system

Abstract

We provide the system. [Solution] A means of accepting user selections from predefined inputs, Means for generating a generation prompt based on selected standard inputs, A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a response, Means for providing the generated response 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, including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a call center or a guidance display system, it is important to respond to inquiries from users quickly and accurately. However, in conventional systems, the reaction to a huge amount of inquiry content is often delayed, and in particular, it is difficult to handle unexpected questions or complex inquiries. In addition, a great deal of labor is required for maintenance work and update work of these systems, lacking in efficiency. In order to solve such problems and improve user satisfaction, the introduction of a more advanced automatic response system has been demanded.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides the following means. First, it provides means for receiving an operation in which the user selects from a set of predefined inputs. Next, it provides means for generating a generation prompt based on the selected predefined input. Furthermore, it constructs means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response. Finally, by configuring a system that includes means for providing the generated response to the user, these problems can be solved. This system makes it possible to respond quickly and accurately to a variety of inquiries from users, and furthermore, to always provide the latest information while minimizing periodic maintenance work.

[0006] A "user" refers to a person who performs operations or makes inquiries to the system.

[0007] "Formulaic input" refers to a format of questions or commands that allows the user to choose from predefined options.

[0008] "Means for accepting selection operations" refers to mechanisms or functions that receive information selected by the user from a set of predefined inputs and allow the system to recognize that selection.

[0009] A "generated prompt" refers to a set of instructions or inquiries that the system generates based on the user's predefined input selections.

[0010] "Means for generating generation prompts" refers to mechanisms or functions for automatically creating specific prompts corresponding to selected standard inputs.

[0011] "Generative artificial intelligence" refers to artificial intelligence models that can generate natural language responses to given prompts.

[0012] "Means for generating a response" refers to a mechanism or function for sending a generation prompt to a generative artificial intelligence and receiving the response generated by the AI ​​as a result.

[0013] "Means of providing generated responses" refers to mechanisms and functions for presenting responses obtained from generative artificial intelligence to the user.

[0014] "System" refers to a collection of devices and programs that, as a whole, realize a series of operations, including the means described above. [Brief explanation of the drawing]

[0015] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13]It is a sequence diagram showing the processing flow of the data processing system in Embodiment 2 when the 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 the emotion engine is combined.

Mode for Carrying Out the Invention

[0016] Hereinafter, an example of an embodiment of the system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

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

[0018] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be one arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be one type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0019] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0020] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0021] 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).

[0022] 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."

[0023] [First Embodiment]

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

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form 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.

[0030] 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.

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

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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".

[0036] System Configuration

[0037] The system of the present invention automates a series of processes, from receiving a standard input selected by the user to generating a response using generative artificial intelligence, and then providing that response to the user. This system includes the following main components:

[0038] 1. User Interface Terminal

[0039] 2. Server

[0040] 3. Generative artificial intelligence models

[0041] Program processing

[0042] Acceptance of user input

[0043] terminal

[0044] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. For example, options such as "Check opening hours," "Firm information," and "Inquire about product information" are available. Once the user makes a selection, that information is sent from the terminal to the server.

[0045] Submit your selections

[0046] terminal

[0047] The terminal sends the user's selected predefined input data to the server. This allows the server to prepare to begin the next process.

[0048] Prompt generation

[0049] server

[0050] The server generates a prompt based on the standardized input information it receives. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to the generative artificial intelligence.

[0051] Response generation

[0052] server

[0053] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, a response such as, "Our business hours are from 9 am to 6 pm on weekdays."

[0054] Displaying responses to the user

[0055] terminal

[0056] The terminal receives the response sent from the server and displays it to the user. By checking this result, the user can immediately obtain the necessary information.

[0057] Specific example

[0058] Examples of call centers

[0059] scenario

[0060] Consider a scenario where a user accesses a call center's automated response system to inquire about business hours. The process in this case is as follows:

[0061] 1. The user selects "Check business hours".

[0062] 2. The terminal sends the selected data to the server.

[0063] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0064] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0065] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0066] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0067] Example of a sign (in-house guide)

[0068] scenario

[0069] Let's consider a scenario where a user wants to find the location of the elevators using a terminal within the building. The process in this case is as follows:

[0070] 1. The user selects the "elevator location".

[0071] 2. The terminal sends the selected data to the server.

[0072] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0073] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0074] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0075] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0076] In this way, the system of the present invention can respond quickly and accurately to a wide range of inquiries from users. Furthermore, it can provide the latest information while minimizing maintenance work. High reliability is ensured by having humans handle final decisions and special cases.

[0077] The following describes the processing flow.

[0078] Step 1:

[0079] The user accesses a display terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed.

[0080] Step 2:

[0081] The terminal receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selections.

[0082] Step 3:

[0083] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, the server generates the prompt "Please tell me your current business hours."

[0084] Step 4:

[0085] The server sends a generation prompt to the generative artificial intelligence. The generative artificial intelligence generates a response in natural language based on the received prompt.

[0086] Step 5:

[0087] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it will generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[0088] Step 6:

[0089] The server receives the response generated by the generative artificial intelligence and sends that response to the terminal. This makes the response available to the user.

[0090] Step 7:

[0091] The terminal displays the response it receives from the server to the user. For example, it might display a message on the screen or via audio saying, "Our store hours are from 9:00 AM to 6:00 PM on weekdays."

[0092] Step 8:

[0093] The system confirms the user's response, whether displayed or spoken, and retrieves the necessary information.

[0094] (Example 1)

[0095] 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."

[0096] Currently, in many systems, the process of responding quickly and appropriately to user inquiries is complex and time-consuming. In particular, ensuring efficiency and accuracy in generating and displaying responses to routine inquiries is difficult. Traditional systems often require human intervention during the response generation process, leading to increased costs and slower response times. Furthermore, the lack of adequate means to consistently provide up-to-date information results in decreased user satisfaction.

[0097] 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.

[0098] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for processing the selected predefined inputs and sending them to the server, means for generating a generation prompt based on the predefined inputs received by the server, means for sending the generation prompt to a generative artificial intelligence system to generate a natural language response, and means for providing the generated natural language response to the user. This makes it possible to always provide the latest information quickly and accurately in response to user inquiries. Furthermore, the overall efficiency and automation of the system are improved, and human intervention in the response generation process is minimized.

[0099] A "user" is an individual or group that operates the system and selects predefined input options.

[0100] "Standard input" refers to pre-configured inquiry content or operation options that users select.

[0101] A "server" is a computing system that receives standardized user input, generates prompts, sends them to generative artificial intelligence, and processes responses.

[0102] A "terminal" is an interface device operated by a user, which sends user input to a server and displays the server's response.

[0103] A "generated prompt" is a set of instructions created by a server based on a user's standardized input, and serves as input data for generating a response from a generative artificial intelligence.

[0104] "Generative artificial intelligence" refers to machine learning algorithms and models that receive a generative prompt and generate a natural language response based on it.

[0105] A "natural language response" is a response sentence in a language format that is easy for humans to understand, which is output by a generative artificial intelligence system based on a generation prompt.

[0106] This invention automates a series of processes, from receiving predefined inputs selected by the user to generating responses using generative artificial intelligence, and then providing those responses to the user. The embodiments for carrying out this invention are described in detail below.

[0107] System Configuration

[0108] The system of the present invention includes the following main components.

[0109] 1. User interface terminals: Examples include mobile information terminals such as iPad® and ANDROID® tablets.

[0110] 2. Servers: Cloud-based servers such as AWS® EC2 and Google® Cloud Compute Engine will be used.

[0111] 3. Generative artificial intelligence models: Natural language processing models such as OpenAI® GPT-4® and Google BERT are used.

[0112] Selection at the user interface terminal

[0113] The user selects their desired option from several choices displayed on the terminal they are using. For example, options such as "Check opening hours," "Firm information guide," and "Inquire about product information" may be displayed. Once the user makes a selection, that information is sent from the terminal to the server.

[0114] Prompt generation on the server

[0115] The server generates appropriate prompts based on the standardized input information received from the user. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to a generative artificial intelligence model.

[0116] Response generation in generative artificial intelligence models

[0117] A generative artificial intelligence model generates a natural language response based on a prompt received from the server. For example, a response such as "Our store hours are from 9 am to 6 pm on weekdays" is generated. This response is then sent back to the server.

[0118] Sending and displaying responses to the user interface terminal

[0119] The server sends the generated response to the terminal, which then displays the response to the user. By checking the response displayed on the terminal's screen, the user can instantly obtain the necessary information.

[0120] Specific example

[0121] Examples of call centers

[0122] Here's a concrete example of the procedure a user would follow if they accessed a call center's automated response system to inquire about business hours.

[0123] 1. The user selects "Check business hours".

[0124] 2. The terminal sends the selected data to the server.

[0125] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0126] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[0127] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0128] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0129] Example of a sign (in-house guide)

[0130] Here's a concrete example of how a user can find out the location of the elevators using a terminal within the building.

[0131] 1. The user selects the "elevator location".

[0132] 2. The terminal sends the selected data to the server.

[0133] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0134] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[0135] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0136] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0137] Specific examples of prompt phrases include, "What are your current business hours?" and "Where is the elevator?"

[0138] As described above, the system of the present invention is capable of responding quickly and accurately to a wide range of inquiries from users. The overall efficiency and automation of the system are improved, and it becomes possible to always provide the latest information.

[0139] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0140] Step 1:

[0141] The user makes a selection for a predefined input. The user interface terminal displays multiple options to the user. For example, options may include "Check opening hours," "Get directions within the building," and "Inquire about product information." The user makes a selection by tapping or clicking. The input is the user's selection, and the output is the data of the selected option.

[0142] Step 2:

[0143] The device sends the user's selections to the server. Specifically, the device sends the data of the selected options to the server as an HTTP request. This data is in JSON format and is passed to the server in a format such as { "query": "Check business hours"}. The input is the user's selection data, and the output is the selection data sent to the server.

[0144] Step 3:

[0145] The server parses the selected data it receives and generates an appropriate prompt. Specifically, the server extracts the "query" field from the received data and generates a corresponding prompt. For example, if the received data is { "query": "Check business hours"}, it will generate the prompt "Please tell me your current business hours". The input is the selected boilerplate data, and the output is the generated prompt.

[0146] Step 4:

[0147] The server sends a generated prompt to the generative artificial intelligence (AI). Specifically, it sends the generated prompt text as an API request to the generative AI model. The generative AI receives this prompt and generates a response. For example, in response to the prompt "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays." The input is the generated prompt text, and the output is a natural language response from the generative AI model.

[0148] Step 5:

[0149] The server sends the generated response to the terminal. Specifically, the server converts the received natural language response back into JSON format and sends it to the terminal as an HTTP response. For example, if the generated response is "Our business hours are from 9 am to 6 pm on weekdays," it will be sent to the terminal in the format { "response": "Our business hours are from 9 am to 6 pm on weekdays"}. The input is the response sentence from the generative artificial intelligence model, and the output is the response data sent to the terminal.

[0150] Step 6:

[0151] The terminal receives a response from the server and displays it to the user. Specifically, the terminal parses the received data and displays it on the screen. Through this screen, the user can confirm a response such as, "Our store hours are from 9 am to 6 pm on weekdays." The input is the response data from the server, and the output is the natural language response displayed on the screen.

[0152] (Application Example 1)

[0153] 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."

[0154] In recent years, there has been a growing demand for information provision systems utilizing smart devices to improve customer convenience in physical stores. However, conventional systems have challenges in responding immediately to customer needs and providing efficient guidance and product information. Furthermore, conventional systems often rely on human intervention, resulting in high operational costs and maintenance burdens. Therefore, there is a need for the development of automated systems that can provide customers with the information they need quickly and accurately.

[0155] 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.

[0156] In this invention, the server includes means for receiving an operation selected by the user from a set of predefined inputs, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for providing the generated response to the user, and means for providing an application installed on a smart device to provide information relevant to the user. This makes it possible to provide the information the user needs quickly and accurately, and to significantly improve customer convenience in physical stores.

[0157] A "user" is a customer who uses a system to obtain information.

[0158] "Standard input" refers to input options provided to the user as predetermined choices.

[0159] A "generated prompt" is an input sentence for a generative artificial intelligence system that is constructed based on a predefined input selected by the user.

[0160] "Generative artificial intelligence" refers to an artificial intelligence system that generates responses in natural language based on input prompts.

[0161] "Response" refers to the reply generated by generative artificial intelligence to a user's inquiry.

[0162] "Means of providing to the user" refers to the interface or method for displaying the generated response to the user.

[0163] A "smart device" refers to a portable device with internet connectivity, such as a smartphone or tablet.

[0164] An "application" is a software program that runs on a smart device and provides information to the user.

[0165] System Configuration

[0166] This invention is an information provision system designed to improve customer convenience in physical stores. The system mainly consists of three main components: a user terminal, a server, and a generative artificial intelligence model.

[0167] 1. User terminal

[0168] The user terminal refers to a smart device such as a smartphone or tablet. This terminal presents pre-defined input options and provides an interface for the user to select the information they need.

[0169] 2. Server

[0170] The server receives standardized input data sent from the user terminal and creates a generation prompt. It then sends this generation prompt to a generative artificial intelligence model and sends the generated response back to the user terminal.

[0171] 3. Generative artificial intelligence models

[0172] Generative artificial intelligence models generate natural language responses based on input prompts. Specifically, high-performance generative AI modeling technologies such as OpenAI's GPT-3® are used.

[0173] Program processing and the hardware and software used

[0174] User terminal

[0175] The user terminal accepts pre-defined inputs from the user through the user interface. For example, options such as "Facility Guide," "Product Information Inquiry," and "Promotion Information" are displayed. When the user selects a pre-defined input, this information is sent to the server.

[0176] server

[0177] The server receives predefined inputs sent from the user's terminal. After receiving them, the server generates a prompt based on the selected predefined input. For example, if the predefined input is "building information," the server generates the prompt "I would like building information." This prompt is sent to a generative artificial intelligence model, which generates a response in natural language.

[0178] Generative artificial intelligence models

[0179] The OpenAI GPT-3 is used as the generative artificial intelligence model. GPT-3 analyzes the sent prompt and generates an appropriate response. For example, it provides specific guidance information such as, "The elevator is located at the back right of the entrance hall."

[0180] Display of response to user terminal

[0181] The generated response is sent back to the user terminal via the server. The user terminal displays the generated response on its user interface, allowing the user to immediately obtain the necessary information.

[0182] Examples of specific cases and prompt statements

[0183] Specific example

[0184] Let's consider a scenario where a user uses their smartphone to obtain information within a physical store. For example, if the user selects "Store Guide," the system will operate as follows:

[0185] 1. The user opens the smartphone app and selects "In-house Guide".

[0186] 2. The app sends a request for "building information" to the server.

[0187] 3. The server generates a prompt saying "I would like a tour of the building" and sends it to the generative artificial intelligence.

[0188] 4. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0189] 5. The server sends the generated response to the user's terminal.

[0190] 6. A response is displayed on the user's smartphone.

[0191] Example of a prompt

[0192] Prompt: "I'd like a tour of the building."

[0193] Response: "The elevator is located at the back right of the entrance hall."

[0194] In this way, the invention can quickly and accurately provide users with a variety of information they need within a physical store.

[0195] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0196] Step 1:

[0197] The user opens an application on their smart device.

[0198] Input: Smart device operation

[0199] Operation: The user launches the application on their smart device and accesses an interface that displays pre-set input options.

[0200] Output: The predefined input options are displayed in the user interface.

[0201] Step 2:

[0202] The user selects "In-house information" from the pre-defined input options.

[0203] Input: User selection operation

[0204] Operation: Select "Building Guide" from the user interface, and the application will recognize this selection.

[0205] Output: Selected standard input data

[0206] Step 3:

[0207] The terminal sends the selected standard input data to the server.

[0208] Input: Standard input data

[0209] Operation: The terminal sends the selected predefined input data to the server as an HTTP request.

[0210] Output: Standard input data received by the server

[0211] Step 4:

[0212] The server generates a prompt based on predefined input.

[0213] Input: Standard input data

[0214] Operation: The server parses the received standardized input data and selects a corresponding generated prompt from a template. In this example, the prompt "I would like a tour of the building" is generated.

[0215] Output: Generated prompt("I'd like a tour of the building")

[0216] Step 5:

[0217] The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[0218] Input: Generate prompt

[0219] Operation: The server sends a generated prompt to the OpenAI GPT-3 API. GPT-3 parses the prompt and generates an appropriate response.

[0220] Output: Generated response (e.g., "The elevator is located at the back right of the entrance hall.")

[0221] Step 6:

[0222] The server sends the generated response to the user's terminal.

[0223] Input: Generated response

[0224] Operation: The server sends the generated response to the user's terminal as an HTTP response.

[0225] Output: Response data received by the user terminal

[0226] Step 7:

[0227] The terminal displays the response it has received to the user.

[0228] Input: Received response data

[0229] Operation: The response data received by the user terminal is displayed on the user interface. The user confirms the information, "The elevator is located at the back right of the entrance hall."

[0230] Output: Response data displayed on the user interface

[0231] This processing step allows users to efficiently obtain information within the physical store, improving convenience.

[0232] 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.

[0233] System Configuration

[0234] In addition to its basic function of receiving standardized input from the user and generating a response using generative artificial intelligence, the system of the present invention improves the quality of the response by incorporating an emotion engine that recognizes and analyzes the user's emotions. This system includes the following main components.

[0235] 1. User Interface Terminal

[0236] 2. Server

[0237] 3. Generative artificial intelligence models

[0238] 4. Emotional Engine

[0239] Program processing

[0240] Acceptance of user input

[0241] terminal

[0242] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. Examples of choices include "check opening hours," "get directions," and "inquire about product information." When presenting these choices, the terminal can use an emotion engine to analyze the user's emotions and suggest appropriate options.

[0243] Submit your selections

[0244] terminal

[0245] The system receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selection and initiate the process of generating a corresponding response.

[0246] Prompt generation

[0247] server

[0248] The server generates prompts based on the standardized input information it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it incorporates feedback from the emotion engine to adjust the prompts to match the user's emotions.

