system

Abstract

We provide the system. [Solution] A means of collecting inquiry data entered by a user from a terminal, A means of sending the collected query data to the server, A means of analyzing the query data received by the server, generating queries for an artificial intelligence model based on that data, and obtaining answers, A means of sending the acquired response from the server to the terminal, A system that includes means for displaying the responses received by the terminal to the user.

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, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Currently, many companies and organizations handle inquiries by phone, which requires a lot of time and resources. There are also problems such as insufficient response to waiting times for phone calls and inquiries outside business hours. In many cases, it is difficult for users to obtain information quickly and easily, and the problem becomes particularly prominent during congestion. To address these problems, there is a need to build a system that efficiently utilizes AI to provide answers before phone inquiries.

Means for Solving the Problems

[0005] This invention provides a system that collects inquiry data entered by a user from a terminal and transmits that data to a server. The server analyzes the received inquiry data, generates inquiries from an artificial intelligence model based on that data, and obtains answers. The obtained answers are transmitted from the server to the terminal, and the terminal displays the received answers to the user. In this way, users can quickly obtain the necessary information before making a telephone inquiry. This reduces the burden of telephone support and improves user convenience.

[0006] A "device" refers to a device used by a user for operation, and includes devices such as personal computers, smartphones, and tablets.

[0007] "User" refers to an individual or group that operates a terminal and makes an inquiry.

[0008] "Inquiry data" refers to data related to questions and requests that users enter into their devices.

[0009] A "server" refers to a computer system that receives and processes inquiry data from terminals on a network.

[0010] "Analysis" refers to the process by which a server understands the query data it receives and extracts the appropriate information.

[0011] An "artificial intelligence model" refers to a program that uses machine learning algorithms to process data and generate appropriate responses.

[0012] "Generating a query" refers to the process of requesting necessary information from an artificial intelligence model based on the analyzed query data.

[0013] "Retrieving an answer" refers to the process of receiving an answer generated by an artificial intelligence model.

[0014] "To transmit" means to send data or information from one system to another system.

[0015] "To display" means to output information in a form that can be visually confirmed by the user on a terminal.

Brief Description of the Drawings

[0016] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. <0000之72>(这里原文可能有误,推测是 [Figure 4] ,翻译为 [Figure 4] ) It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Mode for Carrying Out the Invention

[0017] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0018] First, the terms used in the following description will be explained.

[0019] In the following embodiments, a labeled 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), etc.

[0020] In the following embodiments, a labeled RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0021] In the following embodiments, a labeled 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.

[0022] 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).

[0023] 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."

[0024] [First Embodiment]

[0025] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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".

[0037] This invention provides a system that provides quick and efficient answers to user inquiries. In this system, the user inputs inquiry data through a terminal and sends it to a server, the server generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[0038] System Configuration

[0039] 1. Inquiry input by the user

[0040] Users use individual devices to enter specific questions or requests. These devices include personal computers, smartphones, and tablets. Input is typically done through web forms or application input fields.

[0041] 2. Data transmission from terminal to server

[0042] The terminal has the functionality to send user-entered inquiry data to the server. HTTP POST requests are commonly used for data transmission. The terminal encodes this request in JSON format and sends it to the server.

[0043] 3. Server analysis of query data

[0044] The server has the function of receiving and appropriately analyzing the inquiry data. Specifically, it analyzes the content of the inquiry and identifies what kind of answer is needed. Based on the analysis results, the server generates an inquiry for the artificial intelligence model.

[0045] 4. Answer generation using artificial intelligence models

[0046] The server uses an artificial intelligence model (e.g., a natural language processing model) to generate appropriate answers to user inquiries. This AI model has the ability to generate optimal answers based on past data and a knowledge base.

[0047] 5. Sending responses from the server to the terminal.

[0048] The server-generated response is re-encoded in JSON format and sent to the terminal. The terminal receives this response data and displays it for the user.

[0049] Program processing

[0050] Question data collection

[0051] The user enters a question into the terminal's input field and clicks the submit button. The terminal retrieves the entered data and prepares it for transmission to the server in JSON format. The terminal then sends the data to the server as an HTTP POST request.

[0052] Receiving and analyzing query data on the server.

[0053] The server receives data in JSON format sent from the terminal. After receiving the data, the server analyzes the JSON data and extracts the question. The server then passes this question to an artificial intelligence model to generate an appropriate answer.

[0054] Linking text with artificial intelligence models

[0055] The server calls an AI API and queries the AI ​​model with the extracted question content. The AI ​​model generates an answer based on the received question and returns the result to the server.

[0056] Providing answers to users

[0057] The server receives the response from the artificial intelligence model and encodes it again in JSON format. The server sends this data to the terminal, which parses the received data and displays the response to the user.

[0058] Specific example

[0059] For example, consider a scenario where a user enters the question "What are your business hours?" into a terminal and clicks the send button. The terminal sends this question to a server, which analyzes the question and queries an artificial intelligence model. The AI ​​model generates the answer, "Our weekday business hours are from 9 AM to 6 PM," and returns it to the server. The server sends this answer to the terminal, which then displays the answer to the user. The user can quickly obtain the necessary information without having to make a phone call.

[0060] Thus, the present invention significantly improves user convenience and streamlines the handling of inquiries by companies and organizations.

[0061] The following describes the processing flow.

[0062] Step 1:

[0063] The user enters their inquiry into the input field on the device and clicks the submit button. This retrieves the inquiry data on the device.

[0064] Step 2:

[0065] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data structure will be as follows:

[0066] json

[0067] {

[0068] "query": "What are your opening hours?"

[0069] }

[0070] Step 3:

[0071] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the inquiry content (in this case, "What are your business hours?").

[0072] Step 4:

[0073] The server extracts the query content and analyzes it using natural language processing. This analysis includes preprocessing to understand the intent of the question. The analyzed data is then used to query the AI ​​model.

[0074] Step 5:

[0075] The server sends the analyzed query to the artificial intelligence model. Here, it calls the AI ​​model's API and sends data like the following:

[0076] json

[0077] {

[0078] "prompt": "User question: What are your opening hours?\nAI's answer:",

[0079] "max_tokens": 100

[0080] }

[0081] Step 6:

[0082] The artificial intelligence model receives data sent from the server and generates an appropriate response. This process is carried out by an algorithm within the model. The generated response is then sent back to the server.

[0083] Step 7:

[0084] The server receives the response sent back from the artificial intelligence model. The received response is, for example, the text: "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0085] Step 8:

[0086] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will be in the following format:

[0087] json

[0088] {

[0089] "Answer": "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0090] }

[0091] Step 9:

[0092] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[0093] Step 10:

[0094] The device displays the extracted answer to the user. This allows the user to visually confirm the answer, "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0095] This series of steps allows users to quickly obtain the necessary information through their device without having to make a phone call.

[0096] (Example 1)

[0097] 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."

[0098] Conventional inquiry handling systems struggle to provide quick and accurate answers to user inquiries, and in situations where efficient handling of a large volume of inquiries is required, the response time was often excessive. Furthermore, the lack of artificial intelligence technology to properly understand the content of inquiries and generate optimal answers based on that understanding could lead to decreased user satisfaction.

[0099] 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.

[0100] In this invention, the server includes means for parsing the received JSON-formatted query data, generating a prompt statement, querying an artificial intelligence model, and obtaining a response; means for re-encoding the generated response into JSON format and sending it to the terminal as an HTTP response; and means for the terminal to parsing the received response and displaying it to the user. This makes it possible to provide quick and accurate answers to user inquiries.

[0101] A "user" is the entity that accesses the system and makes inquiries, and refers to the person who uses a terminal to input information.

[0102] A "device" refers to a hardware device used by a user, such as a personal computer, smartphone, or tablet.

[0103] "Inquiry data" refers to information about questions and requests that users input using their devices and send to the system.

[0104] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a data format used to exchange inquiry data and response data between systems.

[0105] An "HTTP POST request" refers to a type of HTTP request that uses the HTTP protocol to send data from a client terminal to a server.

[0106] A "server" refers to a hardware and software system that receives, analyzes, and generates responses to inquiry data sent from terminals.

[0107] "Analysis" refers to the process by which a server interprets the content of received query data and performs appropriate processing in order to understand it.

[0108] A "prompt message" refers to a sentence generated for input into an artificial intelligence model, specifically text that clearly conveys the content of the inquiry.

[0109] An "artificial intelligence model" refers to a machine learning model that understands problems and generates answers in a way similar to a human.

[0110] "Answer" refers to an appropriate response to a user's inquiry, generated based on the analysis results performed by an artificial intelligence model.

[0111] An "HTTP response" refers to the response data sent from a server to a client terminal based on the HTTP protocol.

[0112] "Display" refers to the process by which the device presents the acquired response to the user.

[0113] This invention provides a system that provides quick and efficient answers to user inquiries. This system transmits inquiry data entered by the user via a terminal to a server, the server generates an answer using a generated AI model, and then provides that answer back to the user. Specific embodiments of this system are described below.

[0114] 1. User inquiry input

[0115] Users access the system interface using devices such as PCs, smartphones, and tablets. For example, they access a specified URL using a web browser and enter a question such as "What are your business days?" into an input form. Then they click the submit button.

[0116] 2. Preparing the terminal to send data

[0117] The terminal retrieves the question data entered by the user and encodes it in JSON format. Specifically, it uses the JSON.stringify method internally to generate JSON data in the format {"query": "What are your business days?"}.

[0118] 3. Sending data from the terminal to the server

[0119] The device sends the generated JSON data to the server as an HTTP POST request. The request includes the header information Content-Type: application / json.

[0120] 4. Receiving and analyzing data on the server

[0121] The server receives the HTTP POST request sent from the terminal and extracts JSON data from the request body. The JSON.parse method is used to parse the retrieved JSON data and extract the inquiry content, "What are your business days?".

[0122] 5. Generating queries for artificial intelligence models

[0123] The server generates a prompt based on the analyzed query. An example of a prompt is, "Please answer the following question: What are your business days?" The server then sends this prompt to the artificial intelligence model.

[0124] 6. Answer generation using artificial intelligence models

[0125] The server uses a generative AI model (for example, a natural language processing model) to generate the best response based on the submitted prompt. In this example, the generative AI model generates the response "Weekday business days are Monday through Friday" and sends it back to the server.

[0126] 7. Server encoding of data

[0127] The server then re-encodes the retrieved answer into JSON format. Specifically, it uses the JSON.stringify method again to generate JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."}.

[0128] 8. Sending responses from the server to the terminal.

[0129] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message.

[0130] 9. Data reception and analysis on the terminal.

[0131] The terminal receives the HTTP response sent from the server and parses the data using the JSON.parse method. As a result of the parsing, it extracts the answer {"answer": "Weekday business days are Monday to Friday."}.

[0132] 10. Providing answers to users

[0133] The device displays the answer to the user based on the analysis results. The user can see the answer "Weekday business days are Monday through Friday" on the device screen.

