, further comprising means for the terminal to use an HTTP POST request when sending a user's question.

[1303] "Example 1"

[1304] (Claim 1)

[1305] A means for the user to input a question,

[1306] A means by which the terminal obtains the question entered by the user and sends it to the server,

[1307] A means for providing a server with a question it has acquired to a generative artificial intelligence model and causing it to generate an answer to that question,

[1308] A means of returning the generated response to the user via the server,

[1309] A means of displaying the response received by the terminal to the user,

[1310] A system that includes this.

[1311] (Claim 2)

[1312] The system according to claim 1, further comprising means for a server to format a response from a generative artificial intelligence model into a data format.

[1313] (Claim 3)

[1314] The system according to claim 1, further comprising means for using a data transmission request when a terminal sends a user's question.

[1315] "Application Example 1"

[1316] (Claim 1)

[1317] A means for the user to input a question,

[1318] A means by which the terminal obtains the question entered by the user and sends it to the server,

[1319] A means for providing a server with questions it has acquired to a generative artificial intelligence system, and for generating answers to those questions,

[1320] A means of returning the generated response to the user via the server,

[1321] A means of displaying the response received by the terminal to the user,

[1322] A means by which smart devices obtain questions through voice input,

[1323] A means of displaying the generated response on the display of a smart device,

[1324] A system that includes this.

[1325] (Claim 2)

[1326] The system according to claim 1, further comprising means for the server to format the response from a generative artificial intelligence into JSON format.

[1327] (Claim 3)

[1328] The system according to claim 1, further comprising means for the terminal to use an HTTP POST request when sending a user's question.

[1329] "Example 2 of combining an emotion engine"

[1330] (Claim 1)

[1331] A means for the user to input a question,

[1332] A means by which the terminal obtains the question entered by the user and sends it to the server,

[1333] A means for providing a server with questions it has acquired to a generative artificial intelligence system, and for generating answers to those questions,

[1334] A means of adjusting the generated response based on the user's emotions using an emotion engine,

[1335] A means of returning the adjusted response to the user via the server,

[1336] A means of displaying the response received by the terminal to the user,

[1337] A system that includes this.

[1338] (Claim 2)

[1339] The system according to claim 1, further comprising means for the server to format the response from a generative artificial intelligence into JSON format.

[1340] (Claim 3)

[1341] The system according to claim 1, further comprising means for the terminal to use an HTTP POST request when sending a user's question.

[1342] (Claim 4)

[1343] The system according to claim 1, further comprising means for analyzing user questions acquired by a terminal using an emotion engine to detect the user's emotional state.

[1344] "Application example 2 when combining with an emotional engine"

[1345] (Claim 1)

[1346] A means for the user to input a question,

[1347] A means by which the terminal obtains the question entered by the user and sends it to the server,

[1348] A means for providing a server with questions it has acquired to a generative artificial intelligence system, and for generating answers to those questions,

[1349] A means of returning the generated response to the user via the server,

[1350] A means of displaying the response received by the terminal to the user,

[1351] A means by which the server analyzes the user's emotions using an emotion engine and adjusts the response based on the results,

[1352] A system that includes this.

[1353] (Claim 2)

[1354] The system according to claim 1, further comprising means for the server to format the response from a generative artificial intelligence into JSON format.

[1355] (Claim 3)

[1356] The system according to claim 1, further comprising means for the terminal to use an HTTP POST request when sending a user's question. [Explanation of symbols]

[1357] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for the user to input a question, A means by which the terminal obtains the question entered by the user and sends it to the server, A means for providing a server with questions it has acquired to a generative artificial intelligence system, and for generating answers to those questions, A means of returning the generated response to the user via the server, A means of displaying the response received by the terminal to the user, A system that includes this.

2. The system according to claim 1, further comprising means for the server to format the response from a generative artificial intelligence into JSON format.

3. The system according to claim 1, further comprising means for the terminal to use an HTTP POST request when sending a user's question.

Images