[0249] Response generation

[0250] server

[0251] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, in response to "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[0252] Emotional regulation of responses

[0253] Emotional Engine

[0254] Once the generated response is returned to the server, the emotion engine analyzes it and modifies it to suit the user's current emotions. For example, if the user is stressed, the response is changed to be more polite and kind.

[0255] Displaying responses to the user

[0256] terminal

[0257] The terminal receives the response sent from the server and displays it to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our store hours are from 9 am to 6 pm on weekdays. Is there anything else we can help you with?"

[0258] Specific example

[0259] Examples of call centers

[0260] scenario

[0261] Consider a scenario where a user accesses an automated call center system to inquire about business hours. If the emotion engine determines that the user is experiencing stress, the process would proceed as follows:

[0262] 1. The user selects "Check business hours".

[0263] 2. The terminal sends the selected data to the server.

[0264] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0265] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0266] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0267] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[0268] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0269] Example of a sign (in-house guide)

[0270] scenario

[0271] Let's consider a scenario where a user wants to know the location of the elevator using a terminal for building information. If the emotion engine determines that the user is in an excited state, the process would proceed as follows:

[0272] 1. The user selects the "elevator location".

[0273] 2. The terminal sends the selected data to the server.

[0274] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0275] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0276] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0277] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[0278] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0279] In this way, the system of the present invention can respond quickly and accurately to a variety of inquiries from users, and can also provide responses that are tailored to the user's emotions. This makes it possible to achieve higher user satisfaction.

[0280] The following describes the processing flow.

[0281] Step 1:

[0282] The user accesses a guidance terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed. During this process, the user's emotions are analyzed by an emotion engine.

[0283] Step 2:

[0284] The terminal sends the user's selected standard input data and the emotion data analyzed by the emotion engine to the server. This allows the server to recognize the user's selections and emotions.

[0285] Step 3:

[0286] The server generates an appropriate generation prompt based on the received standard input data. For example, when "Check business hours" is selected, a prompt such as "Please tell me the current business hours" is generated.

[0287] Step 4:

[0288] The server processes the generated prompt with the emotion engine and adjusts the prompt according to the user's emotion. For example, if the user is already feeling stressed, it is changed to a gentle tone such as "Sorry to trouble you, but please tell me the current business hours".

[0289] Step 5:

[0290] The server sends the adjusted generation prompt to the generative artificial intelligence to generate a response. The generative artificial intelligence generates a response in natural language based on the received prompt.

[0291] Step 6:

[0292] The generative artificial intelligence generates a response according to the prompt. For example, for "Please tell me the current business hours", a response such as "Our business hours are from 9:00 to 18:00 on weekdays" is generated.

[0293] Step 7:

[0294] The server receives the response generated by the generative artificial intelligence, analyzes the response again with the emotion engine, and modifies the content in a form suitable for the user's emotion. For example, if the user is feeling stressed, it is made more polite like "Our business hours are from 9:00 to 18:00 on weekdays. We apologize for any inconvenience. Do you have any other questions?"

[0295] Step 8:

[0296] The server sends an emotionally regulated response to the terminal.

[0297] Step 9:

[0298] The terminal displays the response it receives from the server to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our business hours are weekdays from 9 am to 6 pm. We apologize for any inconvenience. Do you have any further questions?"

[0299] Step 10:

[0300] The system reviews the user's responses, whether displayed or voiced, and obtains the necessary information. This cycle is repeated if the user makes further inquiries.

[0301] (Example 2)

[0302] 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".

[0303] Traditional dialogue systems tend to have low user satisfaction because they generate responses without considering the user's emotional state. Furthermore, users don't always choose the optimal option, resulting in inappropriate responses. This can lead to user stress and inconvenience, which is a significant problem.

[0304] 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.

[0305] In this invention, the server includes means for receiving an operation selected by the user from predefined inputs, means for transmitting the selected predefined input, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence to generate a response, means for adjusting the generated response according to the user's emotion, and means for providing the adjusted response to the user. Thereby, it becomes possible to provide a response adapted to the user's emotional state, improving user satisfaction.

[0306] 1. The "user" is the entity that uses the system to select from predefined inputs and receives the response.

[0307] 2. The "predefined input" is a predefined input format or item that the user can select.

[0308] 3. The "means for receiving the selection operation" is a function that provides an interface for the user to select an appropriate option from predefined inputs.

[0309] 4. The "means for transmitting the selected predefined input" is a communication function for transmitting the content selected by the user to the server.

[0310] 5. The "generation prompt" is a sentence in the form of a question or instruction generated based on the selected predefined input.

[0311] 6. The "means for generating a generation prompt" is a function that generates an appropriate question or instruction based on the received predefined input.

[0312] 7. The "generative artificial intelligence" is an artificial intelligence model that receives the generation prompt as input and generates a natural language response based on it.

[0313] 8. The "means for transmitting the generation prompt to the generative artificial intelligence" is a communication function for transmitting the generation prompt to the generative artificial intelligence to generate a response.

[0314] 9. "Means for generating a response" refers to the function of a generative artificial intelligence that receives a generation prompt and generates a natural language response based on it.

[0315] 10. "Means for adjusting generated responses to match the user's emotions" refers to a function that modifies generated responses using an emotion engine to match the user's current emotional state.

[0316] 11. “Means of providing an adapted response to the user” means a function that provides the user with an emotionally adapted response, either visually or aurally.

[0317] System Configuration

[0318] The system of the present invention includes a terminal that accepts an operation for a user to select from a set of predefined inputs, a server that transmits the selected predefined input, a server that generates a generation prompt based on the selected predefined input, a server that transmits the generation prompt to a generative artificial intelligence model and causes it to generate a response, an emotion engine that adjusts the generated response to match the user's emotions, and a terminal that provides the adjusted response to the user.

[0319] Hardware and software

[0320] The hardware used in this system includes terminals that provide the user interface (such as PCs, tablets, and smartphones), servers that process data, and cameras and microphones that collect user emotion data. The software includes generative artificial intelligence models (such as GPT-3), emotion engines (emotion analysis software), communication APIs, and applications for the user interface.

[0321] Acceptance of user input

[0322] terminal

[0323] The user clicks on pre-defined input options on the device screen. These options include, for example, "Check opening hours," "Get directions," and "Inquire about product information." The device transmits the user's facial expressions and voice via the camera and microphone to an emotion engine, which analyzes the user's emotions. Based on this analysis, it can also present the user with the most suitable options.

[0324] Submit your selections

[0325] terminal

[0326] The user's selected input data is sent to the server. This data is sent via a dedicated communication API, and its contents are recorded on the server.

[0327] Prompt generation

[0328] server

[0329] The server generates prompts based on the selected data it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it adjusts the prompt based on the user's emotions, taking into account feedback from the emotion engine. If the emotion engine determines that the user is stressed, the prompt becomes more polite, such as "Could you please tell me your current opening hours?"

[0330] Response generation

[0331] server

[0332] The server sends a generation prompt to a generative artificial intelligence model (e.g., GPT-3) to generate a response. Based on the received prompt, the generative AI model generates an appropriate natural language response. This ensures that the user receives an accurate and appropriate response to the question they selected.

[0333] Emotional regulation of responses

[0334] Emotional Engine

[0335] Once the generated response is returned to the server, the emotion engine analyzes the response and modifies it to suit the user's emotions. For example, if the user is feeling stressed by the generated response, "Our store hours are from 9 am to 6 pm on weekdays," the engine will modify it to, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[0336] Displaying responses to the user

[0337] terminal

[0338] The terminal receives an emotionally tuned response sent from the server and displays it to the user. The terminal not only displays the response on the screen but also plays it aloud as needed. For example, it can display the response "Our current business hours are weekdays from 9 am to 6 pm" on the screen and play it aloud simultaneously.

[0339] Specific example

[0340] Examples of call centers

[0341] Here's a specific example of a user accessing a call center's automated response system to inquire about business hours. The following is the process if the emotion engine determines the user is experiencing stress.

[0342] 1. The user selects "Check business hours".

[0343] 2. The terminal sends the selected data to the server.

[0344] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0345] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[0346] 5. The generative artificial intelligence model generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0347] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[0348] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0349] Examples of signs

[0350] Here's a concrete example of a user wanting to know the location of the elevators using a terminal for building information. The process when the emotion engine determines that the user is in an excited state is as follows:

[0351] 1. The user selects the "elevator location".

[0352] 2. The terminal sends the selected data to the server.

[0353] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0354] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[0355] 5. The generative artificial intelligence model generates the response, "The elevator is located in the back right of the entrance hall."

[0356] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[0357] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0358] This system makes it possible to provide appropriate responses that are adapted to the user's emotions, and is expected to improve user satisfaction.

[0359] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0360] Step 1: Receiving user input

[0361] terminal

[0362] The user clicks on a pre-defined input option on the device screen. Examples of options include "Check opening hours," "Store information," and "Inquire about product information."

[0363] input

[0364] Items selected by the user (e.g., "Check business hours")

[0365] Data processing

[0366] The selected items are retrieved as data and converted to a format corresponding to the next processing step.

[0367] output

[0368] Selected item data (e.g., "Check business hours")

[0369] Specific operation: The device collects the user's facial expressions and voice through the camera and microphone, sends them to the emotion engine, and analyzes the user's emotions. Based on the analysis results, it presents the user with the most suitable options.

[0370] Step 2: Submit your selections

[0371] terminal

[0372] The input data selected by the user is sent to the server.

[0373] input

[0374] Selected item data (e.g., "Check business hours")

[0375] Data processing

[0376] Convert the selected item data into an HTTP request format.

[0377] output

[0378] HTTP request data sent to the server

[0379] Specific operation: Selected item data is sent to the server using a dedicated communication API. The server receives the request and records it in the database.

[0380] Step 3: Generate prompt

[0381] server

[0382] The server creates a generation prompt based on the selected data it receives.

[0383] input

[0384] Selection data sent via HTTP request (e.g., "Check business hours")

[0385] Data processing

[0386] Based on the selected data received, an appropriate prompt is generated (e.g., "Please tell me your current business hours"). Furthermore, the prompt is adjusted based on feedback from the emotion engine.

[0387] output

[0388] The generated prompt message (e.g., "What are your current business hours?")

[0389] Specific operation: The emotion engine analyzes the user's emotional state, and if it determines, for example, that the user is feeling stressed, it adjusts the prompt to something like, "Could you tell me your current business hours?"

[0390] Step 4: Response Generation

[0391] server

[0392] The server sends a generation prompt to a generative artificial intelligence model, which then generates a response.

[0393] input

[0394] The generated prompt message (e.g., "What are your current business hours?")

[0395] Data processing

[0396] The generation prompt is sent to the generative artificial intelligence model using a communication API.

[0397] output

[0398] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[0399] Specific operation: A generation prompt is sent to a generative artificial intelligence model using natural language processing techniques (e.g., GPT-3), and an appropriate response is generated.

[0400] Step 5: Emotional regulation of responses

[0401] Emotional Engine

[0402] The generated response is analyzed, and the content is modified to suit the user's emotions.

[0403] input

[0404] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[0405] Data processing

[0406] The emotion engine analyzes the user's emotional state and modifies the response text accordingly (e.g., "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience.").

[0407] output

[0408] Corrected response data

[0409] Specific action: When the emotion engine detects a user's stress level, it adds polite phrases such as "We apologize for any inconvenience this may cause" to the response.

[0410] Step 6: Displaying a response to the user

[0411] terminal

[0412] The terminal receives an emotion-adjusted response sent from the server and displays it to the user.

[0413] input

[0414] Corrected response data (Example: "Our business hours are from 9:00 AM to 6:00 PM on weekdays. We apologize for any inconvenience.")

[0415] Data processing

[0416] The data is converted for screen display, and then converted for audio output as needed.

[0417] output

[0418] Response information that the user receives visually or aurally

[0419] Specific operation: The device displays the response on the screen and plays it aloud. For example, it displays the response "Our current business hours are from 9 am to 6 pm on weekdays" on the screen and plays it aloud.

[0420] (Application Example 2)

[0421] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0422] Conventional user interface systems, when generating responses using generative artificial intelligence in response to standardized user input, lacked the ability to consider the user's emotional state, posing a challenge to improving the user experience. In particular, within autonomous vehicles, it is necessary to appropriately recognize the stress and excitement felt by passengers and provide corresponding responses to achieve a more comfortable riding experience.

[0423] 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 receiving an operation selected by the user from a set of standard inputs, means for generating a generation prompt based on the selected standard input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for analyzing the generated response with an emotion engine and modifying it according to the user's emotional state, and means for providing the user with an emotion-adjusted response. This makes it possible to provide a response that takes the user's emotional state into consideration, and in particular, it is possible to provide a comfortable and reassuring riding experience to passengers of autonomous vehicles.

[0424] "A means of accepting user selection from predefined inputs" refers to an interface that allows users to select their desired item from multiple options presented.

[0425] "Means for generating a generation prompt based on selected standard input" refers to a function that creates a specific prompt to send to a generative artificial intelligence based on the input content selected by the user.

[0426] "A means of sending a generation prompt to a generative artificial intelligence and causing it to generate a response" refers to a function that sends a generated prompt to a generative artificial intelligence and obtains a natural language response as its answer.

[0427] "A means of analyzing the generated response with an emotion engine and modifying it according to the user's emotional state" refers to a function that analyzes the response generated by a generative artificial intelligence with an emotion analysis engine and adapts the response content to the user's emotional state based on the analysis results.

[0428] "Means of providing emotionally regulated responses to users" refers to functions that communicate responses modified to match the user's emotional state to the user through means such as sight or hearing.

[0429] "A means of displaying multiple options that allow the user to select one of the predefined inputs" refers to a function that presents multiple choices on a display device that the user can select from, thereby enabling the user to make an appropriate choice.

[0430] "A means of analyzing a user's emotions using an emotion engine and suggesting appropriate options" refers to a function that analyzes the user's emotional state using an emotion analysis engine and presents the user with the most suitable options based on the results.

[0431] "Means of using a pre-saved template corresponding to selected standard input when sending a generation prompt to a generative artificial intelligence" refers to a function that generates a prompt using a pre-saved template based on the standard input selected by the user and sends it to the generative artificial intelligence.

[0432] "Means for adjusting prompts based on the user's emotional state" refers to a function that appropriately modifies the content of the generated prompts, taking into account the results of the user's emotion analysis.

[0433] System Configuration and Hardware

[0434] This invention is a system that receives standardized input from the user, generates a response using generative artificial intelligence, and further analyzes the user's emotions using an emotion engine to provide a response tailored to the user's emotional state. This system consists of the following main components.

[0435] 1. User interface devices (smart glasses, in-car displays, microphones, speakers, etc.)

[0436] 2. Server

[0437] 3. Generative artificial intelligence models

[0438] 4. Emotional Engine

[0439] software

[0440] The speech_recognition library is used to convert the user's speech into text.

[0441] The user's emotions are analyzed using the emotion analysis engine in the Hugging Face transformers library.

[0442] Access a generative artificial intelligence service using a RESTful API and generate a response.

[0443] Processing flow

[0444] The server will perform the following steps:

[0445] 1. Receiving user input:

[0446] The user interface terminal accepts user input by allowing selection from a set of predefined inputs. For user voice input, the speech_recognition library is used to convert the speech to text.

[0447] 2. Emotion analysis:

[0448] The acquired text data is sent to the emotion analysis engine in Hugging Face's transformers library to determine the user's emotional state.

[0449] 3. Prompt generation:

[0450] The system generates prompts based on predefined inputs selected by the user. For example, if the user selects that they want to go to the next tourist destination, the prompt "I would like to go to the next tourist destination." will be generated.

[0451] 4. Response generation:

[0452] The server sends the generated prompt to a generative artificial intelligence model, which then generates a response. An example of a generated response might be, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?"

[0453] 5. Emotional regulation:

[0454] The generated response is analyzed by an emotion engine, and the response content is modified according to the user's emotional state. For example, if the user is feeling stressed, the response might be modified to something like, "For your next sightseeing destination, there is a nearby tourist attraction called XX. We apologize for any inconvenience."

[0455] 6. Providing responses to users:

[0456] Emotionally tuned responses are provided on the user interface terminal, either through display or audio.

[0457] Specific example

[0458] For example, when used inside an autonomous vehicle, the following are possible prompt messages and responses:

[0459] User input: I want to go to the next tourist destination. Emotional state: positive

[0460] Examples of responses from generative artificial intelligence models:

[0461] As for your next sightseeing destination, there's a nearby tourist spot called XX. Why not visit it?

[0462] Examples of emotionally regulated responses:

[0463] For your next sightseeing destination, there is a nearby tourist attraction called [Name of tourist spot]. Have a wonderful time!

[0464] In this way, it becomes possible to respond in a way that takes into account the user's emotional state, and in particular, to provide a comfortable and reassuring riding experience for passengers in autonomous vehicles.

[0465] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0466] Step 1:

[0467] The system accepts user selections from a set of predefined input options. Using a user interface terminal (such as smart glasses, an in-car display, or a microphone), the user selects their desired item from multiple options presented. The terminal receives the input (voice or touch) and sends it to the server as text data.

[0468] Step 2:

[0469] The server receives the text data entered by the user and sends it to the sentiment analysis engine in the Hugging Face transformers library. This sentiment analysis engine analyzes the input text data and determines the user's emotional state (positive, negative, etc.). The output is returned as an emotion label and received by the server.

[0470] Step 3:

[0471] Based on the sentiment analysis results, the server creates a generated prompt corresponding to the user's selected standard input. This prompt is sent to the generative artificial intelligence system and converted into specific text, such as "I would like to go to the next tourist destination." The prompt is constructed based on pre-saved templates.

[0472] Step 4:

[0473] The server sends the generated prompt to the generative artificial intelligence (AI). The AI ​​analyzes the prompt and generates a corresponding natural language response. For example, it might generate a response like, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?" This response is then returned to the server.

[0474] Step 5:

[0475] The server sends the generated response back to the emotion engine, which then adjusts the response based on the user's emotional state. For example, if the user is stressed, the emotion engine might modify the response to something like, "For your next sightseeing destination, a nearby attraction is XX. We apologize for any inconvenience." The modified response is then returned to the server.

[0476] Step 6:

[0477] The server sends an emotion-adjusted response to the user interface terminal. The terminal then provides the modified response to the user via display and audio. This allows the user to receive a more appropriate response based on their emotional state.