[0134] This invention allows users to quickly and accurately obtain the necessary information through a series of simple operations, and enables companies and organizations to significantly improve the efficiency of handling inquiries.

[0135] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0136] Step 1:

[0137] The user enters inquiry data using a terminal. They enter "What are your business days?" into the input field and click the submit button. The entered data ("What are your business days?") becomes input data for the terminal.

[0138] Step 2:

[0139] The terminal retrieves the inquiry data entered by the user ("What are your business days?") and encodes it in JSON format. This generates JSON data in the format {"query": "What are your business days?"}. This data becomes the output data sent from the terminal to the server.

[0140] Step 3:

[0141] The device sends the generated JSON data to the server as an HTTP POST request. This request includes the header information Content-Type: application / json. The data is sent over the internet to a specific endpoint on the server.

[0142] Step 4:

[0143] The server receives an HTTP POST request sent from the terminal. It extracts JSON data ({"query": "What are your business days?"}) from the request body and parses the data using the JSON.parse method. As a result of the parsing, the query content ("What are your business days?") is extracted. This extracted content becomes the output data for the server.

[0144] Step 5:

[0145] The server generates a prompt based on the analyzed inquiry ("What are your business days?"). Specifically, it generates a prompt in the form of "Please answer the following question: What are your business days?". This prompt becomes the input data for the artificial intelligence model.

[0146] Step 6:

[0147] The server sends a prompt ("Please answer the following question: What are your business days?") to an artificial intelligence model (for example, a natural language processing model). The generative AI model generates the best possible answer based on the prompt. Specifically, the generative AI model outputs the answer "Our business days are Monday through Friday." This answer becomes the input data for the server.

[0148] Step 7:

[0149] The server re-encodes the response obtained from the generating AI model ("Business days on weekdays are Monday through Friday.") into JSON format. Specifically, JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."} is generated. This data becomes the output data sent to the terminal.

[0150] Step 8:

[0151] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message. The sent JSON data becomes the input data for the terminal.

[0152] Step 9:

[0153] The terminal receives the HTTP response sent from the server. It parses the data ({"answer": "Business days on weekdays are Monday through Friday."}) using the JSON.parse method. As a result of the parsing, the answer ("Business days on weekdays are Monday through Friday.") is extracted. This parsing result becomes the output data for the terminal.

[0154] Step 10:

[0155] The device displays the retrieved answer to the user. The user is shown the answer "Weekday business days are Monday through Friday." on the device screen. The user can confirm this answer.

[0156] (Application Example 1)

[0157] 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."

[0158] In modern brick-and-mortar stores, a problem exists where customers spend a lot of time searching for specific products or locations within the store, leading to increased inquiries to store staff and reduced operational efficiency. This problem is particularly pronounced in large stores and those carrying a wide variety of products, and it contributes to decreased customer satisfaction.

[0159] 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.

[0160] In this invention, the server includes means for collecting inquiry data entered by a user from a terminal; means for transmitting the collected inquiry data to the server; means for analyzing the received inquiry data, generating inquiries from an artificial intelligence model based on that data, and obtaining answers; means for transmitting the obtained answers from the server to the terminal; means for displaying the received answers to the user; and means for generating answers and providing guidance based on the user's inquiry regarding specific locations or product locations within a physical store. This enables quick and efficient responses to customer inquiries within the store, improving customer satisfaction and streamlining store operations.

[0161] A "device" refers to a device operated by a user, and includes smartphones, tablets, personal computers, and other similar devices.

[0162] A "user" refers to an individual or legal entity that makes an inquiry using the system.

[0163] "Inquiry data" refers to data that includes questions and requests entered by the user through their device and sent to the server.

[0164] A "server" is a computing system that analyzes received inquiry data, generates answers using artificial intelligence models, and then sends those answers to terminals.

[0165] "Means of collection" refers to the function of a terminal that acquires and stores inquiry data entered by the user.

[0166] "Means of transmission" refers to the function of a device or software that sends the collected query data to the server.

[0167] "Means of analysis" refers to the process by which a server analyzes the query data it receives and understands its content.

[0168] "Means for generating queries" refers to a function that makes appropriate queries to the artificial intelligence model based on data analyzed by the server.

[0169] "Means of obtaining answers" refers to the function that allows the server to receive answers generated from the artificial intelligence model.

[0170] "Means of display" refers to a function that displays the response sent from the server to the terminal in a format that is easy for the user to read.

[0171] An "artificial intelligence model" is an algorithm that generates appropriate answers based on user inquiries, utilizing past data and knowledge bases.

[0172] A "physical store" refers to a physical location for sales or service provision, where customers can directly purchase goods or services.

[0173] This invention is a system for providing information quickly and efficiently to users when they are searching for specific products or locations within a physical store. In this system, the user inputs inquiry data using a terminal, a server analyzes that data, generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[0174] System Configuration

[0175] 1. Inquiry input by the user

[0176] Users use their smartphones or other devices within the physical store to enter questions about specific products or locations. These devices have a dedicated application installed, and users input their inquiry data through its input fields.

[0177] 2. Data transmission from terminal to server

[0178] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. The terminal program automatically formats and sends the data.

[0179] 3. Server analysis of query data

[0180] The server parses the received query data in JSON format and extracts its contents. Based on the parsed data, it generates appropriate queries that meet the demand and passes them to the artificial intelligence model.

[0181] 4. Answer generation using artificial intelligence models

[0182] The server uses an artificial intelligence model (for example, a natural language processing model built with TENSORFLOW®) to generate answers to received inquiries. The AI ​​model has the ability to generate optimal answers based on past data and a knowledge base.

[0183] 5. Sending responses from the server to the terminal.

[0184] The generated response is re-encoded in JSON format and sent from the server to the terminal. The terminal receives this response data and presents it to the user.

[0185] Hardware and software to be used

[0186] Hardware:

[0187] Smartphones (iOS, ANDROID (registered trademark))

[0188] software:

[0189] Python (Server application using Flask)

[0190] TensorFlow (for artificial intelligence models)

[0191] Specific example

[0192] For example, consider a scenario where a user enters the question "Where is the bread section?" into their device and clicks the submit button. The user's device sends this inquiry to the server, which analyzes the inquiry and queries an artificial intelligence model. The AI ​​model generates the answer "The bread section is in the third row of the food section." The server sends this answer to the user's device, which then displays the answer to the user.

[0193] Example of a prompt:

[0194] User input: "Where is the bread section?"

[0195] Prompt to the generating AI model: Generate the best answer to the user's question, "Where is the bread section?"

[0196] Thus, the system of the present invention improves customer service within stores and streamlines the handling of inquiries.

[0197] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0198] Step 1:

[0199] The user opens the application on their smartphone, enters the question in the input field, and presses the submit button.

[0200] Input: Inquiry data entered by the user (e.g., "Where is the bread section?")

[0201] Operation: The application retrieves input data and encodes it in JSON format.

[0202] Output: Encoded JSON data

[0203] Step 2:

[0204] The device sends JSON data to the server as an HTTP POST request.

[0205] Input: Encoded JSON data

[0206] Operation: The device configures an HTTP POST request and sends data to the specified URL on the server.

[0207] Output: HTTP POST request sent to the server

[0208] Step 3:

[0209] The server receives an HTTP request and parses the query data in JSON format.

[0210] Input: JSON data included in an HTTP POST request

[0211] Operation: The server analyzes the received data and extracts the query content (e.g., "Where is the bread section?").

[0212] Output: Analyzed query content

[0213] Step 4:

[0214] The server generates queries for the artificial intelligence model based on the analyzed data.

[0215] Input: Analyzed query content

[0216] Operation: The server passes the query content to the AI ​​model in an appropriate format (e.g., a prompt like "Where is the bread section?").

[0217] Output: Generated prompt message

[0218] Step 5:

[0219] The server uses an artificial intelligence model (e.g., TensorFlow) to generate answers based on the query.

[0220] Input: Generated prompt message

[0221] Operation: The artificial intelligence model generates an answer based on the prompt sentence (e.g., "The bread section is in the third row of the food section.").

[0222] Output: Generated answer

[0223] Step 6:

[0224] The server re-encodes the generated response into JSON format and sends it to the terminal.

[0225] Input: Generated answer

[0226] Operation: The server encodes the response in JSON format and sends it to the terminal as an HTTP response.

[0227] Output: Encoded JSON format response data

[0228] Step 7:

[0229] The device parses the received JSON data and displays the answer to the user.

[0230] Input: Response data in encoded JSON format

[0231] Operation: The terminal analyzes the received data and displays it in a user-friendly format (e.g., "The bread section is in the third row of the food section.").

[0232] Output: Answer displayed to the user

[0233] Through these steps, users can quickly obtain information about specific products or locations within a physical store.

[0234] 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.

[0235] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[0236] System Configuration

[0237] 1. Inquiry input by the user

[0238] Users use a device to enter specific questions or requests. This device includes PCs, smartphones, and tablets. The process begins when the user fills in the inquiry field and clicks the submit button.

[0239] 2. Data transmission from terminal to server

[0240] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. Standard network protocols are used for transmission.

[0241] 3. Server analysis of query data

[0242] The server receives the query data, converts it to the appropriate data format, and analyzes it. The analysis process also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the text data to identify the user's emotional state, such as anger, anxiety, or joy.

[0243] 4. Emotional analysis using an emotion engine

[0244] An emotion engine implemented within the server analyzes user emotions based on their inquiry data. The results of this analysis are then used in subsequent processing.

[0245] 5. Answer generation using artificial intelligence models

[0246] The server uses the analyzed data and the results of the emotion engine to generate a query for the artificial intelligence model. The AI ​​model generates an appropriate response based on the query and the emotional state. Because the response is output in an emotion-appropriate tone, the response is tailored to the user's emotions.

[0247] 6. Sending responses from the server to the terminal.

[0248] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal receives this response data and decodes it to present it to the user.

[0249] 7. Displaying responses via the device

[0250] The terminal analyzes the response data received from the server and displays it to the user. This allows the user to visually confirm the answer to the question.

[0251] Program processing

[0252] Question data collection

[0253] The user enters their question into the input field on the terminal and clicks the submit button. This prepares the inquiry data to be sent to the server in JSON format.

[0254] Receiving and analyzing query data on the server.

[0255] The server receives JSON data sent from the terminal and performs text analysis. Simultaneously, it also performs sentiment analysis to identify the user's emotional state.

[0256] Integration with the emotion engine

[0257] Text data is passed to an emotion engine to analyze the user's emotions. The results of the emotion analysis are then used in an artificial intelligence model.

[0258] Answer generation using artificial intelligence models

[0259] The server sends inquiry data, including sentiment analysis results, to an artificial intelligence model to generate an appropriate response based on the emotions.

[0260] Submit and display of responses

[0261] The server sends the generated response to the terminal, which then decodes and displays it to the user.

[0262] Specific example

[0263] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[0264] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[0265] The following describes the processing flow.

[0266] Step 1:

[0267] The user enters their inquiry into the input field on the device and clicks the submit button. This action retrieves the inquiry data on the device.