[0478] 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.

[0479] 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.

[0480] 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.

[0481] [Second Embodiment]

[0482] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0483] 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.

[0484] 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).

[0485] 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.

[0486] 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.

[0487] 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).

[0488] 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.

[0489] 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.

[0490] 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.

[0491] 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.

[0492] 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.

[0493] 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".

[0494] System Configuration

[0495] The system of the present invention automates a series of processes, from receiving a standard input selected by the user to generating a response using generative artificial intelligence, and then providing that response to the user. This system includes the following main components:

[0496] 1. User Interface Terminal

[0497] 2. Server

[0498] 3. Generative artificial intelligence models

[0499] Program processing

[0500] Acceptance of user input

[0501] terminal

[0502] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. For example, options such as "Check opening hours," "Firm information," and "Inquire about product information" are available. Once the user makes a selection, that information is sent from the terminal to the server.

[0503] Submit your selections

[0504] terminal

[0505] The terminal sends the user's selected predefined input data to the server. This allows the server to prepare to begin the next process.

[0506] Prompt generation

[0507] server

[0508] The server generates a prompt based on the standardized input information it receives. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to the generative artificial intelligence.

[0509] Response generation

[0510] server

[0511] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, a response such as, "Our business hours are from 9 am to 6 pm on weekdays."

[0512] Displaying responses to the user

[0513] terminal

[0514] The terminal receives the response sent from the server and displays it to the user. By checking this result, the user can immediately obtain the necessary information.

[0515] Specific example

[0516] Examples of call centers

[0517] scenario

[0518] Consider a scenario where a user accesses a call center's automated response system to inquire about business hours. The process in this case is as follows:

[0519] 1. The user selects "Check business hours".

[0520] 2. The terminal sends the selected data to the server.

[0521] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0522] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0523] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0524] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0525] Example of a sign (in-house guide)

[0526] scenario

[0527] Let's consider a scenario where a user wants to find the location of the elevators using a terminal within the building. The process in this case is as follows:

[0528] 1. The user selects the "elevator location".

[0529] 2. The terminal sends the selected data to the server.

[0530] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0531] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0532] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0533] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0534] In this way, the system of the present invention can respond quickly and accurately to a wide range of inquiries from users. Furthermore, it can provide the latest information while minimizing maintenance work. High reliability is ensured by having humans handle final decisions and special cases.

[0535] The following describes the processing flow.

[0536] Step 1:

[0537] The user accesses a display terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed.

[0538] Step 2:

[0539] The terminal receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selections.

[0540] Step 3:

[0541] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, the server generates the prompt "Please tell me your current business hours."

[0542] Step 4:

[0543] The server sends a generation prompt to the generative artificial intelligence. The generative artificial intelligence generates a response in natural language based on the received prompt.

[0544] Step 5:

[0545] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it will generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[0546] Step 6:

[0547] The server receives the response generated by the generative artificial intelligence and sends that response to the terminal. This makes the response available to the user.

[0548] Step 7:

[0549] The terminal displays the response it receives from the server to the user. For example, it might display a message on the screen or via audio saying, "Our store hours are from 9:00 AM to 6:00 PM on weekdays."

[0550] Step 8:

[0551] The system confirms the user's response, whether displayed or spoken, and retrieves the necessary information.

[0552] (Example 1)

[0553] 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."

[0554] Currently, in many systems, the process of responding quickly and appropriately to user inquiries is complex and time-consuming. In particular, ensuring efficiency and accuracy in generating and displaying responses to routine inquiries is difficult. Traditional systems often require human intervention during the response generation process, leading to increased costs and slower response times. Furthermore, the lack of adequate means to consistently provide up-to-date information results in decreased user satisfaction.

[0555] 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.

[0556] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for processing the selected predefined inputs and sending them to the server, means for generating a generation prompt based on the predefined inputs received by the server, means for sending the generation prompt to a generative artificial intelligence system to generate a natural language response, and means for providing the generated natural language response to the user. This makes it possible to always provide the latest information quickly and accurately in response to user inquiries. Furthermore, the overall efficiency and automation of the system are improved, and human intervention in the response generation process is minimized.

[0557] A "user" is an individual or group that operates the system and selects predefined input options.

[0558] "Standard input" refers to pre-configured inquiry content or operation options that users select.

[0559] A "server" is a computing system that receives standardized user input, generates prompts, sends them to generative artificial intelligence, and processes responses.

[0560] A "terminal" is an interface device operated by a user, which sends user input to a server and displays the server's response.

[0561] A "generated prompt" is a set of instructions created by a server based on a user's standardized input, and serves as input data for generating a response from a generative artificial intelligence.

[0562] "Generative artificial intelligence" refers to machine learning algorithms and models that receive a generative prompt and generate a natural language response based on it.

[0563] A "natural language response" is a response sentence in a language format that is easy for humans to understand, which is output by a generative artificial intelligence system based on a generation prompt.

[0564] This invention automates a series of processes, from receiving predefined inputs selected by the user to generating responses using generative artificial intelligence, and then providing those responses to the user. The embodiments for carrying out this invention are described in detail below.

[0565] System Configuration

[0566] The system of the present invention includes the following main components.

[0567] 1. User interface terminals: For example, mobile devices such as iPads and Android tablets are used.

[0568] 2. Servers: Cloud-based servers such as AWS EC2 and Google Cloud Compute Engine will be used.

[0569] 3. Generative artificial intelligence models: Natural language processing models such as OpenAI GPT-4 and Google BERT are used.

[0570] Selection at the user interface terminal

[0571] The user selects their desired option from several choices displayed on the terminal they are using. For example, options such as "Check opening hours," "Firm information guide," and "Inquire about product information" may be displayed. Once the user makes a selection, that information is sent from the terminal to the server.

[0572] Prompt generation on the server

[0573] The server generates appropriate prompts based on the standardized input information received from the user. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to a generative artificial intelligence model.

[0574] Response generation in generative artificial intelligence models

[0575] A generative artificial intelligence model generates a natural language response based on a prompt received from the server. For example, a response such as "Our store hours are from 9 am to 6 pm on weekdays" is generated. This response is then sent back to the server.

[0576] Sending and displaying responses to the user interface terminal

[0577] The server sends the generated response to the terminal, which then displays the response to the user. By checking the response displayed on the terminal's screen, the user can instantly obtain the necessary information.

[0578] Specific example

[0579] Examples of call centers

[0580] Here's a concrete example of the procedure a user would follow if they accessed a call center's automated response system to inquire about business hours.

[0581] 1. The user selects "Check business hours".

[0582] 2. The terminal sends the selected data to the server.

[0583] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0584] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[0585] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0586] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0587] Example of a sign (in-house guide)

[0588] Here's a concrete example of how a user can find out the location of the elevators using a terminal within the building.

[0589] 1. The user selects the "elevator location".

[0590] 2. The terminal sends the selected data to the server.

[0591] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0592] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[0593] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0594] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0595] Specific examples of prompt phrases include, "What are your current business hours?" and "Where is the elevator?"

[0596] As described above, the system of the present invention is capable of responding quickly and accurately to a wide range of inquiries from users. The overall efficiency and automation of the system are improved, and it becomes possible to always provide the latest information.

[0597] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0598] Step 1:

[0599] The user makes a selection for a predefined input. The user interface terminal displays multiple options to the user. For example, options may include "Check opening hours," "Get directions within the building," and "Inquire about product information." The user makes a selection by tapping or clicking. The input is the user's selection, and the output is the data of the selected option.

[0600] Step 2:

[0601] The device sends the user's selections to the server. Specifically, the device sends the data of the selected options to the server as an HTTP request. This data is in JSON format and is passed to the server in a format such as { "query": "Check business hours"}. The input is the user's selection data, and the output is the selection data sent to the server.

[0602] Step 3:

[0603] The server parses the selected data it receives and generates an appropriate prompt. Specifically, the server extracts the "query" field from the received data and generates a corresponding prompt. For example, if the received data is { "query": "Check business hours"}, it will generate the prompt "Please tell me your current business hours". The input is the selected boilerplate data, and the output is the generated prompt.

[0604] Step 4:

[0605] The server sends a generated prompt to the generative artificial intelligence (AI). Specifically, it sends the generated prompt text as an API request to the generative AI model. The generative AI receives this prompt and generates a response. For example, in response to the prompt "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays." The input is the generated prompt text, and the output is a natural language response from the generative AI model.

[0606] Step 5:

[0607] The server sends the generated response to the terminal. Specifically, the server converts the received natural language response back into JSON format and sends it to the terminal as an HTTP response. For example, if the generated response is "Our business hours are from 9 am to 6 pm on weekdays," it will be sent to the terminal in the format { "response": "Our business hours are from 9 am to 6 pm on weekdays"}. The input is the response sentence from the generative artificial intelligence model, and the output is the response data sent to the terminal.

[0608] Step 6:

[0609] The terminal receives a response from the server and displays it to the user. Specifically, the terminal parses the received data and displays it on the screen. Through this screen, the user can confirm a response such as, "Our store hours are from 9 am to 6 pm on weekdays." The input is the response data from the server, and the output is the natural language response displayed on the screen.

[0610] (Application Example 1)

[0611] 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."

[0612] In recent years, there has been a growing demand for information provision systems utilizing smart devices to improve customer convenience in physical stores. However, conventional systems have challenges in responding immediately to customer needs and providing efficient guidance and product information. Furthermore, conventional systems often rely on human intervention, resulting in high operational costs and maintenance burdens. Therefore, there is a need for the development of automated systems that can provide customers with the information they need quickly and accurately.

[0613] 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.

[0614] In this invention, the server includes means for receiving an operation selected by the user from a set of predefined inputs, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for providing the generated response to the user, and means for providing an application installed on a smart device to provide information relevant to the user. This makes it possible to provide the information the user needs quickly and accurately, and to significantly improve customer convenience in physical stores.

[0615] A "user" is a customer who uses a system to obtain information.

[0616] "Standard input" refers to input options provided to the user as predetermined choices.

[0617] A "generated prompt" is an input sentence for a generative artificial intelligence system that is constructed based on a predefined input selected by the user.

[0618] "Generative artificial intelligence" refers to an artificial intelligence system that generates responses in natural language based on input prompts.

[0619] "Response" refers to the reply generated by generative artificial intelligence to a user's inquiry.

[0620] "Means of providing to the user" refers to the interface or method for displaying the generated response to the user.

[0621] A "smart device" refers to a portable device with internet connectivity, such as a smartphone or tablet.

[0622] An "application" is a software program that runs on a smart device and provides information to the user.

[0623] System Configuration

[0624] This invention is an information provision system designed to improve customer convenience in physical stores. The system mainly consists of three main components: a user terminal, a server, and a generative artificial intelligence model.

[0625] 1. User terminal

[0626] The user terminal refers to a smart device such as a smartphone or tablet. This terminal presents pre-defined input options and provides an interface for the user to select the information they need.

[0627] 2. Server

[0628] The server receives standardized input data sent from the user terminal and creates a generation prompt. It then sends this generation prompt to a generative artificial intelligence model and sends the generated response back to the user terminal.

[0629] 3. Generative artificial intelligence models

[0630] Generative artificial intelligence models generate natural language responses based on input prompts. Specifically, high-performance generative AI modeling technologies such as OpenAI's GPT-3 are used.

[0631] Program processing and the hardware and software used

[0632] User terminal

[0633] The user terminal accepts pre-defined inputs from the user through the user interface. For example, options such as "Facility Guide," "Product Information Inquiry," and "Promotion Information" are displayed. When the user selects a pre-defined input, this information is sent to the server.

[0634] server

[0635] The server receives predefined inputs sent from the user's terminal. After receiving them, the server generates a prompt based on the selected predefined input. For example, if the predefined input is "building information," the server generates the prompt "I would like building information." This prompt is sent to a generative artificial intelligence model, which generates a response in natural language.

[0636] Generative artificial intelligence models

[0637] The OpenAI GPT-3 is used as the generative artificial intelligence model. GPT-3 analyzes the sent prompt and generates an appropriate response. For example, it provides specific guidance information such as, "The elevator is located at the back right of the entrance hall."

[0638] Display of response to user terminal

[0639] The generated response is sent back to the user terminal via the server. The user terminal displays the generated response on its user interface, allowing the user to immediately obtain the necessary information.

[0640] Examples of specific cases and prompt statements

[0641] Specific example

[0642] Let's consider a scenario where a user uses their smartphone to obtain information within a physical store. For example, if the user selects "Store Guide," the system will operate as follows:

[0643] 1. The user opens the smartphone app and selects "In-house Guide".

[0644] 2. The app sends a request for "building information" to the server.

[0645] 3. The server generates a prompt saying "I would like a tour of the building" and sends it to the generative artificial intelligence.

[0646] 4. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0647] 5. The server sends the generated response to the user's terminal.

[0648] 6. A response is displayed on the user's smartphone.

[0649] Example of a prompt

[0650] Prompt: "I'd like a tour of the building."

[0651] Response: "The elevator is located at the back right of the entrance hall."

[0652] In this way, the invention can quickly and accurately provide users with a variety of information they need within a physical store.

[0653] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0654] Step 1:

[0655] The user opens an application on their smart device.

[0656] Input: Smart device operation

[0657] Operation: The user launches the application on their smart device and accesses an interface that displays pre-set input options.

[0658] Output: The predefined input options are displayed in the user interface.

[0659] Step 2:

[0660] The user selects "In-house information" from the pre-defined input options.

[0661] Input: User selection operation

[0662] Operation: Select "Building Guide" from the user interface, and the application will recognize this selection.

[0663] Output: Selected standard input data

[0664] Step 3:

[0665] The terminal sends the selected standard input data to the server.

[0666] Input: Standard input data

[0667] Operation: The terminal sends the selected predefined input data to the server as an HTTP request.

[0668] Output: Standard input data received by the server

[0669] Step 4:

[0670] The server generates a prompt based on predefined input.

[0671] Input: Standard input data

[0672] Operation: The server parses the received standardized input data and selects a corresponding generated prompt from a template. In this example, the prompt "I would like a tour of the building" is generated.

[0673] Output: Generated prompt("I'd like a tour of the building")

[0674] Step 5:

[0675] The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[0676] Input: Generate prompt

[0677] Operation: The server sends a generated prompt to the OpenAI GPT-3 API. GPT-3 parses the prompt and generates an appropriate response.

[0678] Output: Generated response (e.g., "The elevator is located at the back right of the entrance hall.")

[0679] Step 6:

[0680] The server sends the generated response to the user's terminal.

[0681] Input: Generated response

[0682] Operation: The server sends the generated response to the user's terminal as an HTTP response.

[0683] Output: Response data received by the user terminal

[0684] Step 7:

[0685] The terminal displays the response it has received to the user.

[0686] Input: Received response data

[0687] Operation: The response data received by the user terminal is displayed on the user interface. The user confirms the information, "The elevator is located at the back right of the entrance hall."

[0688] Output: Response data displayed on the user interface

[0689] This processing step allows users to efficiently obtain information within the physical store, improving convenience.

[0690] 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.

[0691] System Configuration

[0692] In addition to its basic function of receiving standardized input from the user and generating a response using generative artificial intelligence, the system of the present invention improves the quality of the response by incorporating an emotion engine that recognizes and analyzes the user's emotions. This system includes the following main components.

[0693] 1. User Interface Terminal

[0694] 2. Server

[0695] 3. Generative artificial intelligence models

[0696] 4. Emotional Engine

[0697] Program processing

[0698] Acceptance of user input

[0699] terminal

[0700] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. Examples of choices include "check opening hours," "get directions," and "inquire about product information." When presenting these choices, the terminal can use an emotion engine to analyze the user's emotions and suggest appropriate options.

[0701] Submit your selections

[0702] terminal

[0703] The system receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selection and initiate the process of generating a corresponding response.

[0704] Prompt generation

[0705] server

[0706] The server generates prompts based on the standardized input information it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it incorporates feedback from the emotion engine to adjust the prompts to match the user's emotions.

[0707] Response generation

[0708] server

[0709] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, in response to "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[0710] Emotional regulation of responses

[0711] Emotional Engine

[0712] Once the generated response is returned to the server, the emotion engine analyzes it and modifies it to suit the user's current emotions. For example, if the user is stressed, the response is changed to be more polite and kind.

[0713] Displaying responses to the user

[0714] terminal

[0715] The terminal receives the response sent from the server and displays it to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our store hours are from 9 am to 6 pm on weekdays. Is there anything else we can help you with?"

[0716] Specific example

[0717] Examples of call centers

[0718] scenario

[0719] Consider a scenario where a user accesses an automated call center system to inquire about business hours. If the emotion engine determines that the user is experiencing stress, the process would proceed as follows:

[0720] 1. The user selects "Check business hours".

[0721] 2. The terminal sends the selected data to the server.

[0722] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0723] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0724] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0725] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[0726] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0727] Example of a sign (in-house guide)

[0728] scenario

[0729] Let's consider a scenario where a user wants to know the location of the elevator using a terminal for building information. If the emotion engine determines that the user is in an excited state, the process would proceed as follows:

[0730] 1. The user selects the "elevator location".

[0731] 2. The terminal sends the selected data to the server.

[0732] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0733] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0734] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0735] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[0736] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0737] In this way, the system of the present invention can respond quickly and accurately to a variety of inquiries from users, and can also provide responses that are tailored to the user's emotions. This makes it possible to achieve higher user satisfaction.

[0738] The following describes the processing flow.

[0739] Step 1:

[0740] The user accesses a guidance terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed. During this process, the user's emotions are analyzed by an emotion engine.

[0741] Step 2:

[0742] The terminal sends the user's selected standard input data and the emotion data analyzed by the emotion engine to the server. This allows the server to recognize the user's selections and emotions.

[0743] Step 3:

[0744] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, it generates the prompt "Please tell me your current business hours."

[0745] Step 4:

[0746] The server processes the generated prompts using an emotion engine, adjusting them to match the user's emotions. For example, if the user is already stressed, the prompt might be changed to a gentler tone, such as, "Excuse me, but could you please tell me your current business hours?"

[0747] Step 5:

[0748] The server sends a pre-configured generation prompt to the generative AI, which then generates a response. The generative AI then generates a response in natural language based on the received prompt.

[0749] Step 6:

[0750] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it generates the response "Our business hours are from 9 am to 6 pm on weekdays."

[0751] Step 7:

[0752] The server receives a response generated by a generative artificial intelligence, analyzes that response again using an emotion engine, and modifies the content to suit the user's emotions. For example, if the user is feeling stressed, it might respond politely with, "Our business hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience. Do you have any further questions?"

[0753] Step 8:

[0754] The server sends an emotionally regulated response to the terminal.

[0755] Step 9:

[0756] The terminal displays the response it receives from the server to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our business hours are weekdays from 9 am to 6 pm. We apologize for any inconvenience. Do you have any further questions?"

[0757] Step 10:

[0758] The system reviews the user's responses, whether displayed or voiced, and obtains the necessary information. This cycle is repeated if the user makes further inquiries.

[0759] (Example 2)

[0760] 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".

[0761] Traditional dialogue systems tend to have low user satisfaction because they generate responses without considering the user's emotional state. Furthermore, users don't always choose the optimal option, resulting in inappropriate responses. This can lead to user stress and inconvenience, which is a significant problem.

[0762] 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.

[0763] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for transmitting the selected predefined input, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence system to generate a response, means for adjusting the generated response to match the user's emotions, and means for providing the adjusted response to the user. This makes it possible to provide a response that is adapted to the user's emotional state, thereby improving user satisfaction.

[0764] 1. A "user" is an entity that uses a system to make selections from predefined inputs and receives a response.

[0765] 2. "Standard input" refers to a predetermined input format or item that the user can select.

[0766] 3. "Means for accepting selection operations" refers to a function that provides an interface for users to select the appropriate option from a set of predefined inputs.

[0767] 4. "Means for sending selected predefined inputs" refers to a communication function for sending user-selected content to the server.

[0768] 5. A "generated prompt" is a sentence in the form of a question or instruction that is generated based on selected predefined input.

[0769] 6. "Means for generating generation prompts" refers to a function that generates appropriate questions or instructions based on the received standard input.

[0770] 7. "Generative artificial intelligence" refers to an artificial intelligence model that receives a generative prompt as input and generates a natural language response based on it.

[0771] 8. "Means for sending a generation prompt to a generative artificial intelligence" refers to a communication function that sends a generation prompt to a generative artificial intelligence and causes it to generate a response.

[0772] 9. "Means for generating a response" refers to the function of a generative artificial intelligence that receives a generation prompt and generates a natural language response based on it.

[0773] 10. "Means for adjusting generated responses to match the user's emotions" refers to a function that modifies generated responses using an emotion engine to match the user's current emotional state.

[0774] 11. “Means of providing an adapted response to the user” means a function that provides the user with an emotionally adapted response, either visually or aurally.

[0775] System Configuration

[0776] The system of the present invention includes a terminal that accepts an operation for a user to select from a set of predefined inputs, a server that transmits the selected predefined input, a server that generates a generation prompt based on the selected predefined input, a server that transmits the generation prompt to a generative artificial intelligence model and causes it to generate a response, an emotion engine that adjusts the generated response to match the user's emotions, and a terminal that provides the adjusted response to the user.

[0777] Hardware and software

[0778] The hardware used in this system includes terminals that provide the user interface (such as PCs, tablets, and smartphones), servers that process data, and cameras and microphones that collect user emotion data. The software includes generative artificial intelligence models (such as GPT-3), emotion engines (emotion analysis software), communication APIs, and applications for the user interface.

[0779] Acceptance of user input

[0780] terminal

[0781] The user clicks on pre-defined input options on the device screen. These options include, for example, "Check opening hours," "Get directions," and "Inquire about product information." The device transmits the user's facial expressions and voice via the camera and microphone to an emotion engine, which analyzes the user's emotions. Based on this analysis, it can also present the user with the most suitable options.

[0782] Submit your selections

[0783] terminal

[0784] The user's selected input data is sent to the server. This data is sent via a dedicated communication API, and its contents are recorded on the server.

[0785] Prompt generation

[0786] server

[0787] The server generates prompts based on the selected data it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it adjusts the prompt based on the user's emotions, taking into account feedback from the emotion engine. If the emotion engine determines that the user is stressed, the prompt becomes more polite, such as "Could you please tell me your current opening hours?"

[0788] Response generation

[0789] server

[0790] The server sends a generation prompt to a generative artificial intelligence model (e.g., GPT-3) to generate a response. Based on the received prompt, the generative AI model generates an appropriate natural language response. This ensures that the user receives an accurate and appropriate response to the question they selected.

[0791] Emotional regulation of responses

[0792] Emotional Engine

[0793] Once the generated response is returned to the server, the emotion engine analyzes the response and modifies it to suit the user's emotions. For example, if the user is feeling stressed by the generated response, "Our store hours are from 9 am to 6 pm on weekdays," the engine will modify it to, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[0794] Displaying responses to the user

[0795] terminal

[0796] The terminal receives an emotionally tuned response sent from the server and displays it to the user. The terminal not only displays the response on the screen but also plays it aloud as needed. For example, it can display the response "Our current business hours are weekdays from 9 am to 6 pm" on the screen and play it aloud simultaneously.

[0797] Specific example

[0798] Examples of call centers

[0799] Here's a specific example of a user accessing a call center's automated response system to inquire about business hours. The following is the process if the emotion engine determines the user is experiencing stress.

[0800] 1. The user selects "Check business hours".

[0801] 2. The terminal sends the selected data to the server.

[0802] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0803] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[0804] 5. The generative artificial intelligence model generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0805] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[0806] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0807] Examples of signs

[0808] Here's a concrete example of a user wanting to know the location of the elevators using a terminal for building information. The process when the emotion engine determines that the user is in an excited state is as follows:

[0809] 1. The user selects the "elevator location".

[0810] 2. The terminal sends the selected data to the server.

[0811] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0812] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[0813] 5. The generative artificial intelligence model generates the response, "The elevator is located in the back right of the entrance hall."

[0814] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[0815] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[0816] This system makes it possible to provide appropriate responses that are adapted to the user's emotions, and is expected to improve user satisfaction.

[0817] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0818] Step 1: Receiving user input

[0819] terminal

[0820] The user clicks on a pre-defined input option on the device screen. Examples of options include "Check opening hours," "Store information," and "Inquire about product information."

[0821] input

[0822] Items selected by the user (e.g., "Check business hours")

[0823] Data processing

[0824] The selected items are retrieved as data and converted to a format corresponding to the next processing step.

[0825] output

[0826] Selected item data (e.g., "Check business hours")

[0827] Specific operation: The device collects the user's facial expressions and voice through the camera and microphone, sends them to the emotion engine, and analyzes the user's emotions. Based on the analysis results, it presents the user with the most suitable options.

[0828] Step 2: Submit your selections

[0829] terminal

[0830] The input data selected by the user is sent to the server.

[0831] input

[0832] Selected item data (e.g., "Check business hours")

[0833] Data processing

[0834] Convert the selected item data into an HTTP request format.

[0835] output

[0836] HTTP request data sent to the server

[0837] Specific operation: Selected item data is sent to the server using a dedicated communication API. The server receives the request and records it in the database.

[0838] Step 3: Generate prompt

[0839] server

[0840] The server creates a generation prompt based on the selected data it receives.

[0841] input

[0842] Selection data sent via HTTP request (e.g., "Check business hours")

[0843] Data processing

[0844] Based on the selected data received, an appropriate prompt is generated (e.g., "Please tell me your current business hours"). Furthermore, the prompt is adjusted based on feedback from the emotion engine.

[0845] output

[0846] The generated prompt message (e.g., "What are your current business hours?")

[0847] Specific operation: The emotion engine analyzes the user's emotional state, and if it determines, for example, that the user is feeling stressed, it adjusts the prompt to something like, "Could you tell me your current business hours?"

[0848] Step 4: Response Generation

[0849] server

[0850] The server sends a generation prompt to a generative artificial intelligence model, which then generates a response.

[0851] input

[0852] The generated prompt message (e.g., "What are your current business hours?")

[0853] Data processing

[0854] The generation prompt is sent to the generative artificial intelligence model using a communication API.

[0855] output

[0856] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[0857] Specific operation: A generation prompt is sent to a generative artificial intelligence model using natural language processing techniques (e.g., GPT-3), and an appropriate response is generated.

[0858] Step 5: Emotional regulation of responses

[0859] Emotional Engine

[0860] The generated response is analyzed, and the content is modified to suit the user's emotions.

[0861] input

[0862] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[0863] Data processing

[0864] The emotion engine analyzes the user's emotional state and modifies the response text accordingly (e.g., "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience.").

[0865] output

[0866] Corrected response data

[0867] Specific action: When the emotion engine detects a user's stress level, it adds polite phrases such as "We apologize for any inconvenience this may cause" to the response.

[0868] Step 6: Displaying a response to the user

[0869] terminal

[0870] The terminal receives an emotion-adjusted response sent from the server and displays it to the user.

[0871] input

[0872] Corrected response data (Example: "Our business hours are from 9:00 AM to 6:00 PM on weekdays. We apologize for any inconvenience.")

[0873] Data processing

[0874] The data is converted for screen display, and then converted for audio output as needed.

[0875] output

[0876] Response information that the user receives visually or aurally

[0877] Specific operation: The device displays the response on the screen and plays it aloud. For example, it displays the response "Our current business hours are from 9 am to 6 pm on weekdays" on the screen and plays it aloud.

[0878] (Application Example 2)

[0879] 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."

[0880] Conventional user interface systems, when generating responses using generative artificial intelligence in response to standardized user input, lacked the ability to consider the user's emotional state, posing a challenge to improving the user experience. In particular, within autonomous vehicles, it is necessary to appropriately recognize the stress and excitement felt by passengers and provide corresponding responses to achieve a more comfortable riding experience.

[0881] 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 receiving an operation selected by the user from a set of standard inputs, means for generating a generation prompt based on the selected standard input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for analyzing the generated response with an emotion engine and modifying it according to the user's emotional state, and means for providing the user with an emotion-adjusted response. This makes it possible to provide a response that takes the user's emotional state into consideration, and in particular, it is possible to provide a comfortable and reassuring riding experience to passengers of autonomous vehicles.

[0882] "A means of accepting user selection from predefined inputs" refers to an interface that allows users to select their desired item from multiple options presented.

[0883] "Means for generating a generation prompt based on selected standard input" refers to a function that creates a specific prompt to send to a generative artificial intelligence based on the input content selected by the user.

[0884] "A means of sending a generation prompt to a generative artificial intelligence and causing it to generate a response" refers to a function that sends a generated prompt to a generative artificial intelligence and obtains a natural language response as its answer.

[0885] "A means of analyzing the generated response with an emotion engine and modifying it according to the user's emotional state" refers to a function that analyzes the response generated by a generative artificial intelligence with an emotion analysis engine and adapts the response content to the user's emotional state based on the analysis results.

[0886] "Means of providing emotionally regulated responses to users" refers to functions that communicate responses modified to match the user's emotional state to the user through means such as sight or hearing.

[0887] "A means of displaying multiple options that allow the user to select one of the predefined inputs" refers to a function that presents multiple choices on a display device that the user can select from, thereby enabling the user to make an appropriate choice.

[0888] "A means of analyzing a user's emotions using an emotion engine and suggesting appropriate options" refers to a function that analyzes the user's emotional state using an emotion analysis engine and presents the user with the most suitable options based on the results.

[0889] "Means of using a pre-saved template corresponding to selected standard input when sending a generation prompt to a generative artificial intelligence" refers to a function that generates a prompt using a pre-saved template based on the standard input selected by the user and sends it to the generative artificial intelligence.

[0890] "Means for adjusting prompts based on the user's emotional state" refers to a function that appropriately modifies the content of the generated prompts, taking into account the results of the user's emotion analysis.

[0891] System Configuration and Hardware

[0892] This invention is a system that receives standardized input from the user, generates a response using generative artificial intelligence, and further analyzes the user's emotions using an emotion engine to provide a response tailored to the user's emotional state. This system consists of the following main components.

[0893] 1. User interface devices (smart glasses, in-car displays, microphones, speakers, etc.)

[0894] 2. Server

[0895] 3. Generative artificial intelligence models

[0896] 4. Emotional Engine

[0897] software

[0898] The speech_recognition library is used to convert the user's speech into text.

[0899] The user's emotions are analyzed using the emotion analysis engine in the Hugging Face transformers library.

[0900] Access a generative artificial intelligence service using a RESTful API and generate a response.

[0901] Processing flow

[0902] The server will perform the following steps:

[0903] 1. Receiving user input:

[0904] The user interface terminal accepts user input by allowing selection from a set of predefined inputs. For user voice input, the speech_recognition library is used to convert the speech to text.

[0905] 2. Emotion analysis:

[0906] The acquired text data is sent to the emotion analysis engine in Hugging Face's transformers library to determine the user's emotional state.

[0907] 3. Prompt generation:

[0908] The system generates prompts based on predefined inputs selected by the user. For example, if the user selects that they want to go to the next tourist destination, the prompt "I would like to go to the next tourist destination." will be generated.

[0909] 4. Response generation:

[0910] The server sends the generated prompt to a generative artificial intelligence model, which then generates a response. An example of a generated response might be, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?"

[0911] 5. Emotional regulation:

[0912] The generated response is analyzed by an emotion engine, and the response content is modified according to the user's emotional state. For example, if the user is feeling stressed, the response might be modified to something like, "For your next sightseeing destination, there is a nearby tourist attraction called XX. We apologize for any inconvenience."

[0913] 6. Providing responses to users:

[0914] Emotionally tuned responses are provided on the user interface terminal, either through display or audio.

[0915] Specific example

[0916] For example, when used inside an autonomous vehicle, the following are possible prompt messages and responses:

[0917] User input: I want to go to the next tourist destination. Emotional state: positive

[0918] Examples of responses from generative artificial intelligence models:

[0919] As for your next sightseeing destination, there's a nearby tourist spot called XX. Why not visit it?

[0920] Examples of emotionally regulated responses:

[0921] For your next sightseeing destination, there is a nearby tourist attraction called [Name of tourist spot]. Have a wonderful time!

[0922] In this way, it becomes possible to respond in a way that takes into account the user's emotional state, and in particular, to provide a comfortable and reassuring riding experience for passengers in autonomous vehicles.

[0923] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0924] Step 1:

[0925] The system accepts user selections from a set of predefined input options. Using a user interface terminal (such as smart glasses, an in-car display, or a microphone), the user selects their desired item from multiple options presented. The terminal receives the input (voice or touch) and sends it to the server as text data.

[0926] Step 2:

[0927] The server receives the text data entered by the user and sends it to the sentiment analysis engine in the Hugging Face transformers library. This sentiment analysis engine analyzes the input text data and determines the user's emotional state (positive, negative, etc.). The output is returned as an emotion label and received by the server.

[0928] Step 3:

[0929] Based on the sentiment analysis results, the server creates a generated prompt corresponding to the user's selected standard input. This prompt is sent to the generative artificial intelligence system and converted into specific text, such as "I would like to go to the next tourist destination." The prompt is constructed based on pre-saved templates.

[0930] Step 4:

[0931] The server sends the generated prompt to the generative artificial intelligence (AI). The AI ​​analyzes the prompt and generates a corresponding natural language response. For example, it might generate a response like, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?" This response is then returned to the server.

[0932] Step 5:

[0933] The server sends the generated response back to the emotion engine, which then adjusts the response based on the user's emotional state. For example, if the user is stressed, the emotion engine might modify the response to something like, "For your next sightseeing destination, a nearby attraction is XX. We apologize for any inconvenience." The modified response is then returned to the server.

[0934] Step 6:

[0935] The server sends an emotion-adjusted response to the user interface terminal. The terminal then provides the modified response to the user via display and audio. This allows the user to receive a more appropriate response based on their emotional state.

[0936] 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.

[0937] 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.

[0938] 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.

[0939] [Third Embodiment]

[0940] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0941] 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.

[0942] 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).

[0943] 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.

[0944] 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.

[0945] 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).

[0946] 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.

[0947] 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.

[0948] 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.

[0949] 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.

[0950] 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.

[0951] 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".

[0952] System Configuration

[0953] The system of the present invention automates a series of processes, from receiving a standard input selected by the user to generating a response using generative artificial intelligence, and then providing that response to the user. This system includes the following main components:

[0954] 1. User Interface Terminal

[0955] 2. Server

[0956] 3. Generative artificial intelligence models

[0957] Program processing

[0958] Acceptance of user input

[0959] terminal

[0960] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. For example, options such as "Check opening hours," "Firm information," and "Inquire about product information" are available. Once the user makes a selection, that information is sent from the terminal to the server.

[0961] Submit your selections

[0962] terminal

[0963] The terminal sends the user's selected predefined input data to the server. This allows the server to prepare to begin the next process.

[0964] Prompt generation

[0965] server

[0966] The server generates a prompt based on the standardized input information it receives. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to the generative artificial intelligence.

[0967] Response generation

[0968] server

[0969] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, a response such as, "Our business hours are from 9 am to 6 pm on weekdays."

[0970] Displaying responses to the user

[0971] terminal

[0972] The terminal receives the response sent from the server and displays it to the user. By checking this result, the user can immediately obtain the necessary information.

[0973] Specific example

[0974] Examples of call centers

[0975] scenario

[0976] Consider a scenario where a user accesses a call center's automated response system to inquire about business hours. The process in this case is as follows:

[0977] 1. The user selects "Check business hours".

[0978] 2. The terminal sends the selected data to the server.

[0979] 3. The server generates a prompt that says, "Please tell me your current business hours."

[0980] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0981] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[0982] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0983] Example of a sign (in-house guide)

[0984] scenario

[0985] Let's consider a scenario where a user wants to find the location of the elevators using a terminal within the building. The process in this case is as follows:

[0986] 1. The user selects the "elevator location".

[0987] 2. The terminal sends the selected data to the server.

[0988] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[0989] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[0990] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[0991] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[0992] In this way, the system of the present invention can respond quickly and accurately to a wide range of inquiries from users. Furthermore, it can provide the latest information while minimizing maintenance work. High reliability is ensured by having humans handle final decisions and special cases.