[0268] Step 2:

[0269] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data is sent as follows:

[0270] json

[0271] {

[0272] "query": "Why is my order delayed?"

[0273] }

[0274] Step 3:

[0275] The server receives the HTTP POST request sent from the terminal. The server extracts the JSON data from the request body and obtains the inquiry content (in this case, "Why is the order delayed?").

[0276] Step 4:

[0277] The server passes the inquiry content extracted by the server to the sentiment engine to analyze the user's sentiment. The sentiment engine analyzes the text data and identifies the sentiment states such as anger and dissatisfaction.

[0278] Step 5:

[0279] The server obtains the analysis result of the sentiment engine. For example, the sentiment of "anger" is identified as the analysis result.

[0280] Step 6:

[0281] The server sends the analyzed inquiry content and the result of the sentiment engine to the artificial intelligence model. Here, the server sends the following data.

[0282] json

[0283] {

[0284] "prompt": "User's question: Why is the order delayed?\nSentiment: Anger\nAI's answer:",

[0285] "max_tokens": 100

[0286] }

[0287] Step 7:

[0288] The artificial intelligence model receives data sent from the server and generates an appropriate response. In this case, the AI ​​model generates a response in a tone that takes the user's feelings into consideration, such as, "We apologize for the wait. We are currently checking the status of your order."

[0289] Step 8:

[0290] The server receives the response sent back from the artificial intelligence model. The received response might be text such as, "We apologize for the delay. We are currently checking the order status."

[0291] Step 9:

[0292] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will look like this:

[0293] json

[0294] {

[0295] "Answer": "We apologize for the delay. We are currently checking the status of your order."

[0296] }

[0297] Step 10:

[0298] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[0299] Step 11:

[0300] The terminal displays the extracted response to the user. This allows the user to visually confirm the response, "We apologize for the delay. We are currently checking the status of your order."

[0301] Through this series of steps, when the user makes an inquiry, they can receive a prompt response that takes into account their emotions.

[0302] (Example 2)

[0303] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as a "server", and the smart device 14 is referred to as a "terminal".

[0304] In modern inquiry systems, there is a demand for providing prompt and emotion - considered appropriate responses to inquiries from users. However, conventional systems lack the function of properly recognizing users' emotions, and often provide mechanical and uniform responses. Therefore, it is difficult to enhance users' satisfaction and trust. Thus, there is a desire to provide a system that can analyze users' emotions and generate flexible responses accordingly.

[0305] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0306] In this invention, the server includes: means for text - analyzing the received inquiry data and further analyzing the user's emotion using an emotion engine; means for generating an appropriate response using an artificial intelligence model based on the analyzed data and the result of the emotion engine; means for encoding the generated response in JSON format and transmitting it to the terminal. Thereby, it becomes possible to provide a prompt and appropriate response considering the user's emotion.

[0307] A "terminal" is a device that a user operates to input inquiry data and communicate with the server, and includes personal computers, smartphones, tablets, etc.

[0308] "Inquiry data" refers to the content of questions or requests input by the user to the terminal, and is usually information expressed in text form.

[0309] A "standard network protocol" refers to the technical standards used when sending and receiving data over the internet, and includes, for example, HTTP and HTTPS.

[0310] A "server" is a computer system that receives inquiry data entered by a user, performs text analysis and sentiment analysis, generates appropriate responses, and sends them to the terminal.

[0311] "Text analysis" is a method for analyzing received inquiry data and understanding its content, and it is performed using natural language processing technology.

[0312] An "emotion engine" is software or an algorithm that analyzes user inquiry data to identify the emotions contained in the text.

[0313] An "artificial intelligence model" is a system that uses machine learning techniques to generate appropriate answers based on inquiry data and analysis results.

[0314] "JSON format" is a lightweight, text-based data format for structuring and representing data, and it is an abbreviation for JavaScript Object Notation.

[0315] "Decoding" refers to the process of converting encoded data, such as JSON format, back to its original format, and is performed so that the device can display the data received from the server to the user.

[0316] "Emotion analysis results" refer to data indicating emotions identified by the emotion engine after analyzing user inquiry data.

[0317] "Visual display" refers to the device displaying the response data on the screen in a format that is easy for the user to understand.

[0318] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[0319] Users enter specific questions or requests using a device, which includes PCs, smartphones, and tablets. The user enters their inquiry into the input field and clicks the submit button to begin the process.

[0320] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request using a standard network protocol such as HTTPS.

[0321] The server receives the inquiry data and performs text analysis and sentiment analysis. Natural language processing techniques are used for text analysis to understand the content of the user's inquiry. A sentiment engine is used for sentiment analysis to identify the user's emotional state.

[0322] The server passes text data to the emotion engine, which analyzes the user's emotions. The results of this analysis are then used by the subsequent artificial intelligence model to generate responses. For example, the emotion engine might identify that the user is feeling dissatisfied or angry in response to the question, "Why is my order delayed?"

[0323] The server uses the analyzed data and the results of the sentiment engine to send a query to the artificial intelligence model. The generative AI model generates an appropriate response based on the query and the sentiment state. An example of a prompt is used: "Analyze the user's sentiment from the following text and generate a response appropriate to that sentiment. Input: 'Why is my order delayed?'" The model would generate a response such as, "We apologize for the delay. We are currently checking the status of your order."

[0324] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal decodes this data and displays it visually to the user. This allows the user to feel that their emotions are understood and to have a better support experience.

[0325] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[0326] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0327] Step 1:

[0328] The user enters a question into the input field on the device and clicks the submit button.

[0329] Specific action: The user types "Why is my order delayed?" and clicks the submit button.

[0330] Input: Text data entered by the user (question content).

[0331] Output: The entered text data is temporarily stored on the device.

[0332] Step 2:

[0333] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request.

[0334] Specific operation: The program on the terminal converts the query data into JSON format and sends an HTTP POST request to the specified server URL.

[0335] Input: Text data entered by the user.

[0336] Output: The encoded JSON data is sent to the server as an HTTP POST request.

[0337] Step 3:

[0338] The system extracts JSON data from HTTP POST requests received by the server and performs text analysis. It also analyzes user emotions using an emotion engine.

[0339] Specific operation: The server parses the JSON data from the request body and extracts the text portion. Then, it performs text analysis using natural language processing techniques and sentiment analysis using a sentiment engine.

[0340] Input: Encoded JSON data.

[0341] Output: Text analysis results and sentiment analysis results.

[0342] Step 4:

[0343] The server sends a query to an artificial intelligence model based on the text analysis results and sentiment analysis results, and generates an answer.

[0344] Specific operation: The server generates prompts for the generative AI model and inputs them along with the sentiment analysis results. For example, it might use the prompt: "Analyze the user's sentiment from the following text and generate an appropriate response. Input: 'Why is my order delayed?'" The generative AI model then generates an appropriate response.

[0345] Input: Text analysis results, sentiment analysis results, prompt text.

[0346] Output: Generated answer text.

[0347] Step 5:

[0348] The server encodes the generated response text into JSON format and sends it to the terminal as an HTTP response.

[0349] Specific operation: The server-side program converts the response text into JSON format and sends it back to the terminal as an HTTP response.

[0350] Input: Generated response text.

[0351] Output: Encoded JSON data is sent to the terminal as an HTTP response.

[0352] Step 6:

[0353] The device decodes JSON data from the HTTP response it receives and displays it visually to the user.

[0354] Specific operation: The program on the terminal extracts JSON data from the HTTP response body and decodes it back into its original text format. Then, it displays it on the screen. For example, it might display, "We apologize for the wait. We are currently checking your order status."

[0355] Input: Encoded JSON data.

[0356] Output: The response text that is visually displayed to the user.

[0357] (Application Example 2)

[0358] 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".

[0359] Traditional inquiry systems often provide mechanical responses without considering the user's emotions, leading to decreased user satisfaction. Furthermore, the lack of responses in an appropriate tone based on emotions made it difficult to address users' psychological states.

[0360] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0361] In this invention, the server includes means for analyzing received inquiry data, recognizing the user's emotions using an emotion analysis engine based on that data, generating inquiries for an artificial intelligence model, and obtaining an answer appropriate to the emotions; means for transmitting the obtained answer to a terminal; and means for displaying the received answer to the user. This makes it possible to provide answers that take the user's emotions into consideration and improve the user experience.

[0362] A "terminal" is a device used by a user for input, such as a smartphone, personal computer, or tablet.

[0363] "Inquiry data" refers to information about questions and requests that users input and send through their devices.

[0364] A "server" is a central data processing unit that analyzes inquiry data, generates responses, and transmits them.

[0365] A "sentiment analysis engine" is a software program that identifies emotions from user inquiry data and determines their emotional state.

[0366] An "artificial intelligence model" is an artificial intelligence algorithm that generates the optimal response for a user based on inquiry data and the results of an emotion analysis engine.

[0367] "Answer" refers to the information provided or the response content generated based on the user's inquiry data.

[0368] "Transmission" refers to the act of transferring data between different devices, such as terminals and servers.

[0369] "Receiving" refers to the act of a terminal or server acquiring data sent from another party.

[0370] "Display" refers to the act of outputting received information to the device screen so that the user can visually confirm it.

[0371] The system implementing this invention consists of a terminal, a server, an emotion analysis engine, an artificial intelligence model, and a user. The terminal is a device used by the user to input inquiry data, and includes smartphones, personal computers, tablets, and the like.

[0372] Overall system flow

[0373] 1. Inquiry input by the user

[0374] The user enters their question or request into the input field on the terminal and clicks the submit button.

[0375] 2. Data transmission from terminal to server

[0376] The entered query data is encoded in JSON format and sent to the server. The HTTP POST protocol is used for transmission.

[0377] 3. Server analysis of query data

[0378] The server analyzes the received query data and converts it into an appropriate format. This analysis incorporates a sentiment analysis engine that identifies the user's emotions from the text data.

[0379] 4. Emotion analysis using an emotion analysis engine

[0380] The emotion analysis engine on the server recognizes the user's emotions based on the query data. For example, it identifies emotional states such as anger, anxiety, and joy.

[0381] 5. Answer generation using artificial intelligence models

[0382] The server uses the analyzed data and the results of the sentiment analysis engine to generate appropriate responses using an artificial intelligence model. This allows for responses to be output in a tone appropriate to the emotion.

[0383] 6. Sending responses from the server to the terminal.

[0384] The generated response is then encoded again in JSON format and sent to the terminal.

[0385] 7. Displaying responses via the device

[0386] The terminal decodes the received response data and presents it to the user. This display allows the user to visually confirm the answer to the question.

[0387] Hardware and software to be used

[0388] Hardware:

[0389] Devices such as smartphones, personal computers, and tablets

[0390] Server as a central data processing unit

[0391] software:

[0392] Python: The entire programming language

[0393] requests: A library for making HTTP requests.

[0394] JSON: Used for encoding and decoding data.

[0395] SentimentEngine: A software engine used for sentiment analysis.