[0993] The following describes the processing flow.

[0994] Step 1:

[0995] The user accesses a display terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed.

[0996] Step 2:

[0997] The terminal receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selections.

[0998] Step 3:

[0999] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, the server generates the prompt "Please tell me your current business hours."

[1000] Step 4:

[1001] The server sends a generation prompt to the generative artificial intelligence. The generative artificial intelligence generates a response in natural language based on the received prompt.

[1002] Step 5:

[1003] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it will generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[1004] Step 6:

[1005] The server receives the response generated by the generative artificial intelligence and sends that response to the terminal. This makes the response available to the user.

[1006] Step 7:

[1007] The terminal displays the response it receives from the server to the user. For example, it might display a message on the screen or via audio saying, "Our store hours are from 9:00 AM to 6:00 PM on weekdays."

[1008] Step 8:

[1009] The system confirms the user's response, whether displayed or spoken, and retrieves the necessary information.

[1010] (Example 1)

[1011] 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."

[1012] Currently, in many systems, the process of responding quickly and appropriately to user inquiries is complex and time-consuming. In particular, ensuring efficiency and accuracy in generating and displaying responses to routine inquiries is difficult. Traditional systems often require human intervention during the response generation process, leading to increased costs and slower response times. Furthermore, the lack of adequate means to consistently provide up-to-date information results in decreased user satisfaction.

[1013] 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.

[1014] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for processing the selected predefined inputs and sending them to the server, means for generating a generation prompt based on the predefined inputs received by the server, means for sending the generation prompt to a generative artificial intelligence system to generate a natural language response, and means for providing the generated natural language response to the user. This makes it possible to always provide the latest information quickly and accurately in response to user inquiries. Furthermore, the overall efficiency and automation of the system are improved, and human intervention in the response generation process is minimized.

[1015] A "user" is an individual or group that operates the system and selects predefined input options.

[1016] "Standard input" refers to pre-configured inquiry content or operation options that users select.

[1017] A "server" is a computing system that receives standardized user input, generates prompts, sends them to generative artificial intelligence, and processes responses.

[1018] A "terminal" is an interface device operated by a user, which sends user input to a server and displays the server's response.

[1019] A "generated prompt" is a set of instructions created by a server based on a user's standardized input, and serves as input data for generating a response from a generative artificial intelligence.

[1020] "Generative artificial intelligence" refers to machine learning algorithms and models that receive a generative prompt and generate a natural language response based on it.

[1021] A "natural language response" is a response sentence in a language format that is easy for humans to understand, which is output by a generative artificial intelligence system based on a generation prompt.

[1022] This invention automates a series of processes, from receiving predefined inputs selected by the user to generating responses using generative artificial intelligence, and then providing those responses to the user. The embodiments for carrying out this invention are described in detail below.

[1023] System Configuration

[1024] The system of the present invention includes the following main components.

[1025] 1. User interface terminals: For example, mobile devices such as iPads and Android tablets are used.

[1026] 2. Servers: Cloud-based servers such as AWS EC2 and Google Cloud Compute Engine will be used.

[1027] 3. Generative artificial intelligence models: Natural language processing models such as OpenAI GPT-4 and Google BERT are used.

[1028] Selection at the user interface terminal

[1029] The user selects their desired option from several choices displayed on the terminal they are using. For example, options such as "Check opening hours," "Firm information guide," and "Inquire about product information" may be displayed. Once the user makes a selection, that information is sent from the terminal to the server.

[1030] Prompt generation on the server

[1031] The server generates appropriate prompts based on the standardized input information received from the user. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to a generative artificial intelligence model.

[1032] Response generation in generative artificial intelligence models

[1033] A generative artificial intelligence model generates a natural language response based on a prompt received from the server. For example, a response such as "Our store hours are from 9 am to 6 pm on weekdays" is generated. This response is then sent back to the server.

[1034] Sending and displaying responses to the user interface terminal

[1035] The server sends the generated response to the terminal, which then displays the response to the user. By checking the response displayed on the terminal's screen, the user can instantly obtain the necessary information.

[1036] Specific example

[1037] Examples of call centers

[1038] Here's a concrete example of the procedure a user would follow if they accessed a call center's automated response system to inquire about business hours.

[1039] 1. The user selects "Check business hours".

[1040] 2. The terminal sends the selected data to the server.

[1041] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1042] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[1043] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1044] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[1045] Example of a sign (in-house guide)

[1046] Here's a concrete example of how a user can find out the location of the elevators using a terminal within the building.

[1047] 1. The user selects the "elevator location".

[1048] 2. The terminal sends the selected data to the server.

[1049] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1050] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[1051] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1052] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[1053] Specific examples of prompt phrases include, "What are your current business hours?" and "Where is the elevator?"

[1054] As described above, the system of the present invention is capable of responding quickly and accurately to a wide range of inquiries from users. The overall efficiency and automation of the system are improved, and it becomes possible to always provide the latest information.

[1055] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1056] Step 1:

[1057] The user makes a selection for a predefined input. The user interface terminal displays multiple options to the user. For example, options may include "Check opening hours," "Get directions within the building," and "Inquire about product information." The user makes a selection by tapping or clicking. The input is the user's selection, and the output is the data of the selected option.

[1058] Step 2:

[1059] The device sends the user's selections to the server. Specifically, the device sends the data of the selected options to the server as an HTTP request. This data is in JSON format and is passed to the server in a format such as { "query": "Check business hours"}. The input is the user's selection data, and the output is the selection data sent to the server.

[1060] Step 3:

[1061] The server parses the selected data it receives and generates an appropriate prompt. Specifically, the server extracts the "query" field from the received data and generates a corresponding prompt. For example, if the received data is { "query": "Check business hours"}, it will generate the prompt "Please tell me your current business hours". The input is the selected boilerplate data, and the output is the generated prompt.

[1062] Step 4:

[1063] The server sends a generated prompt to the generative artificial intelligence (AI). Specifically, it sends the generated prompt text as an API request to the generative AI model. The generative AI receives this prompt and generates a response. For example, in response to the prompt "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays." The input is the generated prompt text, and the output is a natural language response from the generative AI model.

[1064] Step 5:

[1065] The server sends the generated response to the terminal. Specifically, the server converts the received natural language response back into JSON format and sends it to the terminal as an HTTP response. For example, if the generated response is "Our business hours are from 9 am to 6 pm on weekdays," it will be sent to the terminal in the format { "response": "Our business hours are from 9 am to 6 pm on weekdays"}. The input is the response sentence from the generative artificial intelligence model, and the output is the response data sent to the terminal.

[1066] Step 6:

[1067] The terminal receives a response from the server and displays it to the user. Specifically, the terminal parses the received data and displays it on the screen. Through this screen, the user can confirm a response such as, "Our store hours are from 9 am to 6 pm on weekdays." The input is the response data from the server, and the output is the natural language response displayed on the screen.

[1068] (Application Example 1)

[1069] 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."

[1070] In recent years, there has been a growing demand for information provision systems utilizing smart devices to improve customer convenience in physical stores. However, conventional systems have challenges in responding immediately to customer needs and providing efficient guidance and product information. Furthermore, conventional systems often rely on human intervention, resulting in high operational costs and maintenance burdens. Therefore, there is a need for the development of automated systems that can provide customers with the information they need quickly and accurately.

[1071] 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.

[1072] In this invention, the server includes means for receiving an operation selected by the user from a set of predefined inputs, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for providing the generated response to the user, and means for providing an application installed on a smart device to provide information relevant to the user. This makes it possible to provide the information the user needs quickly and accurately, and to significantly improve customer convenience in physical stores.

[1073] A "user" is a customer who uses a system to obtain information.

[1074] "Standard input" refers to input options provided to the user as predetermined choices.

[1075] A "generated prompt" is an input sentence for a generative artificial intelligence system that is constructed based on a predefined input selected by the user.

[1076] "Generative artificial intelligence" refers to an artificial intelligence system that generates responses in natural language based on input prompts.

[1077] "Response" refers to the reply generated by generative artificial intelligence to a user's inquiry.

[1078] "Means of providing to the user" refers to the interface or method for displaying the generated response to the user.

[1079] A "smart device" refers to a portable device with internet connectivity, such as a smartphone or tablet.

[1080] An "application" is a software program that runs on a smart device and provides information to the user.

[1081] System Configuration

[1082] This invention is an information provision system designed to improve customer convenience in physical stores. The system mainly consists of three main components: a user terminal, a server, and a generative artificial intelligence model.

[1083] 1. User terminal

[1084] The user terminal refers to a smart device such as a smartphone or tablet. This terminal presents pre-defined input options and provides an interface for the user to select the information they need.

[1085] 2. Server

[1086] The server receives standardized input data sent from the user terminal and creates a generation prompt. It then sends this generation prompt to a generative artificial intelligence model and sends the generated response back to the user terminal.

[1087] 3. Generative artificial intelligence models

[1088] Generative artificial intelligence models generate natural language responses based on input prompts. Specifically, high-performance generative AI modeling technologies such as OpenAI's GPT-3 are used.

[1089] Program processing and the hardware and software used

[1090] User terminal

[1091] The user terminal accepts pre-defined inputs from the user through the user interface. For example, options such as "Facility Guide," "Product Information Inquiry," and "Promotion Information" are displayed. When the user selects a pre-defined input, this information is sent to the server.

[1092] server

[1093] The server receives predefined inputs sent from the user's terminal. After receiving them, the server generates a prompt based on the selected predefined input. For example, if the predefined input is "building information," the server generates the prompt "I would like building information." This prompt is sent to a generative artificial intelligence model, which generates a response in natural language.

[1094] Generative artificial intelligence models

[1095] The OpenAI GPT-3 is used as the generative artificial intelligence model. GPT-3 analyzes the sent prompt and generates an appropriate response. For example, it provides specific guidance information such as, "The elevator is located at the back right of the entrance hall."

[1096] Display of response to user terminal

[1097] The generated response is sent back to the user terminal via the server. The user terminal displays the generated response on its user interface, allowing the user to immediately obtain the necessary information.

[1098] Examples of specific cases and prompt statements

[1099] Specific example

[1100] Let's consider a scenario where a user uses their smartphone to obtain information within a physical store. For example, if the user selects "Store Guide," the system will operate as follows:

[1101] 1. The user opens the smartphone app and selects "In-house Guide".

[1102] 2. The app sends a request for "building information" to the server.

[1103] 3. The server generates a prompt saying "I would like a tour of the building" and sends it to the generative artificial intelligence.

[1104] 4. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1105] 5. The server sends the generated response to the user's terminal.

[1106] 6. A response is displayed on the user's smartphone.

[1107] Example of a prompt

[1108] Prompt: "I'd like a tour of the building."

[1109] Response: "The elevator is located at the back right of the entrance hall."

[1110] In this way, the invention can quickly and accurately provide users with a variety of information they need within a physical store.

[1111] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1112] Step 1:

[1113] The user opens an application on their smart device.

[1114] Input: Smart device operation

[1115] Operation: The user launches the application on their smart device and accesses an interface that displays pre-set input options.

[1116] Output: The predefined input options are displayed in the user interface.

[1117] Step 2:

[1118] The user selects "In-house information" from the pre-defined input options.

[1119] Input: User selection operation

[1120] Operation: Select "Building Guide" from the user interface, and the application will recognize this selection.

[1121] Output: Selected standard input data

[1122] Step 3:

[1123] The terminal sends the selected standard input data to the server.

[1124] Input: Standard input data

[1125] Operation: The terminal sends the selected predefined input data to the server as an HTTP request.

[1126] Output: Standard input data received by the server

[1127] Step 4:

[1128] The server generates a prompt based on predefined input.

[1129] Input: Standard input data

[1130] Operation: The server parses the received standardized input data and selects a corresponding generated prompt from a template. In this example, the prompt "I would like a tour of the building" is generated.

[1131] Output: Generated prompt("I'd like a tour of the building")

[1132] Step 5:

[1133] The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[1134] Input: Generate prompt

[1135] Operation: The server sends a generated prompt to the OpenAI GPT-3 API. GPT-3 parses the prompt and generates an appropriate response.

[1136] Output: Generated response (e.g., "The elevator is located at the back right of the entrance hall.")

[1137] Step 6:

[1138] The server sends the generated response to the user's terminal.

[1139] Input: Generated response

[1140] Operation: The server sends the generated response to the user's terminal as an HTTP response.

[1141] Output: Response data received by the user terminal

[1142] Step 7:

[1143] The terminal displays the response it has received to the user.

[1144] Input: Received response data

[1145] Operation: The response data received by the user terminal is displayed on the user interface. The user confirms the information, "The elevator is located at the back right of the entrance hall."

[1146] Output: Response data displayed on the user interface

[1147] This processing step allows users to efficiently obtain information within the physical store, improving convenience.

[1148] 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.

[1149] System Configuration

[1150] In addition to its basic function of receiving standardized input from the user and generating a response using generative artificial intelligence, the system of the present invention improves the quality of the response by incorporating an emotion engine that recognizes and analyzes the user's emotions. This system includes the following main components.

[1151] 1. User Interface Terminal

[1152] 2. Server

[1153] 3. Generative artificial intelligence models

[1154] 4. Emotional Engine

[1155] Program processing

[1156] Acceptance of user input

[1157] terminal

[1158] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. Examples of choices include "check opening hours," "get directions," and "inquire about product information." When presenting these choices, the terminal can use an emotion engine to analyze the user's emotions and suggest appropriate options.

[1159] Submit your selections

[1160] terminal

[1161] The system receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selection and initiate the process of generating a corresponding response.

[1162] Prompt generation

[1163] server

[1164] The server generates prompts based on the standardized input information it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it incorporates feedback from the emotion engine to adjust the prompts to match the user's emotions.

[1165] Response generation

[1166] server

[1167] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, in response to "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[1168] Emotional regulation of responses

[1169] Emotional Engine

[1170] Once the generated response is returned to the server, the emotion engine analyzes it and modifies it to suit the user's current emotions. For example, if the user is stressed, the response is changed to be more polite and kind.

[1171] Displaying responses to the user

[1172] terminal

[1173] The terminal receives the response sent from the server and displays it to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our store hours are from 9 am to 6 pm on weekdays. Is there anything else we can help you with?"

[1174] Specific example

[1175] Examples of call centers

[1176] scenario

[1177] Consider a scenario where a user accesses an automated call center system to inquire about business hours. If the emotion engine determines that the user is experiencing stress, the process would proceed as follows:

[1178] 1. The user selects "Check business hours".

[1179] 2. The terminal sends the selected data to the server.

[1180] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1181] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[1182] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1183] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[1184] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1185] Example of a sign (in-house guide)

[1186] scenario

[1187] Let's consider a scenario where a user wants to know the location of the elevator using a terminal for building information. If the emotion engine determines that the user is in an excited state, the process would proceed as follows:

[1188] 1. The user selects the "elevator location".

[1189] 2. The terminal sends the selected data to the server.

[1190] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1191] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[1192] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1193] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[1194] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1195] In this way, the system of the present invention can respond quickly and accurately to a variety of inquiries from users, and can also provide responses that are tailored to the user's emotions. This makes it possible to achieve higher user satisfaction.

[1196] The following describes the processing flow.

[1197] Step 1:

[1198] The user accesses a guidance terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed. During this process, the user's emotions are analyzed by an emotion engine.

[1199] Step 2:

[1200] The terminal sends the user's selected standard input data and the emotion data analyzed by the emotion engine to the server. This allows the server to recognize the user's selections and emotions.

[1201] Step 3:

[1202] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, it generates the prompt "Please tell me your current business hours."

[1203] Step 4:

[1204] The server processes the generated prompts using an emotion engine, adjusting them to match the user's emotions. For example, if the user is already stressed, the prompt might be changed to a gentler tone, such as, "Excuse me, but could you please tell me your current business hours?"

[1205] Step 5:

[1206] The server sends a pre-configured generation prompt to the generative AI, which then generates a response. The generative AI then generates a response in natural language based on the received prompt.

[1207] Step 6:

[1208] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it generates the response "Our business hours are from 9 am to 6 pm on weekdays."

[1209] Step 7:

[1210] The server receives a response generated by a generative artificial intelligence, analyzes that response again using an emotion engine, and modifies the content to suit the user's emotions. For example, if the user is feeling stressed, it might respond politely with, "Our business hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience. Do you have any further questions?"

[1211] Step 8:

[1212] The server sends an emotionally regulated response to the terminal.

[1213] Step 9:

[1214] The terminal displays the response it receives from the server to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our business hours are weekdays from 9 am to 6 pm. We apologize for any inconvenience. Do you have any further questions?"

[1215] Step 10:

[1216] The system reviews the user's responses, whether displayed or voiced, and obtains the necessary information. This cycle is repeated if the user makes further inquiries.

[1217] (Example 2)

[1218] 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."

[1219] Traditional dialogue systems tend to have low user satisfaction because they generate responses without considering the user's emotional state. Furthermore, users don't always choose the optimal option, resulting in inappropriate responses. This can lead to user stress and inconvenience, which is a significant problem.

[1220] 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.

[1221] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for transmitting the selected predefined input, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence system to generate a response, means for adjusting the generated response to match the user's emotions, and means for providing the adjusted response to the user. This makes it possible to provide a response that is adapted to the user's emotional state, thereby improving user satisfaction.

[1222] 1. A "user" is an entity that uses a system to make selections from predefined inputs and receives a response.

[1223] 2. "Standard input" refers to a predetermined input format or item that the user can select.

[1224] 3. "Means for accepting selection operations" refers to a function that provides an interface for users to select the appropriate option from a set of predefined inputs.

[1225] 4. "Means for sending selected predefined inputs" refers to a communication function for sending user-selected content to the server.

[1226] 5. A "generated prompt" is a sentence in the form of a question or instruction that is generated based on selected predefined input.

[1227] 6. "Means for generating generation prompts" refers to a function that generates appropriate questions or instructions based on the received standard input.

[1228] 7. "Generative artificial intelligence" refers to an artificial intelligence model that receives a generative prompt as input and generates a natural language response based on it.

[1229] 8. "Means for sending a generation prompt to a generative artificial intelligence" refers to a communication function that sends a generation prompt to a generative artificial intelligence and causes it to generate a response.

[1230] 9. "Means for generating a response" refers to the function of a generative artificial intelligence that receives a generation prompt and generates a natural language response based on it.

[1231] 10. "Means for adjusting generated responses to match the user's emotions" refers to a function that modifies generated responses using an emotion engine to match the user's current emotional state.

[1232] 11. “Means of providing an adapted response to the user” means a function that provides the user with an emotionally adapted response, either visually or aurally.

[1233] System Configuration

[1234] The system of the present invention includes a terminal that accepts an operation for a user to select from a set of predefined inputs, a server that transmits the selected predefined input, a server that generates a generation prompt based on the selected predefined input, a server that transmits the generation prompt to a generative artificial intelligence model and causes it to generate a response, an emotion engine that adjusts the generated response to match the user's emotions, and a terminal that provides the adjusted response to the user.

[1235] Hardware and software

[1236] The hardware used in this system includes terminals that provide the user interface (such as PCs, tablets, and smartphones), servers that process data, and cameras and microphones that collect user emotion data. The software includes generative artificial intelligence models (such as GPT-3), emotion engines (emotion analysis software), communication APIs, and applications for the user interface.

[1237] Acceptance of user input

[1238] terminal

[1239] The user clicks on pre-defined input options on the device screen. These options include, for example, "Check opening hours," "Get directions," and "Inquire about product information." The device transmits the user's facial expressions and voice via the camera and microphone to an emotion engine, which analyzes the user's emotions. Based on this analysis, it can also present the user with the most suitable options.

[1240] Submit your selections

[1241] terminal

[1242] The user's selected input data is sent to the server. This data is sent via a dedicated communication API, and its contents are recorded on the server.

[1243] Prompt generation

[1244] server

[1245] The server generates prompts based on the selected data it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it adjusts the prompt based on the user's emotions, taking into account feedback from the emotion engine. If the emotion engine determines that the user is stressed, the prompt becomes more polite, such as "Could you please tell me your current opening hours?"

[1246] Response generation

[1247] server

[1248] The server sends a generation prompt to a generative artificial intelligence model (e.g., GPT-3) to generate a response. Based on the received prompt, the generative AI model generates an appropriate natural language response. This ensures that the user receives an accurate and appropriate response to the question they selected.

[1249] Emotional regulation of responses

[1250] Emotional Engine

[1251] Once the generated response is returned to the server, the emotion engine analyzes the response and modifies it to suit the user's emotions. For example, if the user is feeling stressed by the generated response, "Our store hours are from 9 am to 6 pm on weekdays," the engine will modify it to, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[1252] Displaying responses to the user

[1253] terminal

[1254] The terminal receives an emotionally tuned response sent from the server and displays it to the user. The terminal not only displays the response on the screen but also plays it aloud as needed. For example, it can display the response "Our current business hours are weekdays from 9 am to 6 pm" on the screen and play it aloud simultaneously.

[1255] Specific example

[1256] Examples of call centers

[1257] Here's a specific example of a user accessing a call center's automated response system to inquire about business hours. The following is the process if the emotion engine determines the user is experiencing stress.

[1258] 1. The user selects "Check business hours".

[1259] 2. The terminal sends the selected data to the server.

[1260] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1261] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[1262] 5. The generative artificial intelligence model generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1263] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[1264] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1265] Examples of signs

[1266] Here's a concrete example of a user wanting to know the location of the elevators using a terminal for building information. The process when the emotion engine determines that the user is in an excited state is as follows:

[1267] 1. The user selects the "elevator location".

[1268] 2. The terminal sends the selected data to the server.

[1269] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1270] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[1271] 5. The generative artificial intelligence model generates the response, "The elevator is located in the back right of the entrance hall."

[1272] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[1273] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1274] This system makes it possible to provide appropriate responses that are adapted to the user's emotions, and is expected to improve user satisfaction.

[1275] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1276] Step 1: Receiving user input

[1277] terminal

[1278] The user clicks on a pre-defined input option on the device screen. Examples of options include "Check opening hours," "Store information," and "Inquire about product information."

[1279] input

[1280] Items selected by the user (e.g., "Check business hours")

[1281] Data processing

[1282] The selected items are retrieved as data and converted to a format corresponding to the next processing step.

[1283] output

[1284] Selected item data (e.g., "Check business hours")

[1285] Specific operation: The device collects the user's facial expressions and voice through the camera and microphone, sends them to the emotion engine, and analyzes the user's emotions. Based on the analysis results, it presents the user with the most suitable options.

[1286] Step 2: Submit your selections

[1287] terminal

[1288] The input data selected by the user is sent to the server.

[1289] input

[1290] Selected item data (e.g., "Check business hours")

[1291] Data processing

[1292] Convert the selected item data into an HTTP request format.

[1293] output

[1294] HTTP request data sent to the server

[1295] Specific operation: Selected item data is sent to the server using a dedicated communication API. The server receives the request and records it in the database.

[1296] Step 3: Generate prompt

[1297] server

[1298] The server creates a generation prompt based on the selected data it receives.

[1299] input

[1300] Selection data sent via HTTP request (e.g., "Check business hours")

[1301] Data processing

[1302] Based on the selected data received, an appropriate prompt is generated (e.g., "Please tell me your current business hours"). Furthermore, the prompt is adjusted based on feedback from the emotion engine.

[1303] output

[1304] The generated prompt message (e.g., "What are your current business hours?")

[1305] Specific operation: The emotion engine analyzes the user's emotional state, and if it determines, for example, that the user is feeling stressed, it adjusts the prompt to something like, "Could you tell me your current business hours?"

[1306] Step 4: Response Generation

[1307] server

[1308] The server sends a generation prompt to a generative artificial intelligence model, which then generates a response.

[1309] input

[1310] The generated prompt message (e.g., "What are your current business hours?")

[1311] Data processing

[1312] The generation prompt is sent to the generative artificial intelligence model using a communication API.

[1313] output

[1314] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[1315] Specific operation: A generation prompt is sent to a generative artificial intelligence model using natural language processing techniques (e.g., GPT-3), and an appropriate response is generated.

[1316] Step 5: Emotional regulation of responses

[1317] Emotional Engine

[1318] The generated response is analyzed, and the content is modified to suit the user's emotions.

[1319] input

[1320] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[1321] Data processing

[1322] The emotion engine analyzes the user's emotional state and modifies the response text accordingly (e.g., "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience.").

[1323] output

[1324] Corrected response data

[1325] Specific action: When the emotion engine detects a user's stress level, it adds polite phrases such as "We apologize for any inconvenience this may cause" to the response.

[1326] Step 6: Displaying a response to the user

[1327] terminal

[1328] The terminal receives an emotion-adjusted response sent from the server and displays it to the user.

[1329] input

[1330] Corrected response data (Example: "Our business hours are from 9:00 AM to 6:00 PM on weekdays. We apologize for any inconvenience.")

[1331] Data processing

[1332] The data is converted for screen display, and then converted for audio output as needed.

[1333] output

[1334] Response information that the user receives visually or aurally

[1335] Specific operation: The device displays the response on the screen and plays it aloud. For example, it displays the response "Our current business hours are from 9 am to 6 pm on weekdays" on the screen and plays it aloud.

[1336] (Application Example 2)

[1337] 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."

[1338] Conventional user interface systems, when generating responses using generative artificial intelligence in response to standardized user input, lacked the ability to consider the user's emotional state, posing a challenge to improving the user experience. In particular, within autonomous vehicles, it is necessary to appropriately recognize the stress and excitement felt by passengers and provide corresponding responses to achieve a more comfortable riding experience.

[1339] 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 receiving an operation selected by the user from a set of standard inputs, means for generating a generation prompt based on the selected standard input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for analyzing the generated response with an emotion engine and modifying it according to the user's emotional state, and means for providing the user with an emotion-adjusted response. This makes it possible to provide a response that takes the user's emotional state into consideration, and in particular, it is possible to provide a comfortable and reassuring riding experience to passengers of autonomous vehicles.

[1340] "A means of accepting user selection from predefined inputs" refers to an interface that allows users to select their desired item from multiple options presented.

[1341] "Means for generating a generation prompt based on selected standard input" refers to a function that creates a specific prompt to send to a generative artificial intelligence based on the input content selected by the user.

[1342] "A means of sending a generation prompt to a generative artificial intelligence and causing it to generate a response" refers to a function that sends a generated prompt to a generative artificial intelligence and obtains a natural language response as its answer.

[1343] "A means of analyzing the generated response with an emotion engine and modifying it according to the user's emotional state" refers to a function that analyzes the response generated by a generative artificial intelligence with an emotion analysis engine and adapts the response content to the user's emotional state based on the analysis results.

[1344] "Means of providing emotionally regulated responses to users" refers to functions that communicate responses modified to match the user's emotional state to the user through means such as sight or hearing.

[1345] "A means of displaying multiple options that allow the user to select one of the predefined inputs" refers to a function that presents multiple choices on a display device that the user can select from, thereby enabling the user to make an appropriate choice.

[1346] "A means of analyzing a user's emotions using an emotion engine and suggesting appropriate options" refers to a function that analyzes the user's emotional state using an emotion analysis engine and presents the user with the most suitable options based on the results.

[1347] "Means of using a pre-saved template corresponding to selected standard input when sending a generation prompt to a generative artificial intelligence" refers to a function that generates a prompt using a pre-saved template based on the standard input selected by the user and sends it to the generative artificial intelligence.

[1348] "Means for adjusting prompts based on the user's emotional state" refers to a function that appropriately modifies the content of the generated prompts, taking into account the results of the user's emotion analysis.

[1349] System Configuration and Hardware

[1350] This invention is a system that receives standardized input from the user, generates a response using generative artificial intelligence, and further analyzes the user's emotions using an emotion engine to provide a response tailored to the user's emotional state. This system consists of the following main components.

[1351] 1. User interface devices (smart glasses, in-car displays, microphones, speakers, etc.)

[1352] 2. Server

[1353] 3. Generative artificial intelligence models

[1354] 4. Emotional Engine

[1355] software

[1356] The speech_recognition library is used to convert the user's speech into text.

[1357] The user's emotions are analyzed using the emotion analysis engine in the Hugging Face transformers library.

[1358] Access a generative artificial intelligence service using a RESTful API and generate a response.

[1359] Processing flow

[1360] The server will perform the following steps:

[1361] 1. Receiving user input:

[1362] The user interface terminal accepts user input by allowing selection from a set of predefined inputs. For user voice input, the speech_recognition library is used to convert the speech to text.

[1363] 2. Emotion analysis:

[1364] The acquired text data is sent to the emotion analysis engine in Hugging Face's transformers library to determine the user's emotional state.

[1365] 3. Prompt generation:

[1366] The system generates prompts based on predefined inputs selected by the user. For example, if the user selects that they want to go to the next tourist destination, the prompt "I would like to go to the next tourist destination." will be generated.

[1367] 4. Response generation:

[1368] The server sends the generated prompt to a generative artificial intelligence model, which then generates a response. An example of a generated response might be, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?"

[1369] 5. Emotional regulation:

[1370] The generated response is analyzed by an emotion engine, and the response content is modified according to the user's emotional state. For example, if the user is feeling stressed, the response might be modified to something like, "For your next sightseeing destination, there is a nearby tourist attraction called XX. We apologize for any inconvenience."

[1371] 6. Providing responses to users:

[1372] Emotionally tuned responses are provided on the user interface terminal, either through display or audio.

[1373] Specific example

[1374] For example, when used inside an autonomous vehicle, the following are possible prompt messages and responses:

[1375] User input: I want to go to the next tourist destination. Emotional state: positive

[1376] Examples of responses from generative artificial intelligence models:

[1377] As for your next sightseeing destination, there's a nearby tourist spot called XX. Why not visit it?

[1378] Examples of emotionally regulated responses:

[1379] For your next sightseeing destination, there is a nearby tourist attraction called [Name of tourist spot]. Have a wonderful time!

[1380] In this way, it becomes possible to respond in a way that takes into account the user's emotional state, and in particular, to provide a comfortable and reassuring riding experience for passengers in autonomous vehicles.

[1381] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1382] Step 1:

[1383] The system accepts user selections from a set of predefined input options. Using a user interface terminal (such as smart glasses, an in-car display, or a microphone), the user selects their desired item from multiple options presented. The terminal receives the input (voice or touch) and sends it to the server as text data.

[1384] Step 2:

[1385] The server receives the text data entered by the user and sends it to the sentiment analysis engine in the Hugging Face transformers library. This sentiment analysis engine analyzes the input text data and determines the user's emotional state (positive, negative, etc.). The output is returned as an emotion label and received by the server.

[1386] Step 3:

[1387] Based on the sentiment analysis results, the server creates a generated prompt corresponding to the user's selected standard input. This prompt is sent to the generative artificial intelligence system and converted into specific text, such as "I would like to go to the next tourist destination." The prompt is constructed based on pre-saved templates.

[1388] Step 4:

[1389] The server sends the generated prompt to the generative artificial intelligence (AI). The AI ​​analyzes the prompt and generates a corresponding natural language response. For example, it might generate a response like, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?" This response is then returned to the server.

[1390] Step 5:

[1391] The server sends the generated response back to the emotion engine, which then adjusts the response based on the user's emotional state. For example, if the user is stressed, the emotion engine might modify the response to something like, "For your next sightseeing destination, a nearby attraction is XX. We apologize for any inconvenience." The modified response is then returned to the server.

[1392] Step 6:

[1393] The server sends an emotion-adjusted response to the user interface terminal. The terminal then provides the modified response to the user via display and audio. This allows the user to receive a more appropriate response based on their emotional state.

[1394] 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.

[1395] 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.

[1396] 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.

[1397] [Fourth Embodiment]

[1398] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1399] 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.

[1400] 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).

[1401] 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.

[1402] 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.

[1403] 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).

[1404] 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.

[1405] 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.

[1406] 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.

[1407] 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.

[1408] 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.

[1409] 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.

[1410] 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".

[1411] System Configuration

[1412] The system of the present invention automates a series of processes, from receiving a standard input selected by the user to generating a response using generative artificial intelligence, and then providing that response to the user. This system includes the following main components:

[1413] 1. User Interface Terminal

[1414] 2. Server

[1415] 3. Generative artificial intelligence models

[1416] Program processing

[1417] Acceptance of user input

[1418] terminal

[1419] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. For example, options such as "Check opening hours," "Firm information," and "Inquire about product information" are available. Once the user makes a selection, that information is sent from the terminal to the server.

[1420] Submit your selections

[1421] terminal

[1422] The terminal sends the user's selected predefined input data to the server. This allows the server to prepare to begin the next process.

[1423] Prompt generation

[1424] server

[1425] The server generates a prompt based on the standardized input information it receives. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to the generative artificial intelligence.

[1426] Response generation

[1427] server

[1428] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, a response such as, "Our business hours are from 9 am to 6 pm on weekdays."

[1429] Displaying responses to the user

[1430] terminal

[1431] The terminal receives the response sent from the server and displays it to the user. By checking this result, the user can immediately obtain the necessary information.

[1432] Specific example

[1433] Examples of call centers

[1434] scenario

[1435] Consider a scenario where a user accesses a call center's automated response system to inquire about business hours. The process in this case is as follows:

[1436] 1. The user selects "Check business hours".

[1437] 2. The terminal sends the selected data to the server.

[1438] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1439] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[1440] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1441] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[1442] Example of a sign (in-house guide)

[1443] scenario

[1444] Let's consider a scenario where a user wants to find the location of the elevators using a terminal within the building. The process in this case is as follows:

[1445] 1. The user selects the "elevator location".

[1446] 2. The terminal sends the selected data to the server.

[1447] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1448] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[1449] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1450] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[1451] In this way, the system of the present invention can respond quickly and accurately to a wide range of inquiries from users. Furthermore, it can provide the latest information while minimizing maintenance work. High reliability is ensured by having humans handle final decisions and special cases.

[1452] The following describes the processing flow.

[1453] Step 1:

[1454] The user accesses a display terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed.

[1455] Step 2:

[1456] The terminal receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selections.

[1457] Step 3:

[1458] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, the server generates the prompt "Please tell me your current business hours."

[1459] Step 4:

[1460] The server sends a generation prompt to the generative artificial intelligence. The generative artificial intelligence generates a response in natural language based on the received prompt.

[1461] Step 5:

[1462] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it will generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[1463] Step 6:

[1464] The server receives the response generated by the generative artificial intelligence and sends that response to the terminal. This makes the response available to the user.

[1465] Step 7:

[1466] The terminal displays the response it receives from the server to the user. For example, it might display a message on the screen or via audio saying, "Our store hours are from 9:00 AM to 6:00 PM on weekdays."

[1467] Step 8:

[1468] The system confirms the user's response, whether displayed or spoken, and retrieves the necessary information.

[1469] (Example 1)

[1470] 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".

[1471] Currently, in many systems, the process of responding quickly and appropriately to user inquiries is complex and time-consuming. In particular, ensuring efficiency and accuracy in generating and displaying responses to routine inquiries is difficult. Traditional systems often require human intervention during the response generation process, leading to increased costs and slower response times. Furthermore, the lack of adequate means to consistently provide up-to-date information results in decreased user satisfaction.

[1472] 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.

[1473] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for processing the selected predefined inputs and sending them to the server, means for generating a generation prompt based on the predefined inputs received by the server, means for sending the generation prompt to a generative artificial intelligence system to generate a natural language response, and means for providing the generated natural language response to the user. This makes it possible to always provide the latest information quickly and accurately in response to user inquiries. Furthermore, the overall efficiency and automation of the system are improved, and human intervention in the response generation process is minimized.

[1474] A "user" is an individual or group that operates the system and selects predefined input options.

[1475] "Standard input" refers to pre-configured inquiry content or operation options that users select.

[1476] A "server" is a computing system that receives standardized user input, generates prompts, sends them to generative artificial intelligence, and processes responses.

[1477] A "terminal" is an interface device operated by a user, which sends user input to a server and displays the server's response.

[1478] A "generated prompt" is a set of instructions created by a server based on a user's standardized input, and serves as input data for generating a response from a generative artificial intelligence.

[1479] "Generative artificial intelligence" refers to machine learning algorithms and models that receive a generative prompt and generate a natural language response based on it.