[0396] AIResponseGenerator: An artificial intelligence model that generates responses based on emotions.

[0397] Specific example

[0398] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[0399] Example of a prompt

[0400] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[0401] As described above, this invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take user emotions into consideration.

[0402] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0403] Step 1:

[0404] User-initiated inquiry input: The user enters a question or request into the terminal's input field and clicks the submit button. The input data is in text format and constitutes the inquiry data. Input is made from the user to the terminal, and the output is the inquiry data.

[0405] Step 2:

[0406] Data transmission from terminal to server: The terminal encodes the input query data into JSON format and sends it to the server as an HTTP POST request. The terminal uses HTTP as the transmission protocol. The input is query data (in text format), and the output is encoded JSON data.

[0407] Step 3:

[0408] Server reception and parsing of query data: The server receives JSON data sent from the terminal and decodes it to obtain query data in text format. This data contains the user's questions and requests. The server then parses this data. The input is encoded JSON data, and the output is query data in text format.

[0409] Step 4:

[0410] Emotional analysis by the emotion analysis engine: The emotion analysis engine on the server identifies the user's emotions based on the analyzed query data. For example, it identifies emotional states such as anger, anxiety, and joy. In this step, the input is query data in text format, and the output is the emotional state.

[0411] Step 5:

[0412] AI-powered response generation: The server uses the analyzed query data and the results of the sentiment analysis engine to provide prompts to the generating AI model, which then generates an appropriate response. The input is the query data and sentiment state, and the output is a response (in text format) corresponding to the sentiment.

[0413] Example of a prompt:

[0414] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[0415] Step 6:

[0416] Sending the response from the server to the terminal: The generated response is re-encoded in JSON format and sent to the terminal as an HTTP response. The input is the generated text-formatted response, and the output is encoded JSON data.

[0417] Step 7:

[0418] Receiving and displaying responses by the terminal: The terminal decodes the JSON data received from the server and obtains the generated response in text format. This response is then displayed on the screen for presentation to the user. The input is encoded JSON data, and the output is the text-formatted response displayed to the user.

[0419] By following these steps, users can receive prompt and appropriate responses to their inquiries, thereby improving the user experience.

[0420] 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.

[0421] 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.

[0422] 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.

[0423] [Second Embodiment]

[0424] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0425] 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.

[0426] 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).

[0427] 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.

[0428] 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.

[0429] 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).

[0430] 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.

[0431] 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.

[0432] 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.

[0433] 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.

[0434] 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.

[0435] 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".

[0436] This invention provides a system that provides quick and efficient answers to user inquiries. In this system, the user inputs inquiry data through a terminal and sends it to a server, the server generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[0437] System Configuration

[0438] 1. Inquiry input by the user

[0439] Users use individual devices to enter specific questions or requests. These devices include personal computers, smartphones, and tablets. Input is typically done through web forms or application input fields.

[0440] 2. Data transmission from terminal to server

[0441] The terminal has the functionality to send user-entered inquiry data to the server. HTTP POST requests are commonly used for data transmission. The terminal encodes this request in JSON format and sends it to the server.

[0442] 3. Server analysis of query data

[0443] The server has the function of receiving and appropriately analyzing the inquiry data. Specifically, it analyzes the content of the inquiry and identifies what kind of answer is needed. Based on the analysis results, the server generates an inquiry for the artificial intelligence model.

[0444] 4. Answer generation using artificial intelligence models

[0445] The server uses an artificial intelligence model (e.g., a natural language processing model) to generate appropriate answers to user inquiries. This AI model has the ability to generate optimal answers based on past data and a knowledge base.

[0446] 5. Sending responses from the server to the terminal.

[0447] The server-generated response is re-encoded in JSON format and sent to the terminal. The terminal receives this response data and displays it for the user.

[0448] Program processing

[0449] Question data collection

[0450] The user enters a question into the terminal's input field and clicks the submit button. The terminal retrieves the entered data and prepares it for transmission to the server in JSON format. The terminal then sends the data to the server as an HTTP POST request.

[0451] Receiving and analyzing query data on the server.

[0452] The server receives data in JSON format sent from the terminal. After receiving the data, the server analyzes the JSON data and extracts the question. The server then passes this question to an artificial intelligence model to generate an appropriate answer.

[0453] Linking text with artificial intelligence models

[0454] The server calls an AI API and queries the AI ​​model with the extracted question content. The AI ​​model generates an answer based on the received question and returns the result to the server.

[0455] Providing answers to users

[0456] The server receives the response from the artificial intelligence model and encodes it again in JSON format. The server sends this data to the terminal, which parses the received data and displays the response to the user.

[0457] Specific example

[0458] For example, consider a scenario where a user enters the question "What are your business hours?" into a terminal and clicks the send button. The terminal sends this question to a server, which analyzes the question and queries an artificial intelligence model. The AI ​​model generates the answer, "Our weekday business hours are from 9 AM to 6 PM," and returns it to the server. The server sends this answer to the terminal, which then displays the answer to the user. The user can quickly obtain the necessary information without having to make a phone call.

[0459] Thus, the present invention significantly improves user convenience and streamlines the handling of inquiries by companies and organizations.

[0460] The following describes the processing flow.

[0461] Step 1:

[0462] The user enters their inquiry into the input field on the device and clicks the submit button. This retrieves the inquiry data on the device.

[0463] Step 2:

[0464] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data structure will be as follows:

[0465] json

[0466] {

[0467] "query": "What are your opening hours?"

[0468] }

[0469] Step 3:

[0470] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the inquiry content (in this case, "What are your business hours?").

[0471] Step 4:

[0472] The server extracts the query content and analyzes it using natural language processing. This analysis includes preprocessing to understand the intent of the question. The analyzed data is then used to query the AI ​​model.

[0473] Step 5:

[0474] The server sends the analyzed query to the artificial intelligence model. Here, it calls the AI ​​model's API and sends data like the following:

[0475] json

[0476] {

[0477] "prompt": "User question: What are your opening hours?\nAI's answer:",

[0478] "max_tokens": 100

[0479] }

[0480] Step 6:

[0481] The artificial intelligence model receives data sent from the server and generates an appropriate response. This process is carried out by an algorithm within the model. The generated response is then sent back to the server.

[0482] Step 7:

[0483] The server receives the response sent back from the artificial intelligence model. The received response is, for example, the text: "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0484] Step 8:

[0485] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will be in the following format:

[0486] json

[0487] {

[0488] "Answer": "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0489] }

[0490] Step 9:

[0491] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[0492] Step 10:

[0493] The device displays the extracted answer to the user. This allows the user to visually confirm the answer, "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0494] This series of steps allows users to quickly obtain the necessary information through their device without having to make a phone call.

[0495] (Example 1)

[0496] 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."

[0497] Conventional inquiry handling systems struggle to provide quick and accurate answers to user inquiries, and in situations where efficient handling of a large volume of inquiries is required, the response time was often excessive. Furthermore, the lack of artificial intelligence technology to properly understand the content of inquiries and generate optimal answers based on that understanding could lead to decreased user satisfaction.

[0498] 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.

[0499] In this invention, the server includes means for parsing the received JSON-formatted query data, generating a prompt statement, querying an artificial intelligence model, and obtaining a response; means for re-encoding the generated response into JSON format and sending it to the terminal as an HTTP response; and means for the terminal to parsing the received response and displaying it to the user. This makes it possible to provide quick and accurate answers to user inquiries.

[0500] A "user" is the entity that accesses the system and makes inquiries, and refers to the person who uses a terminal to input information.

[0501] A "device" refers to a hardware device used by a user, such as a personal computer, smartphone, or tablet.

[0502] "Inquiry data" refers to information about questions and requests that users input using their devices and send to the system.

[0503] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a data format used to exchange inquiry data and response data between systems.

[0504] An "HTTP POST request" refers to a type of HTTP request that uses the HTTP protocol to send data from a client terminal to a server.

[0505] A "server" refers to a hardware and software system that receives, analyzes, and generates responses to inquiry data sent from terminals.

[0506] "Analysis" refers to the process by which a server interprets the content of received query data and performs appropriate processing in order to understand it.

[0507] A "prompt message" refers to a sentence generated for input into an artificial intelligence model, specifically text that clearly conveys the content of the inquiry.

[0508] An "artificial intelligence model" refers to a machine learning model that understands problems and generates answers in a way similar to a human.

[0509] "Answer" refers to an appropriate response to a user's inquiry, generated based on the analysis results performed by an artificial intelligence model.

[0510] An "HTTP response" refers to the response data sent from a server to a client terminal based on the HTTP protocol.

[0511] "Display" refers to the process by which the device presents the acquired response to the user.

[0512] This invention provides a system that provides quick and efficient answers to user inquiries. This system transmits inquiry data entered by the user via a terminal to a server, the server generates an answer using a generated AI model, and then provides that answer back to the user. Specific embodiments of this system are described below.

[0513] 1. User inquiry input

[0514] Users access the system interface using devices such as PCs, smartphones, and tablets. For example, they access a specified URL using a web browser and enter a question such as "What are your business days?" into an input form. Then they click the submit button.

[0515] 2. Preparing the terminal to send data

[0516] The terminal retrieves the question data entered by the user and encodes it in JSON format. Specifically, it uses the JSON.stringify method internally to generate JSON data in the format {"query": "What are your business days?"}.

[0517] 3. Sending data from the terminal to the server

[0518] The device sends the generated JSON data to the server as an HTTP POST request. The request includes the header information Content-Type: application / json.

[0519] 4. Receiving and analyzing data on the server

[0520] The server receives the HTTP POST request sent from the terminal and extracts JSON data from the request body. The JSON.parse method is used to parse the retrieved JSON data and extract the inquiry content, "What are your business days?".

[0521] 5. Generating queries for artificial intelligence models

[0522] The server generates a prompt based on the analyzed query. An example of a prompt is, "Please answer the following question: What are your business days?" The server then sends this prompt to the artificial intelligence model.

[0523] 6. Answer generation using artificial intelligence models

[0524] The server uses a generative AI model (for example, a natural language processing model) to generate the best response based on the submitted prompt. In this example, the generative AI model generates the response "Weekday business days are Monday through Friday" and sends it back to the server.

[0525] 7. Server encoding of data

[0526] The server then re-encodes the retrieved answer into JSON format. Specifically, it uses the JSON.stringify method again to generate JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."}.

[0527] 8. Sending responses from the server to the terminal.

[0528] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message.

[0529] 9. Data reception and analysis on the terminal.

[0530] The terminal receives the HTTP response sent from the server and parses the data using the JSON.parse method. As a result of the parsing, it extracts the answer {"answer": "Weekday business days are Monday to Friday."}.

[0531] 10. Providing answers to users

[0532] The device displays the answer to the user based on the analysis results. The user can see the answer "Weekday business days are Monday through Friday" on the device screen.

[0533] This invention allows users to quickly and accurately obtain the necessary information through a series of simple operations, and enables companies and organizations to significantly improve the efficiency of handling inquiries.