[1480] A "natural language response" is a response sentence in a language format that is easy for humans to understand, which is output by a generative artificial intelligence system based on a generation prompt.

[1481] This invention automates a series of processes, from receiving predefined inputs selected by the user to generating responses using generative artificial intelligence, and then providing those responses to the user. The embodiments for carrying out this invention are described in detail below.

[1482] System Configuration

[1483] The system of the present invention includes the following main components.

[1484] 1. User interface terminals: For example, mobile devices such as iPads and Android tablets are used.

[1485] 2. Servers: Cloud-based servers such as AWS EC2 and Google Cloud Compute Engine will be used.

[1486] 3. Generative artificial intelligence models: Natural language processing models such as OpenAI GPT-4 and Google BERT are used.

[1487] Selection at the user interface terminal

[1488] The user selects their desired option from several choices displayed on the terminal they are using. For example, options such as "Check opening hours," "Firm information guide," and "Inquire about product information" may be displayed. Once the user makes a selection, that information is sent from the terminal to the server.

[1489] Prompt generation on the server

[1490] The server generates appropriate prompts based on the standardized input information received from the user. For example, if the user selects "Check business hours," the server generates the prompt "Please tell me the current business hours." This prompt is then sent to a generative artificial intelligence model.

[1491] Response generation in generative artificial intelligence models

[1492] A generative artificial intelligence model generates a natural language response based on a prompt received from the server. For example, a response such as "Our store hours are from 9 am to 6 pm on weekdays" is generated. This response is then sent back to the server.

[1493] Sending and displaying responses to the user interface terminal

[1494] The server sends the generated response to the terminal, which then displays the response to the user. By checking the response displayed on the terminal's screen, the user can instantly obtain the necessary information.

[1495] Specific example

[1496] Examples of call centers

[1497] Here's a concrete example of the procedure a user would follow if they accessed a call center's automated response system to inquire about business hours.

[1498] 1. The user selects "Check business hours".

[1499] 2. The terminal sends the selected data to the server.

[1500] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1501] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[1502] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1503] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[1504] Example of a sign (in-house guide)

[1505] Here's a concrete example of how a user can find out the location of the elevators using a terminal within the building.

[1506] 1. The user selects the "elevator location".

[1507] 2. The terminal sends the selected data to the server.

[1508] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1509] 4. The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[1510] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1511] 6. The server sends the generated response to the terminal, and the terminal displays the response to the user.

[1512] Specific examples of prompt phrases include, "What are your current business hours?" and "Where is the elevator?"

[1513] As described above, the system of the present invention is capable of responding quickly and accurately to a wide range of inquiries from users. The overall efficiency and automation of the system are improved, and it becomes possible to always provide the latest information.

[1514] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1515] Step 1:

[1516] The user makes a selection for a predefined input. The user interface terminal displays multiple options to the user. For example, options may include "Check opening hours," "Get directions within the building," and "Inquire about product information." The user makes a selection by tapping or clicking. The input is the user's selection, and the output is the data of the selected option.

[1517] Step 2:

[1518] The device sends the user's selections to the server. Specifically, the device sends the data of the selected options to the server as an HTTP request. This data is in JSON format and is passed to the server in a format such as { "query": "Check business hours"}. The input is the user's selection data, and the output is the selection data sent to the server.

[1519] Step 3:

[1520] The server parses the selected data it receives and generates an appropriate prompt. Specifically, the server extracts the "query" field from the received data and generates a corresponding prompt. For example, if the received data is { "query": "Check business hours"}, it will generate the prompt "Please tell me your current business hours". The input is the selected boilerplate data, and the output is the generated prompt.

[1521] Step 4:

[1522] The server sends a generated prompt to the generative artificial intelligence (AI). Specifically, it sends the generated prompt text as an API request to the generative AI model. The generative AI receives this prompt and generates a response. For example, in response to the prompt "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays." The input is the generated prompt text, and the output is a natural language response from the generative AI model.

[1523] Step 5:

[1524] The server sends the generated response to the terminal. Specifically, the server converts the received natural language response back into JSON format and sends it to the terminal as an HTTP response. For example, if the generated response is "Our business hours are from 9 am to 6 pm on weekdays," it will be sent to the terminal in the format { "response": "Our business hours are from 9 am to 6 pm on weekdays"}. The input is the response sentence from the generative artificial intelligence model, and the output is the response data sent to the terminal.

[1525] Step 6:

[1526] The terminal receives a response from the server and displays it to the user. Specifically, the terminal parses the received data and displays it on the screen. Through this screen, the user can confirm a response such as, "Our store hours are from 9 am to 6 pm on weekdays." The input is the response data from the server, and the output is the natural language response displayed on the screen.

[1527] (Application Example 1)

[1528] 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".

[1529] In recent years, there has been a growing demand for information provision systems utilizing smart devices to improve customer convenience in physical stores. However, conventional systems have challenges in responding immediately to customer needs and providing efficient guidance and product information. Furthermore, conventional systems often rely on human intervention, resulting in high operational costs and maintenance burdens. Therefore, there is a need for the development of automated systems that can provide customers with the information they need quickly and accurately.

[1530] 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.

[1531] In this invention, the server includes means for receiving an operation selected by the user from a set of predefined inputs, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for providing the generated response to the user, and means for providing an application installed on a smart device to provide information relevant to the user. This makes it possible to provide the information the user needs quickly and accurately, and to significantly improve customer convenience in physical stores.

[1532] A "user" is a customer who uses a system to obtain information.

[1533] "Standard input" refers to input options provided to the user as predetermined choices.

[1534] A "generated prompt" is an input sentence for a generative artificial intelligence system that is constructed based on a predefined input selected by the user.

[1535] "Generative artificial intelligence" refers to an artificial intelligence system that generates responses in natural language based on input prompts.

[1536] "Response" refers to the reply generated by generative artificial intelligence to a user's inquiry.

[1537] "Means of providing to the user" refers to the interface or method for displaying the generated response to the user.

[1538] A "smart device" refers to a portable device with internet connectivity, such as a smartphone or tablet.

[1539] An "application" is a software program that runs on a smart device and provides information to the user.

[1540] System Configuration

[1541] This invention is an information provision system designed to improve customer convenience in physical stores. The system mainly consists of three main components: a user terminal, a server, and a generative artificial intelligence model.

[1542] 1. User terminal

[1543] The user terminal refers to a smart device such as a smartphone or tablet. This terminal presents pre-defined input options and provides an interface for the user to select the information they need.

[1544] 2. Server

[1545] The server receives standardized input data sent from the user terminal and creates a generation prompt. It then sends this generation prompt to a generative artificial intelligence model and sends the generated response back to the user terminal.

[1546] 3. Generative artificial intelligence models

[1547] Generative artificial intelligence models generate natural language responses based on input prompts. Specifically, high-performance generative AI modeling technologies such as OpenAI's GPT-3 are used.

[1548] Program processing and the hardware and software used

[1549] User terminal

[1550] The user terminal accepts pre-defined inputs from the user through the user interface. For example, options such as "Facility Guide," "Product Information Inquiry," and "Promotion Information" are displayed. When the user selects a pre-defined input, this information is sent to the server.

[1551] server

[1552] The server receives predefined inputs sent from the user's terminal. After receiving them, the server generates a prompt based on the selected predefined input. For example, if the predefined input is "building information," the server generates the prompt "I would like building information." This prompt is sent to a generative artificial intelligence model, which generates a response in natural language.

[1553] Generative artificial intelligence models

[1554] The OpenAI GPT-3 is used as the generative artificial intelligence model. GPT-3 analyzes the sent prompt and generates an appropriate response. For example, it provides specific guidance information such as, "The elevator is located at the back right of the entrance hall."

[1555] Display of response to user terminal

[1556] The generated response is sent back to the user terminal via the server. The user terminal displays the generated response on its user interface, allowing the user to immediately obtain the necessary information.

[1557] Examples of specific cases and prompt statements

[1558] Specific example

[1559] Let's consider a scenario where a user uses their smartphone to obtain information within a physical store. For example, if the user selects "Store Guide," the system will operate as follows:

[1560] 1. The user opens the smartphone app and selects "In-house Guide".

[1561] 2. The app sends a request for "building information" to the server.

[1562] 3. The server generates a prompt saying "I would like a tour of the building" and sends it to the generative artificial intelligence.

[1563] 4. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1564] 5. The server sends the generated response to the user's terminal.

[1565] 6. A response is displayed on the user's smartphone.

[1566] Example of a prompt

[1567] Prompt: "I'd like a tour of the building."

[1568] Response: "The elevator is located at the back right of the entrance hall."

[1569] In this way, the invention can quickly and accurately provide users with a variety of information they need within a physical store.

[1570] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1571] Step 1:

[1572] The user opens an application on their smart device.

[1573] Input: Smart device operation

[1574] Operation: The user launches the application on their smart device and accesses an interface that displays pre-set input options.

[1575] Output: The predefined input options are displayed in the user interface.

[1576] Step 2:

[1577] The user selects "In-house information" from the pre-defined input options.

[1578] Input: User selection operation

[1579] Operation: Select "Building Guide" from the user interface, and the application will recognize this selection.

[1580] Output: Selected standard input data

[1581] Step 3:

[1582] The terminal sends the selected standard input data to the server.

[1583] Input: Standard input data

[1584] Operation: The terminal sends the selected predefined input data to the server as an HTTP request.

[1585] Output: Standard input data received by the server

[1586] Step 4:

[1587] The server generates a prompt based on predefined input.

[1588] Input: Standard input data

[1589] Operation: The server parses the received standardized input data and selects a corresponding generated prompt from a template. In this example, the prompt "I would like a tour of the building" is generated.

[1590] Output: Generated prompt("I'd like a tour of the building")

[1591] Step 5:

[1592] The server sends a generation prompt to the generative artificial intelligence, which then generates a response.

[1593] Input: Generate prompt

[1594] Operation: The server sends a generated prompt to the OpenAI GPT-3 API. GPT-3 parses the prompt and generates an appropriate response.

[1595] Output: Generated response (e.g., "The elevator is located at the back right of the entrance hall.")

[1596] Step 6:

[1597] The server sends the generated response to the user's terminal.

[1598] Input: Generated response

[1599] Operation: The server sends the generated response to the user's terminal as an HTTP response.

[1600] Output: Response data received by the user terminal

[1601] Step 7:

[1602] The terminal displays the response it has received to the user.

[1603] Input: Received response data

[1604] Operation: The response data received by the user terminal is displayed on the user interface. The user confirms the information, "The elevator is located at the back right of the entrance hall."

[1605] Output: Response data displayed on the user interface

[1606] This processing step allows users to efficiently obtain information within the physical store, improving convenience.

[1607] 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.

[1608] System Configuration

[1609] In addition to its basic function of receiving standardized input from the user and generating a response using generative artificial intelligence, the system of the present invention improves the quality of the response by incorporating an emotion engine that recognizes and analyzes the user's emotions. This system includes the following main components.

[1610] 1. User Interface Terminal

[1611] 2. Server

[1612] 3. Generative artificial intelligence models

[1613] 4. Emotional Engine

[1614] Program processing

[1615] Acceptance of user input

[1616] terminal

[1617] It functions as an interface for users to select from predefined input options. The terminal displays multiple choices to the user, from which the user makes a selection. Examples of choices include "check opening hours," "get directions," and "inquire about product information." When presenting these choices, the terminal can use an emotion engine to analyze the user's emotions and suggest appropriate options.

[1618] Submit your selections

[1619] terminal

[1620] The system receives predefined input data selected by the user and sends that data to the server. This allows the server to recognize the user's selection and initiate the process of generating a corresponding response.

[1621] Prompt generation

[1622] server

[1623] The server generates prompts based on the standardized input information it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it incorporates feedback from the emotion engine to adjust the prompts to match the user's emotions.

[1624] Response generation

[1625] server

[1626] The server sends a generation prompt to the generative AI and waits for a response. The generative AI generates a response in natural language based on the received prompt. For example, in response to "What are your current business hours?", it might generate a response such as "Our business hours are from 9 am to 6 pm on weekdays."

[1627] Emotional regulation of responses

[1628] Emotional Engine

[1629] Once the generated response is returned to the server, the emotion engine analyzes it and modifies it to suit the user's current emotions. For example, if the user is stressed, the response is changed to be more polite and kind.

[1630] Displaying responses to the user

[1631] terminal

[1632] The terminal receives the response sent from the server and displays it to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our store hours are from 9 am to 6 pm on weekdays. Is there anything else we can help you with?"

[1633] Specific example

[1634] Examples of call centers

[1635] scenario

[1636] Consider a scenario where a user accesses an automated call center system to inquire about business hours. If the emotion engine determines that the user is experiencing stress, the process would proceed as follows:

[1637] 1. The user selects "Check business hours".

[1638] 2. The terminal sends the selected data to the server.

[1639] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1640] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[1641] 5. The generative artificial intelligence generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1642] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[1643] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1644] Example of a sign (in-house guide)

[1645] scenario

[1646] Let's consider a scenario where a user wants to know the location of the elevator using a terminal for building information. If the emotion engine determines that the user is in an excited state, the process would proceed as follows:

[1647] 1. The user selects the "elevator location".

[1648] 2. The terminal sends the selected data to the server.

[1649] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1650] 4. The server sends a generation prompt to the generative artificial intelligence and generates a response.

[1651] 5. The generative artificial intelligence generates the response, "The elevator is located in the back right of the entrance hall."

[1652] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[1653] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1654] In this way, the system of the present invention can respond quickly and accurately to a variety of inquiries from users, and can also provide responses that are tailored to the user's emotions. This makes it possible to achieve higher user satisfaction.

[1655] The following describes the processing flow.

[1656] Step 1:

[1657] The user accesses a guidance terminal or an IVR system in a call center and selects the appropriate item from several predefined input options displayed. During this process, the user's emotions are analyzed by an emotion engine.

[1658] Step 2:

[1659] The terminal sends the user's selected standard input data and the emotion data analyzed by the emotion engine to the server. This allows the server to recognize the user's selections and emotions.

[1660] Step 3:

[1661] The server generates appropriate prompts based on the standardized input data it receives. For example, if "Check business hours" is selected, it generates the prompt "Please tell me your current business hours."

[1662] Step 4:

[1663] The server processes the generated prompts using an emotion engine, adjusting them to match the user's emotions. For example, if the user is already stressed, the prompt might be changed to a gentler tone, such as, "Excuse me, but could you please tell me your current business hours?"

[1664] Step 5:

[1665] The server sends a pre-configured generation prompt to the generative AI, which then generates a response. The generative AI then generates a response in natural language based on the received prompt.

[1666] Step 6:

[1667] Generative artificial intelligence generates responses in response to prompts. For example, in response to "What are your current business hours?", it generates the response "Our business hours are from 9 am to 6 pm on weekdays."

[1668] Step 7:

[1669] The server receives a response generated by a generative artificial intelligence, analyzes that response again using an emotion engine, and modifies the content to suit the user's emotions. For example, if the user is feeling stressed, it might respond politely with, "Our business hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience. Do you have any further questions?"

[1670] Step 8:

[1671] The server sends an emotionally regulated response to the terminal.

[1672] Step 9:

[1673] The terminal displays the response it receives from the server to the user. For example, it might present an emotionally responsive message via screen or audio, such as, "Our business hours are weekdays from 9 am to 6 pm. We apologize for any inconvenience. Do you have any further questions?"

[1674] Step 10:

[1675] The system reviews the user's responses, whether displayed or voiced, and obtains the necessary information. This cycle is repeated if the user makes further inquiries.

[1676] (Example 2)

[1677] 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".

[1678] Traditional dialogue systems tend to have low user satisfaction because they generate responses without considering the user's emotional state. Furthermore, users don't always choose the optimal option, resulting in inappropriate responses. This can lead to user stress and inconvenience, which is a significant problem.

[1679] 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.

[1680] In this invention, the server includes means for receiving an operation in which the user selects from a set of predefined inputs, means for transmitting the selected predefined input, means for generating a generation prompt based on the selected predefined input, means for transmitting the generation prompt to a generative artificial intelligence system to generate a response, means for adjusting the generated response to match the user's emotions, and means for providing the adjusted response to the user. This makes it possible to provide a response that is adapted to the user's emotional state, thereby improving user satisfaction.

[1681] 1. A "user" is an entity that uses a system to make selections from predefined inputs and receives a response.

[1682] 2. "Standard input" refers to a predetermined input format or item that the user can select.

[1683] 3. "Means for accepting selection operations" refers to a function that provides an interface for users to select the appropriate option from a set of predefined inputs.

[1684] 4. "Means for sending selected predefined inputs" refers to a communication function for sending user-selected content to the server.

[1685] 5. A "generated prompt" is a sentence in the form of a question or instruction that is generated based on selected predefined input.

[1686] 6. "Means for generating generation prompts" refers to a function that generates appropriate questions or instructions based on the received standard input.

[1687] 7. "Generative artificial intelligence" refers to an artificial intelligence model that receives a generative prompt as input and generates a natural language response based on it.

[1688] 8. "Means for sending a generation prompt to a generative artificial intelligence" refers to a communication function that sends a generation prompt to a generative artificial intelligence and causes it to generate a response.

[1689] 9. "Means for generating a response" refers to the function of a generative artificial intelligence that receives a generation prompt and generates a natural language response based on it.

[1690] 10. "Means for adjusting generated responses to match the user's emotions" refers to a function that modifies generated responses using an emotion engine to match the user's current emotional state.

[1691] 11. “Means of providing an adapted response to the user” means a function that provides the user with an emotionally adapted response, either visually or aurally.

[1692] System Configuration

[1693] The system of the present invention includes a terminal that accepts an operation for a user to select from a set of predefined inputs, a server that transmits the selected predefined input, a server that generates a generation prompt based on the selected predefined input, a server that transmits the generation prompt to a generative artificial intelligence model and causes it to generate a response, an emotion engine that adjusts the generated response to match the user's emotions, and a terminal that provides the adjusted response to the user.

[1694] Hardware and software

[1695] The hardware used in this system includes terminals that provide the user interface (such as PCs, tablets, and smartphones), servers that process data, and cameras and microphones that collect user emotion data. The software includes generative artificial intelligence models (such as GPT-3), emotion engines (emotion analysis software), communication APIs, and applications for the user interface.