[0534] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0535] Step 1:

[0536] The user enters inquiry data using a terminal. They enter "What are your business days?" into the input field and click the submit button. The entered data ("What are your business days?") becomes input data for the terminal.

[0537] Step 2:

[0538] The terminal retrieves the inquiry data entered by the user ("What are your business days?") and encodes it in JSON format. This generates JSON data in the format {"query": "What are your business days?"}. This data becomes the output data sent from the terminal to the server.

[0539] Step 3:

[0540] The device sends the generated JSON data to the server as an HTTP POST request. This request includes the header information Content-Type: application / json. The data is sent over the internet to a specific endpoint on the server.

[0541] Step 4:

[0542] The server receives an HTTP POST request sent from the terminal. It extracts JSON data ({"query": "What are your business days?"}) from the request body and parses the data using the JSON.parse method. As a result of the parsing, the query content ("What are your business days?") is extracted. This extracted content becomes the output data for the server.

[0543] Step 5:

[0544] The server generates a prompt based on the analyzed inquiry ("What are your business days?"). Specifically, it generates a prompt in the form of "Please answer the following question: What are your business days?". This prompt becomes the input data for the artificial intelligence model.

[0545] Step 6:

[0546] The server sends a prompt ("Please answer the following question: What are your business days?") to an artificial intelligence model (for example, a natural language processing model). The generative AI model generates the best possible answer based on the prompt. Specifically, the generative AI model outputs the answer "Our business days are Monday through Friday." This answer becomes the input data for the server.

[0547] Step 7:

[0548] The server re-encodes the response obtained from the generating AI model ("Business days on weekdays are Monday through Friday.") into JSON format. Specifically, JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."} is generated. This data becomes the output data sent to the terminal.

[0549] Step 8:

[0550] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message. The sent JSON data becomes the input data for the terminal.

[0551] Step 9:

[0552] The terminal receives the HTTP response sent from the server. It parses the data ({"answer": "Business days on weekdays are Monday through Friday."}) using the JSON.parse method. As a result of the parsing, the answer ("Business days on weekdays are Monday through Friday.") is extracted. This parsing result becomes the output data for the terminal.

[0553] Step 10:

[0554] The device displays the retrieved answer to the user. The user is shown the answer "Weekday business days are Monday through Friday." on the device screen. The user can confirm this answer.

[0555] (Application Example 1)

[0556] 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."

[0557] In modern brick-and-mortar stores, a problem exists where customers spend a lot of time searching for specific products or locations within the store, leading to increased inquiries to store staff and reduced operational efficiency. This problem is particularly pronounced in large stores and those carrying a wide variety of products, and it contributes to decreased customer satisfaction.

[0558] 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.

[0559] In this invention, the server includes means for collecting inquiry data entered by a user from a terminal; means for transmitting the collected inquiry data to the server; means for analyzing the received inquiry data, generating inquiries from an artificial intelligence model based on that data, and obtaining answers; means for transmitting the obtained answers from the server to the terminal; means for displaying the received answers to the user; and means for generating answers and providing guidance based on the user's inquiry regarding specific locations or product locations within a physical store. This enables quick and efficient responses to customer inquiries within the store, improving customer satisfaction and streamlining store operations.

[0560] A "device" refers to a device operated by a user, and includes smartphones, tablets, personal computers, and other similar devices.

[0561] A "user" refers to an individual or legal entity that makes an inquiry using the system.

[0562] "Inquiry data" refers to data that includes questions and requests entered by the user through their device and sent to the server.

[0563] A "server" is a computing system that analyzes received inquiry data, generates answers using artificial intelligence models, and then sends those answers to terminals.

[0564] "Means of collection" refers to the function of a terminal that acquires and stores inquiry data entered by the user.

[0565] "Means of transmission" refers to the function of a device or software that sends the collected query data to the server.

[0566] "Means of analysis" refers to the process by which a server analyzes the query data it receives and understands its content.

[0567] "Means for generating queries" refers to a function that makes appropriate queries to the artificial intelligence model based on data analyzed by the server.

[0568] "Means of obtaining answers" refers to the function that allows the server to receive answers generated from the artificial intelligence model.

[0569] "Means of display" refers to a function that displays the response sent from the server to the terminal in a format that is easy for the user to read.

[0570] An "artificial intelligence model" is an algorithm that generates appropriate answers based on user inquiries, utilizing past data and knowledge bases.

[0571] A "physical store" refers to a physical location for sales or service provision, where customers can directly purchase goods or services.

[0572] This invention is a system for providing information quickly and efficiently to users when they are searching for specific products or locations within a physical store. In this system, the user inputs inquiry data using a terminal, a server analyzes that data, generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[0573] System Configuration

[0574] 1. Inquiry input by the user

[0575] Users use their smartphones or other devices within the physical store to enter questions about specific products or locations. These devices have a dedicated application installed, and users input their inquiry data through its input fields.

[0576] 2. Data transmission from terminal to server

[0577] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. The terminal program automatically formats and sends the data.

[0578] 3. Server analysis of query data

[0579] The server parses the received query data in JSON format and extracts its contents. Based on the parsed data, it generates appropriate queries that meet the demand and passes them to the artificial intelligence model.

[0580] 4. Answer generation using artificial intelligence models

[0581] The server uses an artificial intelligence model (for example, a natural language processing model built with TensorFlow) to generate answers to incoming inquiries. The AI ​​model has the ability to generate the optimal answer based on past data and a knowledge base.

[0582] 5. Sending responses from the server to the terminal.

[0583] The generated response is re-encoded in JSON format and sent from the server to the terminal. The terminal receives this response data and presents it to the user.

[0584] Hardware and software to be used

[0585] Hardware:

[0586] Smartphones (iOS, Android)

[0587] software:

[0588] Python (Server application using Flask)

[0589] TensorFlow (for artificial intelligence models)

[0590] Specific example

[0591] For example, consider a scenario where a user enters the question "Where is the bread section?" into their device and clicks the submit button. The user's device sends this inquiry to the server, which analyzes the inquiry and queries an artificial intelligence model. The AI ​​model generates the answer "The bread section is in the third row of the food section." The server sends this answer to the user's device, which then displays the answer to the user.

[0592] Example of a prompt:

[0593] User input: "Where is the bread section?"

[0594] Prompt to the generating AI model: Generate the best answer to the user's question, "Where is the bread section?"

[0595] Thus, the system of the present invention improves customer service within stores and streamlines the handling of inquiries.

[0596] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0597] Step 1:

[0598] The user opens the application on their smartphone, enters the question in the input field, and presses the submit button.

[0599] Input: Inquiry data entered by the user (e.g., "Where is the bread section?")

[0600] Operation: The application retrieves input data and encodes it in JSON format.

[0601] Output: Encoded JSON data

[0602] Step 2:

[0603] The device sends JSON data to the server as an HTTP POST request.

[0604] Input: Encoded JSON data

[0605] Operation: The device configures an HTTP POST request and sends data to the specified URL on the server.

[0606] Output: HTTP POST request sent to the server

[0607] Step 3:

[0608] The server receives an HTTP request and parses the query data in JSON format.

[0609] Input: JSON data included in an HTTP POST request

[0610] Operation: The server analyzes the received data and extracts the query content (e.g., "Where is the bread section?").

[0611] Output: Analyzed query content

[0612] Step 4:

[0613] The server generates queries for the artificial intelligence model based on the analyzed data.

[0614] Input: Analyzed query content

[0615] Operation: The server passes the query content to the AI ​​model in an appropriate format (e.g., a prompt like "Where is the bread section?").

[0616] Output: Generated prompt message

[0617] Step 5:

[0618] The server uses an artificial intelligence model (e.g., TensorFlow) to generate answers based on the query.

[0619] Input: Generated prompt message

[0620] Operation: The artificial intelligence model generates an answer based on the prompt sentence (e.g., "The bread section is in the third row of the food section.").

[0621] Output: Generated answer

[0622] Step 6:

[0623] The server re-encodes the generated response into JSON format and sends it to the terminal.

[0624] Input: Generated answer

[0625] Operation: The server encodes the response in JSON format and sends it to the terminal as an HTTP response.

[0626] Output: Encoded JSON format response data

[0627] Step 7:

[0628] The device parses the received JSON data and displays the answer to the user.

[0629] Input: Response data in encoded JSON format

[0630] Operation: The terminal analyzes the received data and displays it in a user-friendly format (e.g., "The bread section is in the third row of the food section.").

[0631] Output: Answer displayed to the user

[0632] Through these steps, users can quickly obtain information about specific products or locations within a physical store.

[0633] 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.

[0634] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[0635] System Configuration

[0636] 1. Inquiry input by the user

[0637] Users use a device to enter specific questions or requests. This device includes PCs, smartphones, and tablets. The process begins when the user fills in the inquiry field and clicks the submit button.

[0638] 2. Data transmission from terminal to server

[0639] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. Standard network protocols are used for transmission.

[0640] 3. Server analysis of query data

[0641] The server receives the query data, converts it to the appropriate data format, and analyzes it. The analysis process also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the text data to identify the user's emotional state, such as anger, anxiety, or joy.

[0642] 4. Emotional analysis using an emotion engine

[0643] An emotion engine implemented within the server analyzes user emotions based on their inquiry data. The results of this analysis are then used in subsequent processing.

[0644] 5. Answer generation using artificial intelligence models

[0645] The server uses the analyzed data and the results of the emotion engine to generate a query for the artificial intelligence model. The AI ​​model generates an appropriate response based on the query and the emotional state. Because the response is output in an emotion-appropriate tone, the response is tailored to the user's emotions.

[0646] 6. Sending responses from the server to the terminal.

[0647] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal receives this response data and decodes it to present it to the user.

[0648] 7. Displaying responses via the device

[0649] The terminal analyzes the response data received from the server and displays it to the user. This allows the user to visually confirm the answer to the question.

[0650] Program processing

[0651] Question data collection

[0652] The user enters their question into the input field on the terminal and clicks the submit button. This prepares the inquiry data to be sent to the server in JSON format.

[0653] Receiving and analyzing query data on the server.

[0654] The server receives JSON data sent from the terminal and performs text analysis. Simultaneously, it also performs sentiment analysis to identify the user's emotional state.

[0655] Integration with the emotion engine

[0656] Text data is passed to an emotion engine to analyze the user's emotions. The results of the emotion analysis are then used in an artificial intelligence model.

[0657] Answer generation using artificial intelligence models

[0658] The server sends inquiry data, including sentiment analysis results, to an artificial intelligence model to generate an appropriate response based on the emotions.

[0659] Submit and display of responses

[0660] The server sends the generated response to the terminal, which then decodes and displays it to the user.

[0661] Specific example

[0662] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[0663] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[0664] The following describes the processing flow.

[0665] Step 1:

[0666] The user enters their inquiry into the input field on the device and clicks the submit button. This action retrieves the inquiry data on the device.

[0667] Step 2:

[0668] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data is sent as follows:

[0669] json

[0670] {

[0671] "query": "Why is my order delayed?"

[0672] }

[0673] Step 3:

[0674] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the query content (in this case, "Why is my order delayed?").

[0675] Step 4:

[0676] The server extracts the query content and passes it to the emotion engine to analyze the user's emotions. The emotion engine analyzes the text data and identifies emotional states such as anger and dissatisfaction.

[0677] Step 5:

[0678] The server retrieves the analysis results from the emotion engine. For example, the analysis results might identify the emotion as "anger."

[0679] Step 6:

[0680] The server sends the analyzed query content and the results of the emotion engine to the artificial intelligence model. Here, the server sends the following data:

[0681] json

[0682] {

[0683] "prompt": "User question: Why is my order delayed?\nEmotion: Anger\nAI answer:",

[0684] "max_tokens": 100

[0685] }

[0686] Step 7:

[0687] The artificial intelligence model receives data sent from the server and generates an appropriate response. In this case, the AI ​​model generates a response in a tone that takes the user's feelings into consideration, such as, "We apologize for the wait. We are currently checking the status of your order."

[0688] Step 8:

[0689] The server receives the response sent back from the artificial intelligence model. The received response might be text such as, "We apologize for the delay. We are currently checking the order status."

[0690] Step 9:

[0691] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will look like this:

[0692] json

[0693] {

[0694] "Answer": "We apologize for the delay. We are currently checking the status of your order."

[0695] }

[0696] Step 10:

[0697] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[0698] Step 11:

[0699] The terminal displays the extracted response to the user. This allows the user to visually confirm the response, "We apologize for the delay. We are currently checking the status of your order."

[0700] This series of steps ensures that users receive prompt, emotionally sensitive responses when they submit an inquiry.

[0701] (Example 2)

[0702] 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".

[0703] Modern inquiry systems are required to provide prompt, emotionally sensitive, and appropriate responses to user inquiries. However, conventional systems lack the ability to properly recognize user emotions, often providing mechanical and uniform answers. This makes it difficult to increase user satisfaction and trust. Therefore, there is a need for a system that can analyze user emotions and generate flexible responses accordingly.

[0704] 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.

[0705] In this invention, the server includes means for [analyzing received inquiry data as text and further analyzing the user's emotions using an emotion engine], [generating an appropriate response using an artificial intelligence model based on the analyzed data and the results of the emotion engine], and [encoding the generated response in JSON format and sending it to the terminal]. This makes it possible to [provide a quick and appropriate response that takes the user's emotions into consideration].

[0706] A "terminal" is a device that a user operates to input inquiry data and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[0707] "Inquiry data" refers to the content of questions and requests entered by the user into the device, and is usually information expressed in text format.

[0708] A "standard network protocol" refers to the technical standards used when sending and receiving data over the internet, and includes, for example, HTTP and HTTPS.

[0709] A "server" is a computer system that receives inquiry data entered by a user, performs text analysis and sentiment analysis, generates appropriate responses, and sends them to the terminal.

[0710] "Text analysis" is a method for analyzing received inquiry data and understanding its content, and it is performed using natural language processing technology.

[0711] An "emotion engine" is software or an algorithm that analyzes user inquiry data to identify the emotions contained in the text.

[0712] An "artificial intelligence model" is a system that uses machine learning techniques to generate appropriate answers based on inquiry data and analysis results.

[0713] "JSON format" is a lightweight, text-based data format for structuring and representing data, and it is an abbreviation for JavaScript Object Notation.

[0714] "Decoding" refers to the process of converting encoded data, such as JSON format, back to its original format, and is performed so that the device can display the data received from the server to the user.

[0715] "Emotion analysis results" refer to data indicating emotions identified by the emotion engine after analyzing user inquiry data.

[0716] "Visual display" refers to the device displaying the response data on the screen in a format that is easy for the user to understand.

[0717] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[0718] Users enter specific questions or requests using a device, which includes PCs, smartphones, and tablets. The user enters their inquiry into the input field and clicks the submit button to begin the process.

[0719] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request using a standard network protocol such as HTTPS.

[0720] The server receives the inquiry data and performs text analysis and sentiment analysis. Natural language processing techniques are used for text analysis to understand the content of the user's inquiry. A sentiment engine is used for sentiment analysis to identify the user's emotional state.

[0721] The server passes text data to the emotion engine, which analyzes the user's emotions. The results of this analysis are then used by the subsequent artificial intelligence model to generate responses. For example, the emotion engine might identify that the user is feeling dissatisfied or angry in response to the question, "Why is my order delayed?"

[0722] The server uses the analyzed data and the results of the sentiment engine to send a query to the artificial intelligence model. The generative AI model generates an appropriate response based on the query and the sentiment state. An example of a prompt is used: "Analyze the user's sentiment from the following text and generate a response appropriate to that sentiment. Input: 'Why is my order delayed?'" The model would generate a response such as, "We apologize for the delay. We are currently checking the status of your order."

[0723] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal decodes this data and displays it visually to the user. This allows the user to feel that their emotions are understood and to have a better support experience.

[0724] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[0725] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0726] Step 1:

[0727] The user enters a question into the input field on the device and clicks the submit button.

[0728] Specific action: The user types "Why is my order delayed?" and clicks the submit button.

[0729] Input: Text data entered by the user (question content).

[0730] Output: The entered text data is temporarily stored on the device.

[0731] Step 2:

[0732] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request.

[0733] Specific operation: The program on the terminal converts the query data into JSON format and sends an HTTP POST request to the specified server URL.

[0734] Input: Text data entered by the user.

[0735] Output: The encoded JSON data is sent to the server as an HTTP POST request.

[0736] Step 3:

[0737] The system extracts JSON data from HTTP POST requests received by the server and performs text analysis. It also analyzes user emotions using an emotion engine.

[0738] Specific operation: The server parses the JSON data from the request body and extracts the text portion. Then, it performs text analysis using natural language processing techniques and sentiment analysis using a sentiment engine.

[0739] Input: Encoded JSON data.

[0740] Output: Text analysis results and sentiment analysis results.

[0741] Step 4:

[0742] The server sends a query to an artificial intelligence model based on the text analysis results and sentiment analysis results, and generates an answer.

[0743] Specific operation: The server generates prompts for the generative AI model and inputs them along with the sentiment analysis results. For example, it might use the prompt: "Analyze the user's sentiment from the following text and generate an appropriate response. Input: 'Why is my order delayed?'" The generative AI model then generates an appropriate response.

[0744] Input: Text analysis results, sentiment analysis results, prompt text.

[0745] Output: Generated answer text.

[0746] Step 5:

[0747] The server encodes the generated response text into JSON format and sends it to the terminal as an HTTP response.

[0748] Specific operation: The server-side program converts the response text into JSON format and sends it back to the terminal as an HTTP response.

[0749] Input: Generated response text.

[0750] Output: Encoded JSON data is sent to the terminal as an HTTP response.

[0751] Step 6:

[0752] The device decodes JSON data from the HTTP response it receives and displays it visually to the user.

[0753] Specific operation: The program on the terminal extracts JSON data from the HTTP response body and decodes it back into its original text format. Then, it displays it on the screen. For example, it might display, "We apologize for the wait. We are currently checking your order status."

[0754] Input: Encoded JSON data.

[0755] Output: The response text that is visually displayed to the user.

[0756] (Application Example 2)

[0757] 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."

[0758] Traditional inquiry systems often provide mechanical responses without considering the user's emotions, leading to decreased user satisfaction. Furthermore, the lack of responses in an appropriate tone based on emotions made it difficult to address users' psychological states.

[0759] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0760] In this invention, the server includes means for analyzing received inquiry data, recognizing the user's emotions using an emotion analysis engine based on that data, generating inquiries for an artificial intelligence model, and obtaining an answer appropriate to the emotions; means for transmitting the obtained answer to a terminal; and means for displaying the received answer to the user. This makes it possible to provide answers that take the user's emotions into consideration and improve the user experience.

[0761] A "terminal" is a device used by a user for input, such as a smartphone, personal computer, or tablet.

[0762] "Inquiry data" refers to information about questions and requests that users input and send through their devices.

[0763] A "server" is a central data processing unit that analyzes inquiry data, generates responses, and transmits them.

[0764] A "sentiment analysis engine" is a software program that identifies emotions from user inquiry data and determines their emotional state.

[0765] An "artificial intelligence model" is an artificial intelligence algorithm that generates the optimal response for a user based on inquiry data and the results of an emotion analysis engine.

[0766] "Answer" refers to the information provided or the response content generated based on the user's inquiry data.

[0767] "Transmission" refers to the act of transferring data between different devices, such as terminals and servers.

[0768] "Receiving" refers to the act of a terminal or server acquiring data sent from another party.

[0769] "Display" refers to the act of outputting received information to the device screen so that the user can visually confirm it.

[0770] The system implementing this invention consists of a terminal, a server, an emotion analysis engine, an artificial intelligence model, and a user. The terminal is a device used by the user to input inquiry data, and includes smartphones, personal computers, tablets, and the like.

[0771] Overall system flow

[0772] 1. Inquiry input by the user

[0773] The user enters their question or request into the input field on the terminal and clicks the submit button.

[0774] 2. Data transmission from terminal to server

[0775] The entered query data is encoded in JSON format and sent to the server. The HTTP POST protocol is used for transmission.

[0776] 3. Server analysis of query data

[0777] The server analyzes the received query data and converts it into an appropriate format. This analysis incorporates a sentiment analysis engine that identifies the user's emotions from the text data.

[0778] 4. Emotion analysis using an emotion analysis engine

[0779] The emotion analysis engine on the server recognizes the user's emotions based on the query data. For example, it identifies emotional states such as anger, anxiety, and joy.

[0780] 5. Answer generation using artificial intelligence models

[0781] The server uses the analyzed data and the results of the sentiment analysis engine to generate appropriate responses using an artificial intelligence model. This allows for responses to be output in a tone appropriate to the emotion.

[0782] 6. Sending responses from the server to the terminal.

[0783] The generated response is then encoded again in JSON format and sent to the terminal.

[0784] 7. Displaying responses via the device

[0785] The terminal decodes the received response data and presents it to the user. This display allows the user to visually confirm the answer to the question.

[0786] Hardware and software to be used

[0787] Hardware:

[0788] Devices such as smartphones, personal computers, and tablets

[0789] Server as a central data processing unit

[0790] software:

[0791] Python: The entire programming language

[0792] requests: A library for making HTTP requests.

[0793] JSON: Used for encoding and decoding data.

[0794] SentimentEngine: A software engine used for sentiment analysis.

[0795] AIResponseGenerator: An artificial intelligence model that generates responses based on emotions.

[0796] Specific example

[0797] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[0798] Example of a prompt

[0799] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[0800] As described above, this invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take user emotions into consideration.

[0801] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0802] Step 1:

[0803] User-initiated inquiry input: The user enters a question or request into the terminal's input field and clicks the submit button. The input data is in text format and constitutes the inquiry data. Input is made from the user to the terminal, and the output is the inquiry data.