[1696] Acceptance of user input

[1697] terminal

[1698] The user clicks on pre-defined input options on the device screen. These options include, for example, "Check opening hours," "Get directions," and "Inquire about product information." The device transmits the user's facial expressions and voice via the camera and microphone to an emotion engine, which analyzes the user's emotions. Based on this analysis, it can also present the user with the most suitable options.

[1699] Submit your selections

[1700] terminal

[1701] The user's selected input data is sent to the server. This data is sent via a dedicated communication API, and its contents are recorded on the server.

[1702] Prompt generation

[1703] server

[1704] The server generates prompts based on the selected data it receives. For example, if the user selects "Check opening hours," the server generates a prompt such as "Please tell me your current opening hours." Furthermore, it adjusts the prompt based on the user's emotions, taking into account feedback from the emotion engine. If the emotion engine determines that the user is stressed, the prompt becomes more polite, such as "Could you please tell me your current opening hours?"

[1705] Response generation

[1706] server

[1707] The server sends a generation prompt to a generative artificial intelligence model (e.g., GPT-3) to generate a response. Based on the received prompt, the generative AI model generates an appropriate natural language response. This ensures that the user receives an accurate and appropriate response to the question they selected.

[1708] Emotional regulation of responses

[1709] Emotional Engine

[1710] Once the generated response is returned to the server, the emotion engine analyzes the response and modifies it to suit the user's emotions. For example, if the user is feeling stressed by the generated response, "Our store hours are from 9 am to 6 pm on weekdays," the engine will modify it to, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[1711] Displaying responses to the user

[1712] terminal

[1713] The terminal receives an emotionally tuned response sent from the server and displays it to the user. The terminal not only displays the response on the screen but also plays it aloud as needed. For example, it can display the response "Our current business hours are weekdays from 9 am to 6 pm" on the screen and play it aloud simultaneously.

[1714] Specific example

[1715] Examples of call centers

[1716] Here's a specific example of a user accessing a call center's automated response system to inquire about business hours. The following is the process if the emotion engine determines the user is experiencing stress.

[1717] 1. The user selects "Check business hours".

[1718] 2. The terminal sends the selected data to the server.

[1719] 3. The server generates a prompt that says, "Please tell me your current business hours."

[1720] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[1721] 5. The generative artificial intelligence model generates the response, "Our store's business hours are from 9:00 AM to 6:00 PM on weekdays."

[1722] 6. The emotion engine analyzes this response and, for example, modifies it for users who are feeling stressed, to say, "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience this may cause."

[1723] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1724] Examples of signs

[1725] Here's a concrete example of a user wanting to know the location of the elevators using a terminal for building information. The process when the emotion engine determines that the user is in an excited state is as follows:

[1726] 1. The user selects the "elevator location".

[1727] 2. The terminal sends the selected data to the server.

[1728] 3. The server generates a prompt that says, "Please tell me where the elevator is."

[1729] 4. The server sends a generation prompt to the generative artificial intelligence model and generates a response.

[1730] 5. The generative artificial intelligence model generates the response, "The elevator is located in the back right of the entrance hall."

[1731] 6. The emotion engine analyzes this response and, for example, modifies it to soften the content for an excited user, saying, "The elevator is located at the back right of the entrance hall, so please don't worry."

[1732] 7. The server sends an emotion-adjusted response to the terminal, which then displays it to the user.

[1733] This system makes it possible to provide appropriate responses that are adapted to the user's emotions, and is expected to improve user satisfaction.

[1734] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1735] Step 1: Receiving user input

[1736] terminal

[1737] The user clicks on a pre-defined input option on the device screen. Examples of options include "Check opening hours," "Store information," and "Inquire about product information."

[1738] input

[1739] Items selected by the user (e.g., "Check business hours")

[1740] Data processing

[1741] The selected items are retrieved as data and converted to a format corresponding to the next processing step.

[1742] output

[1743] Selected item data (e.g., "Check business hours")

[1744] Specific operation: The device collects the user's facial expressions and voice through the camera and microphone, sends them to the emotion engine, and analyzes the user's emotions. Based on the analysis results, it presents the user with the most suitable options.

[1745] Step 2: Submit your selections

[1746] terminal

[1747] The input data selected by the user is sent to the server.

[1748] input

[1749] Selected item data (e.g., "Check business hours")

[1750] Data processing

[1751] Convert the selected item data into an HTTP request format.

[1752] output

[1753] HTTP request data sent to the server

[1754] Specific operation: Selected item data is sent to the server using a dedicated communication API. The server receives the request and records it in the database.

[1755] Step 3: Generate prompt

[1756] server

[1757] The server creates a generation prompt based on the selected data it receives.

[1758] input

[1759] Selection data sent via HTTP request (e.g., "Check business hours")

[1760] Data processing

[1761] Based on the selected data received, an appropriate prompt is generated (e.g., "Please tell me your current business hours"). Furthermore, the prompt is adjusted based on feedback from the emotion engine.

[1762] output

[1763] The generated prompt message (e.g., "What are your current business hours?")

[1764] Specific operation: The emotion engine analyzes the user's emotional state, and if it determines, for example, that the user is feeling stressed, it adjusts the prompt to something like, "Could you tell me your current business hours?"

[1765] Step 4: Response Generation

[1766] server

[1767] The server sends a generation prompt to a generative artificial intelligence model, which then generates a response.

[1768] input

[1769] The generated prompt message (e.g., "What are your current business hours?")

[1770] Data processing

[1771] The generation prompt is sent to the generative artificial intelligence model using a communication API.

[1772] output

[1773] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[1774] Specific operation: A generation prompt is sent to a generative artificial intelligence model using natural language processing techniques (e.g., GPT-3), and an appropriate response is generated.

[1775] Step 5: Emotional regulation of responses

[1776] Emotional Engine

[1777] The generated response is analyzed, and the content is modified to suit the user's emotions.

[1778] input

[1779] Response data from a generative artificial intelligence model (Example: "Our store hours are from 9:00 AM to 6:00 PM on weekdays")

[1780] Data processing

[1781] The emotion engine analyzes the user's emotional state and modifies the response text accordingly (e.g., "Our store hours are from 9 am to 6 pm on weekdays. We apologize for any inconvenience.").

[1782] output

[1783] Corrected response data

[1784] Specific action: When the emotion engine detects a user's stress level, it adds polite phrases such as "We apologize for any inconvenience this may cause" to the response.

[1785] Step 6: Displaying a response to the user

[1786] terminal

[1787] The terminal receives an emotion-adjusted response sent from the server and displays it to the user.

[1788] input

[1789] Corrected response data (Example: "Our business hours are from 9:00 AM to 6:00 PM on weekdays. We apologize for any inconvenience.")

[1790] Data processing

[1791] The data is converted for screen display, and then converted for audio output as needed.

[1792] output

[1793] Response information that the user receives visually or aurally

[1794] Specific operation: The device displays the response on the screen and plays it aloud. For example, it displays the response "Our current business hours are from 9 am to 6 pm on weekdays" on the screen and plays it aloud.

[1795] (Application Example 2)

[1796] 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".

[1797] Conventional user interface systems, when generating responses using generative artificial intelligence in response to standardized user input, lacked the ability to consider the user's emotional state, posing a challenge to improving the user experience. In particular, within autonomous vehicles, it is necessary to appropriately recognize the stress and excitement felt by passengers and provide corresponding responses to achieve a more comfortable riding experience.

[1798] 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 receiving an operation selected by the user from a set of standard inputs, means for generating a generation prompt based on the selected standard input, means for transmitting the generation prompt to a generative artificial intelligence and causing it to generate a response, means for analyzing the generated response with an emotion engine and modifying it according to the user's emotional state, and means for providing the user with an emotion-adjusted response. This makes it possible to provide a response that takes the user's emotional state into consideration, and in particular, it is possible to provide a comfortable and reassuring riding experience to passengers of autonomous vehicles.

[1799] "A means of accepting user selection from predefined inputs" refers to an interface that allows users to select their desired item from multiple options presented.

[1800] "Means for generating a generation prompt based on selected standard input" refers to a function that creates a specific prompt to send to a generative artificial intelligence based on the input content selected by the user.

[1801] "A means of sending a generation prompt to a generative artificial intelligence and causing it to generate a response" refers to a function that sends a generated prompt to a generative artificial intelligence and obtains a natural language response as its answer.

[1802] "A means of analyzing the generated response with an emotion engine and modifying it according to the user's emotional state" refers to a function that analyzes the response generated by a generative artificial intelligence with an emotion analysis engine and adapts the response content to the user's emotional state based on the analysis results.

[1803] "Means of providing emotionally regulated responses to users" refers to functions that communicate responses modified to match the user's emotional state to the user through means such as sight or hearing.

[1804] "A means of displaying multiple options that allow the user to select one of the predefined inputs" refers to a function that presents multiple choices on a display device that the user can select from, thereby enabling the user to make an appropriate choice.

[1805] "A means of analyzing a user's emotions using an emotion engine and suggesting appropriate options" refers to a function that analyzes the user's emotional state using an emotion analysis engine and presents the user with the most suitable options based on the results.

[1806] "Means of using a pre-saved template corresponding to selected standard input when sending a generation prompt to a generative artificial intelligence" refers to a function that generates a prompt using a pre-saved template based on the standard input selected by the user and sends it to the generative artificial intelligence.

[1807] "Means for adjusting prompts based on the user's emotional state" refers to a function that appropriately modifies the content of the generated prompts, taking into account the results of the user's emotion analysis.

[1808] System Configuration and Hardware

[1809] This invention is a system that receives standardized input from the user, generates a response using generative artificial intelligence, and further analyzes the user's emotions using an emotion engine to provide a response tailored to the user's emotional state. This system consists of the following main components.

[1810] 1. User interface devices (smart glasses, in-car displays, microphones, speakers, etc.)

[1811] 2. Server

[1812] 3. Generative artificial intelligence models

[1813] 4. Emotional Engine

[1814] software

[1815] The speech_recognition library is used to convert the user's speech into text.

[1816] The user's emotions are analyzed using the emotion analysis engine in the Hugging Face transformers library.

[1817] Access a generative artificial intelligence service using a RESTful API and generate a response.

[1818] Processing flow

[1819] The server will perform the following steps:

[1820] 1. Receiving user input:

[1821] The user interface terminal accepts user input by allowing selection from a set of predefined inputs. For user voice input, the speech_recognition library is used to convert the speech to text.

[1822] 2. Emotion analysis:

[1823] The acquired text data is sent to the emotion analysis engine in Hugging Face's transformers library to determine the user's emotional state.

[1824] 3. Prompt generation:

[1825] The system generates prompts based on predefined inputs selected by the user. For example, if the user selects that they want to go to the next tourist destination, the prompt "I would like to go to the next tourist destination." will be generated.

[1826] 4. Response generation:

[1827] The server sends the generated prompt to a generative artificial intelligence model, which then generates a response. An example of a generated response might be, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?"

[1828] 5. Emotional regulation:

[1829] The generated response is analyzed by an emotion engine, and the response content is modified according to the user's emotional state. For example, if the user is feeling stressed, the response might be modified to something like, "For your next sightseeing destination, there is a nearby tourist attraction called XX. We apologize for any inconvenience."

[1830] 6. Providing responses to users:

[1831] Emotionally tuned responses are provided on the user interface terminal, either through display or audio.

[1832] Specific example

[1833] For example, when used inside an autonomous vehicle, the following are possible prompt messages and responses:

[1834] User input: I want to go to the next tourist destination. Emotional state: positive

[1835] Examples of responses from generative artificial intelligence models:

[1836] As for your next sightseeing destination, there's a nearby tourist spot called XX. Why not visit it?

[1837] Examples of emotionally regulated responses:

[1838] For your next sightseeing destination, there is a nearby tourist attraction called [Name of tourist spot]. Have a wonderful time!

[1839] In this way, it becomes possible to respond in a way that takes into account the user's emotional state, and in particular, to provide a comfortable and reassuring riding experience for passengers in autonomous vehicles.

[1840] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1841] Step 1:

[1842] The system accepts user selections from a set of predefined input options. Using a user interface terminal (such as smart glasses, an in-car display, or a microphone), the user selects their desired item from multiple options presented. The terminal receives the input (voice or touch) and sends it to the server as text data.

[1843] Step 2:

[1844] The server receives the text data entered by the user and sends it to the sentiment analysis engine in the Hugging Face transformers library. This sentiment analysis engine analyzes the input text data and determines the user's emotional state (positive, negative, etc.). The output is returned as an emotion label and received by the server.

[1845] Step 3:

[1846] Based on the sentiment analysis results, the server creates a generated prompt corresponding to the user's selected standard input. This prompt is sent to the generative artificial intelligence system and converted into specific text, such as "I would like to go to the next tourist destination." The prompt is constructed based on pre-saved templates.

[1847] Step 4:

[1848] The server sends the generated prompt to the generative artificial intelligence (AI). The AI ​​analyzes the prompt and generates a corresponding natural language response. For example, it might generate a response like, "As your next sightseeing destination, there is a nearby tourist attraction called XX. Why not visit it?" This response is then returned to the server.

[1849] Step 5:

[1850] The server sends the generated response back to the emotion engine, which then adjusts the response based on the user's emotional state. For example, if the user is stressed, the emotion engine might modify the response to something like, "For your next sightseeing destination, a nearby attraction is XX. We apologize for any inconvenience." The modified response is then returned to the server.

[1851] Step 6:

[1852] The server sends an emotion-adjusted response to the user interface terminal. The terminal then provides the modified response to the user via display and audio. This allows the user to receive a more appropriate response based on their emotional state.

[1853] 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.

[1854] 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.

[1855] 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.

[1856] 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.

[1857] 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. In the upper and lower directions of the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. Also, the upper side of the concentric circles is where "pleasant" emotions are located, and the lower side is where "unpleasant" emotions are located. In this way, 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.

[1858] 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.

[1859] 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.

[1860] 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.

[1861] 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."

[1862] 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.

[1863] 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.

[1864] 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.

[1865] 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.

[1866] 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.

[1867] 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.

[1868] 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.

[1869] 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.

[1870] 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.

[1871] 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.

[1872] 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.

[1873] 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 as being incorporated by reference.

[1874] The following is further disclosed regarding the embodiments described above.

[1875] (Claim 1)

[1876] A means of accepting user selections from predefined inputs,

[1877] Means for generating a generation prompt based on selected standard inputs,

[1878] A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a response,

[1879] Means for providing the generated response to the user,

[1880] A system that includes this.

[1881] (Claim 2)

[1882] The system according to claim 1, further comprising means for displaying multiple options that allow the user to select one of a set inputs.

[1883] (Claim 3)

[1884] The system according to claim 1, comprising means of using a pre-stored template corresponding to a selected standard input when sending a generation prompt to a generative artificial intelligence.

[1885] "Example 1"

[1886] (Claim 1)

[1887] A means of accepting user selections from predefined inputs,

[1888] A means for processing selected standard inputs and sending them to the server,

[1889] A means for generating a generation prompt based on a set of inputs received by the server,

[1890] A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a natural language response,

[1891] A means of providing the generated natural language response to the user,

[1892] A system that includes this.

[1893] (Claim 2)

[1894] The system according to claim 1, further comprising means for displaying multiple options that allow the user to select one of a set inputs.

[1895] (Claim 3)

[1896] The system according to claim 1, comprising means of using a pre-stored template corresponding to a selected standard input when sending a generation prompt to a generative artificial intelligence.

[1897] "Application Example 1"

[1898] (Claim 1)

[1899] A means of accepting user selections from predefined inputs,

[1900] Means for generating a generation prompt based on selected standard inputs,

[1901] A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a response,

[1902] Means for providing the generated response to the user,

[1903] A means comprising an application installed on a smart device in order to provide information related to the user,

[1904] A system that includes this.

[1905] (Claim 2)

[1906] The system according to claim 1, further comprising means for displaying multiple options that allow the user to select one of a set inputs.

[1907] (Claim 3)

[1908] The system according to claim 1, comprising means of using a pre-stored template corresponding to a selected standard input when sending a generation prompt to a generative artificial intelligence.

[1909] "Example 2 of combining an emotion engine"

[1910] (Claim 1)

[1911] A means of accepting user selections from predefined inputs,

[1912] A means for sending selected predefined inputs,

[1913] Means for generating a generation prompt based on selected standard inputs,

[1914] A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a response,

[1915] A means of adjusting the generated response to match the user's emotions,

[1916] Means for providing a tailored response to the user,

[1917] A system that includes this.

[1918] (Claim 2)

[1919] The system according to claim 1, further comprising means for displaying multiple options that allow the user to select one of a set inputs.

[1920] (Claim 3)

[1921] The system according to claim 1, comprising means of using a pre-stored template corresponding to a selected standard input when sending a generation prompt to a generative artificial intelligence.

[1922] "Application example 2 when combining with an emotional engine"

[1923] (Claim 1)

[1924] A means of accepting user selections from predefined inputs,

[1925] Means for generating a generation prompt based on selected standard inputs,

[1926] A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a response,

[1927] A means of analyzing the generated response with an emotion engine and making modifications according to the user's emotional state,

[1928] Means for providing emotionally regulated responses to users,

[1929] A system that includes this.

[1930] (Claim 2)

[1931] The system according to claim 1, further comprising means for displaying multiple options for selecting one of a set input, and means for analyzing the user's emotions using an emotion engine and suggesting an appropriate option.

[1932] (Claim 3)

[1933] The system according to claim 1, comprising means for using a pre-storage template corresponding to selected standard input when sending a generation prompt to a generative artificial intelligence, and means for adjusting the prompt based on the user's emotional state. [Explanation of symbols]

[1934] 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 of accepting user selections from predefined inputs, Means for generating a generation prompt based on selected standard inputs, A means for sending a generation prompt to a generative artificial intelligence and causing it to generate a response, Means for providing the generated response to the user, A system that includes this.

2. The system according to claim 1, further comprising means for displaying multiple options that allow the user to select one of the predefined inputs.

3. The system according to claim 1, comprising means of using a pre-stored template corresponding to a selected standard input when sending a generation prompt to a generative artificial intelligence.

Images