[0804] Step 2:

[0805] Data transmission from terminal to server: The terminal encodes the input query data into JSON format and sends it to the server as an HTTP POST request. The terminal uses HTTP as the transmission protocol. The input is query data (in text format), and the output is encoded JSON data.

[0806] Step 3:

[0807] Server reception and parsing of query data: The server receives JSON data sent from the terminal and decodes it to obtain query data in text format. This data contains the user's questions and requests. The server then parses this data. The input is encoded JSON data, and the output is query data in text format.

[0808] Step 4:

[0809] Emotional analysis by the emotion analysis engine: The emotion analysis engine on the server identifies the user's emotions based on the analyzed query data. For example, it identifies emotional states such as anger, anxiety, and joy. In this step, the input is query data in text format, and the output is the emotional state.

[0810] Step 5:

[0811] AI-powered response generation: The server uses the analyzed query data and the results of the sentiment analysis engine to provide prompts to the generating AI model, which then generates an appropriate response. The input is the query data and sentiment state, and the output is a response (in text format) corresponding to the sentiment.

[0812] Example of a prompt:

[0813] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[0814] Step 6:

[0815] Sending the response from the server to the terminal: The generated response is re-encoded in JSON format and sent to the terminal as an HTTP response. The input is the generated text-formatted response, and the output is encoded JSON data.

[0816] Step 7:

[0817] Receiving and displaying responses by the terminal: The terminal decodes the JSON data received from the server and obtains the generated response in text format. This response is then displayed on the screen for presentation to the user. The input is encoded JSON data, and the output is the text-formatted response displayed to the user.

[0818] By following these steps, users can receive prompt and appropriate responses to their inquiries, thereby improving the user experience.

[0819] 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.

[0820] 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.

[0821] 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.

[0822] [Third Embodiment]

[0823] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0824] 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.

[0825] 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).

[0826] 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.

[0827] 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.

[0828] 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).

[0829] 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.

[0830] 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.

[0831] 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.

[0832] 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.

[0833] 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.

[0834] 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".

[0835] This invention provides a system that provides quick and efficient answers to user inquiries. In this system, the user inputs inquiry data through a terminal and sends it to a server, the server generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[0836] System Configuration

[0837] 1. Inquiry input by the user

[0838] Users use individual devices to enter specific questions or requests. These devices include personal computers, smartphones, and tablets. Input is typically done through web forms or application input fields.

[0839] 2. Data transmission from terminal to server

[0840] The terminal has the functionality to send user-entered inquiry data to the server. HTTP POST requests are commonly used for data transmission. The terminal encodes this request in JSON format and sends it to the server.

[0841] 3. Server analysis of query data

[0842] The server has the function of receiving and appropriately analyzing the inquiry data. Specifically, it analyzes the content of the inquiry and identifies what kind of answer is needed. Based on the analysis results, the server generates an inquiry for the artificial intelligence model.

[0843] 4. Answer generation using artificial intelligence models

[0844] The server uses an artificial intelligence model (e.g., a natural language processing model) to generate appropriate answers to user inquiries. This AI model has the ability to generate optimal answers based on past data and a knowledge base.

[0845] 5. Sending responses from the server to the terminal.

[0846] The server-generated response is re-encoded in JSON format and sent to the terminal. The terminal receives this response data and displays it for the user.

[0847] Program processing

[0848] Question data collection

[0849] The user enters a question into the terminal's input field and clicks the submit button. The terminal retrieves the entered data and prepares it for transmission to the server in JSON format. The terminal then sends the data to the server as an HTTP POST request.

[0850] Receiving and analyzing query data on the server.

[0851] The server receives data in JSON format sent from the terminal. After receiving the data, the server analyzes the JSON data and extracts the question. The server then passes this question to an artificial intelligence model to generate an appropriate answer.

[0852] Linking text with artificial intelligence models

[0853] The server calls an AI API and queries the AI ​​model with the extracted question content. The AI ​​model generates an answer based on the received question and returns the result to the server.

[0854] Providing answers to users

[0855] The server receives the response from the artificial intelligence model and encodes it again in JSON format. The server sends this data to the terminal, which parses the received data and displays the response to the user.

[0856] Specific example

[0857] For example, consider a scenario where a user enters the question "What are your business hours?" into a terminal and clicks the send button. The terminal sends this question to a server, which analyzes the question and queries an artificial intelligence model. The AI ​​model generates the answer, "Our weekday business hours are from 9 AM to 6 PM," and returns it to the server. The server sends this answer to the terminal, which then displays the answer to the user. The user can quickly obtain the necessary information without having to make a phone call.

[0858] Thus, the present invention significantly improves user convenience and streamlines the handling of inquiries by companies and organizations.

[0859] The following describes the processing flow.

[0860] Step 1:

[0861] The user enters their inquiry into the input field on the device and clicks the submit button. This retrieves the inquiry data on the device.

[0862] Step 2:

[0863] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data structure will be as follows:

[0864] json

[0865] {

[0866] "query": "What are your opening hours?"

[0867] }

[0868] Step 3:

[0869] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the inquiry content (in this case, "What are your business hours?").

[0870] Step 4:

[0871] The server extracts the query content and analyzes it using natural language processing. This analysis includes preprocessing to understand the intent of the question. The analyzed data is then used to query the AI ​​model.

[0872] Step 5:

[0873] The server sends the analyzed query to the artificial intelligence model. Here, it calls the AI ​​model's API and sends data like the following:

[0874] json

[0875] {

[0876] "prompt": "User question: What are your opening hours?\nAI's answer:",

[0877] "max_tokens": 100

[0878] }

[0879] Step 6:

[0880] The artificial intelligence model receives data sent from the server and generates an appropriate response. This process is carried out by an algorithm within the model. The generated response is then sent back to the server.

[0881] Step 7:

[0882] The server receives the response sent back from the artificial intelligence model. The received response is, for example, the text: "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0883] Step 8:

[0884] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will be in the following format:

[0885] json

[0886] {

[0887] "Answer": "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0888] }

[0889] Step 9:

[0890] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[0891] Step 10:

[0892] The device displays the extracted answer to the user. This allows the user to visually confirm the answer, "Our weekday business hours are from 9:00 AM to 6:00 PM."

[0893] This series of steps allows users to quickly obtain the necessary information through their device without having to make a phone call.

[0894] (Example 1)

[0895] 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."

[0896] Conventional inquiry handling systems struggle to provide quick and accurate answers to user inquiries, and in situations where efficient handling of a large volume of inquiries is required, the response time was often excessive. Furthermore, the lack of artificial intelligence technology to properly understand the content of inquiries and generate optimal answers based on that understanding could lead to decreased user satisfaction.

[0897] 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.

[0898] In this invention, the server includes means for parsing the received JSON-formatted query data, generating a prompt statement, querying an artificial intelligence model, and obtaining a response; means for re-encoding the generated response into JSON format and sending it to the terminal as an HTTP response; and means for the terminal to parsing the received response and displaying it to the user. This makes it possible to provide quick and accurate answers to user inquiries.

[0899] A "user" is the entity that accesses the system and makes inquiries, and refers to the person who uses a terminal to input information.

[0900] A "device" refers to a hardware device used by a user, such as a personal computer, smartphone, or tablet.

[0901] "Inquiry data" refers to information about questions and requests that users input using their devices and send to the system.

[0902] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a data format used to exchange inquiry data and response data between systems.

[0903] An "HTTP POST request" refers to a type of HTTP request that uses the HTTP protocol to send data from a client terminal to a server.

[0904] A "server" refers to a hardware and software system that receives, analyzes, and generates responses to inquiry data sent from terminals.

[0905] "Analysis" refers to the process by which a server interprets the content of received query data and performs appropriate processing in order to understand it.

[0906] A "prompt message" refers to a sentence generated for input into an artificial intelligence model, specifically text that clearly conveys the content of the inquiry.

[0907] An "artificial intelligence model" refers to a machine learning model that understands problems and generates answers in a way similar to a human.

[0908] "Answer" refers to an appropriate response to a user's inquiry, generated based on the analysis results performed by an artificial intelligence model.

[0909] An "HTTP response" refers to the response data sent from a server to a client terminal based on the HTTP protocol.

[0910] "Display" refers to the process by which the device presents the acquired response to the user.

[0911] This invention provides a system that provides quick and efficient answers to user inquiries. This system transmits inquiry data entered by the user via a terminal to a server, the server generates an answer using a generated AI model, and then provides that answer back to the user. Specific embodiments of this system are described below.

[0912] 1. User inquiry input

[0913] Users access the system interface using devices such as PCs, smartphones, and tablets. For example, they access a specified URL using a web browser and enter a question such as "What are your business days?" into an input form. Then they click the submit button.

[0914] 2. Preparing the terminal to send data

[0915] The terminal retrieves the question data entered by the user and encodes it in JSON format. Specifically, it uses the JSON.stringify method internally to generate JSON data in the format {"query": "What are your business days?"}.

[0916] 3. Sending data from the terminal to the server

[0917] The device sends the generated JSON data to the server as an HTTP POST request. The request includes the header information Content-Type: application / json.

[0918] 4. Receiving and analyzing data on the server

[0919] The server receives the HTTP POST request sent from the terminal and extracts JSON data from the request body. The JSON.parse method is used to parse the retrieved JSON data and extract the inquiry content, "What are your business days?".

[0920] 5. Generating queries for artificial intelligence models

[0921] The server generates a prompt based on the analyzed query. An example of a prompt is, "Please answer the following question: What are your business days?" The server then sends this prompt to the artificial intelligence model.

[0922] 6. Answer generation using artificial intelligence models

[0923] The server uses a generative AI model (for example, a natural language processing model) to generate the best response based on the submitted prompt. In this example, the generative AI model generates the response "Weekday business days are Monday through Friday" and sends it back to the server.

[0924] 7. Server encoding of data

[0925] The server then re-encodes the retrieved answer into JSON format. Specifically, it uses the JSON.stringify method again to generate JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."}.

[0926] 8. Sending responses from the server to the terminal.

[0927] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message.

[0928] 9. Data reception and analysis on the terminal.

[0929] The terminal receives the HTTP response sent from the server and parses the data using the JSON.parse method. As a result of the parsing, it extracts the answer {"answer": "Weekday business days are Monday to Friday."}.

[0930] 10. Providing answers to users

[0931] The device displays the answer to the user based on the analysis results. The user can see the answer "Weekday business days are Monday through Friday" on the device screen.

[0932] This invention allows users to quickly and accurately obtain the necessary information through a series of simple operations, and enables companies and organizations to significantly improve the efficiency of handling inquiries.

[0933] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0934] Step 1:

[0935] The user enters inquiry data using a terminal. They enter "What are your business days?" into the input field and click the submit button. The entered data ("What are your business days?") becomes input data for the terminal.

[0936] Step 2:

[0937] The terminal retrieves the inquiry data entered by the user ("What are your business days?") and encodes it in JSON format. This generates JSON data in the format {"query": "What are your business days?"}. This data becomes the output data sent from the terminal to the server.

[0938] Step 3:

[0939] The device sends the generated JSON data to the server as an HTTP POST request. This request includes the header information Content-Type: application / json. The data is sent over the internet to a specific endpoint on the server.

[0940] Step 4:

[0941] The server receives an HTTP POST request sent from the terminal. It extracts JSON data ({"query": "What are your business days?"}) from the request body and parses the data using the JSON.parse method. As a result of the parsing, the query content ("What are your business days?") is extracted. This extracted content becomes the output data for the server.

[0942] Step 5:

[0943] The server generates a prompt based on the analyzed inquiry ("What are your business days?"). Specifically, it generates a prompt in the form of "Please answer the following question: What are your business days?". This prompt becomes the input data for the artificial intelligence model.

[0944] Step 6:

[0945] The server sends a prompt ("Please answer the following question: What are your business days?") to an artificial intelligence model (for example, a natural language processing model). The generative AI model generates the best possible answer based on the prompt. Specifically, the generative AI model outputs the answer "Our business days are Monday through Friday." This answer becomes the input data for the server.

[0946] Step 7:

[0947] The server re-encodes the response obtained from the generating AI model ("Business days on weekdays are Monday through Friday.") into JSON format. Specifically, JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."} is generated. This data becomes the output data sent to the terminal.

[0948] Step 8:

[0949] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message. The sent JSON data becomes the input data for the terminal.

[0950] Step 9:

[0951] The terminal receives the HTTP response sent from the server. It parses the data ({"answer": "Business days on weekdays are Monday through Friday."}) using the JSON.parse method. As a result of the parsing, the answer ("Business days on weekdays are Monday through Friday.") is extracted. This parsing result becomes the output data for the terminal.

[0952] Step 10:

[0953] The device displays the retrieved answer to the user. The user is shown the answer "Weekday business days are Monday through Friday." on the device screen. The user can confirm this answer.

[0954] (Application Example 1)

[0955] 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."

[0956] In modern brick-and-mortar stores, a problem exists where customers spend a lot of time searching for specific products or locations within the store, leading to increased inquiries to store staff and reduced operational efficiency. This problem is particularly pronounced in large stores and those carrying a wide variety of products, and it contributes to decreased customer satisfaction.

[0957] 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.

[0958] In this invention, the server includes means for collecting inquiry data entered by a user from a terminal; means for transmitting the collected inquiry data to the server; means for analyzing the received inquiry data, generating inquiries from an artificial intelligence model based on that data, and obtaining answers; means for transmitting the obtained answers from the server to the terminal; means for displaying the received answers to the user; and means for generating answers and providing guidance based on the user's inquiry regarding specific locations or product locations within a physical store. This enables quick and efficient responses to customer inquiries within the store, improving customer satisfaction and streamlining store operations.

[0959] A "device" refers to a device operated by a user, and includes smartphones, tablets, personal computers, and other similar devices.

[0960] A "user" refers to an individual or legal entity that makes an inquiry using the system.

[0961] "Inquiry data" refers to data that includes questions and requests entered by the user through their device and sent to the server.

[0962] A "server" is a computing system that analyzes received inquiry data, generates answers using artificial intelligence models, and then sends those answers to terminals.

[0963] "Means of collection" refers to the function of a terminal that acquires and stores inquiry data entered by the user.

[0964] "Means of transmission" refers to the function of a device or software that sends the collected query data to the server.

[0965] "Means of analysis" refers to the process by which a server analyzes the query data it receives and understands its content.

[0966] "Means for generating queries" refers to a function that makes appropriate queries to the artificial intelligence model based on data analyzed by the server.

[0967] "Means of obtaining answers" refers to the function that allows the server to receive answers generated from the artificial intelligence model.

[0968] "Means of display" refers to a function that displays the response sent from the server to the terminal in a format that is easy for the user to read.

[0969] An "artificial intelligence model" is an algorithm that generates appropriate answers based on user inquiries, utilizing past data and knowledge bases.

[0970] A "physical store" refers to a physical location for sales or service provision, where customers can directly purchase goods or services.

[0971] This invention is a system for providing information quickly and efficiently to users when they are searching for specific products or locations within a physical store. In this system, the user inputs inquiry data using a terminal, a server analyzes that data, generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[0972] System Configuration

[0973] 1. Inquiry input by the user

[0974] Users use their smartphones or other devices within the physical store to enter questions about specific products or locations. These devices have a dedicated application installed, and users input their inquiry data through its input fields.

[0975] 2. Data transmission from terminal to server

[0976] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. The terminal program automatically formats and sends the data.

[0977] 3. Server analysis of query data

[0978] The server parses the received query data in JSON format and extracts its contents. Based on the parsed data, it generates appropriate queries that meet the demand and passes them to the artificial intelligence model.

[0979] 4. Answer generation using artificial intelligence models

[0980] The server uses an artificial intelligence model (for example, a natural language processing model built with TensorFlow) to generate answers to incoming inquiries. The AI ​​model has the ability to generate the optimal answer based on past data and a knowledge base.

[0981] 5. Sending responses from the server to the terminal.

[0982] The generated response is re-encoded in JSON format and sent from the server to the terminal. The terminal receives this response data and presents it to the user.

[0983] Hardware and software to be used

[0984] Hardware:

[0985] Smartphones (iOS, Android)

[0986] software:

[0987] Python (Server application using Flask)

[0988] TensorFlow (for artificial intelligence models)

[0989] Specific example

[0990] For example, consider a scenario where a user enters the question "Where is the bread section?" into their device and clicks the submit button. The user's device sends this inquiry to the server, which analyzes the inquiry and queries an artificial intelligence model. The AI ​​model generates the answer "The bread section is in the third row of the food section." The server sends this answer to the user's device, which then displays the answer to the user.

[0991] Example of a prompt:

[0992] User input: "Where is the bread section?"

[0993] Prompt to the generating AI model: Generate the best answer to the user's question, "Where is the bread section?"

[0994] Thus, the system of the present invention improves customer service within stores and streamlines the handling of inquiries.

[0995] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0996] Step 1:

[0997] The user opens the application on their smartphone, enters the question in the input field, and presses the submit button.

[0998] Input: Inquiry data entered by the user (e.g., "Where is the bread section?")

[0999] Operation: The application retrieves input data and encodes it in JSON format.

[1000] Output: Encoded JSON data

[1001] Step 2:

[1002] The device sends JSON data to the server as an HTTP POST request.

[1003] Input: Encoded JSON data

[1004] Operation: The device configures an HTTP POST request and sends data to the specified URL on the server.

[1005] Output: HTTP POST request sent to the server

[1006] Step 3:

[1007] The server receives an HTTP request and parses the query data in JSON format.

[1008] Input: JSON data included in an HTTP POST request

[1009] Operation: The server analyzes the received data and extracts the query content (e.g., "Where is the bread section?").

[1010] Output: Analyzed query content

[1011] Step 4:

[1012] The server generates queries for the artificial intelligence model based on the analyzed data.

[1013] Input: Analyzed query content

[1014] Operation: The server passes the query content to the AI ​​model in an appropriate format (e.g., a prompt like "Where is the bread section?").

[1015] Output: Generated prompt message

[1016] Step 5:

[1017] The server uses an artificial intelligence model (e.g., TensorFlow) to generate answers based on the query.

[1018] Input: Generated prompt message

[1019] Operation: The artificial intelligence model generates an answer based on the prompt sentence (e.g., "The bread section is in the third row of the food section.").

[1020] Output: Generated answer

[1021] Step 6:

[1022] The server re-encodes the generated response into JSON format and sends it to the terminal.

[1023] Input: Generated answer

[1024] Operation: The server encodes the response in JSON format and sends it to the terminal as an HTTP response.

[1025] Output: Encoded JSON format response data

[1026] Step 7:

[1027] The device parses the received JSON data and displays the answer to the user.

[1028] Input: Response data in encoded JSON format

[1029] Operation: The terminal analyzes the received data and displays it in a user-friendly format (e.g., "The bread section is in the third row of the food section.").

[1030] Output: Answer displayed to the user

[1031] Through these steps, users can quickly obtain information about specific products or locations within a physical store.

[1032] 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.

[1033] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[1034] System Configuration

[1035] 1. Inquiry input by the user

[1036] Users use a device to enter specific questions or requests. This device includes PCs, smartphones, and tablets. The process begins when the user fills in the inquiry field and clicks the submit button.

[1037] 2. Data transmission from terminal to server

[1038] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. Standard network protocols are used for transmission.

[1039] 3. Server analysis of query data

[1040] The server receives the query data, converts it to the appropriate data format, and analyzes it. The analysis process also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the text data to identify the user's emotional state, such as anger, anxiety, or joy.

[1041] 4. Emotional analysis using an emotion engine

[1042] An emotion engine implemented within the server analyzes user emotions based on their inquiry data. The results of this analysis are then used in subsequent processing.

[1043] 5. Answer generation using artificial intelligence models

[1044] The server uses the analyzed data and the results of the emotion engine to generate a query for the artificial intelligence model. The AI ​​model generates an appropriate response based on the query and the emotional state. Because the response is output in an emotion-appropriate tone, the response is tailored to the user's emotions.

[1045] 6. Sending responses from the server to the terminal.

[1046] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal receives this response data and decodes it to present it to the user.

[1047] 7. Displaying responses via the device

[1048] The terminal analyzes the response data received from the server and displays it to the user. This allows the user to visually confirm the answer to the question.

[1049] Program processing

[1050] Question data collection

[1051] The user enters their question into the input field on the terminal and clicks the submit button. This prepares the inquiry data to be sent to the server in JSON format.

[1052] Receiving and analyzing query data on the server.

[1053] The server receives JSON data sent from the terminal and performs text analysis. Simultaneously, it also performs sentiment analysis to identify the user's emotional state.

[1054] Integration with the emotion engine

[1055] Text data is passed to an emotion engine to analyze the user's emotions. The results of the emotion analysis are then used in an artificial intelligence model.

[1056] Answer generation using artificial intelligence models

[1057] The server sends inquiry data, including sentiment analysis results, to an artificial intelligence model to generate an appropriate response based on the emotions.

[1058] Submit and display of responses

[1059] The server sends the generated response to the terminal, which then decodes and displays it to the user.

[1060] Specific example

[1061] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[1062] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[1063] The following describes the processing flow.

[1064] Step 1:

[1065] The user enters their inquiry into the input field on the device and clicks the submit button. This action retrieves the inquiry data on the device.

[1066] Step 2:

[1067] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data is sent as follows:

[1068] json

[1069] {

[1070] "query": "Why is my order delayed?"

[1071] }

[1072] Step 3:

[1073] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the query content (in this case, "Why is my order delayed?").

[1074] Step 4:

[1075] The server extracts the query content and passes it to the emotion engine to analyze the user's emotions. The emotion engine analyzes the text data and identifies emotional states such as anger and dissatisfaction.

[1076] Step 5:

[1077] The server retrieves the analysis results from the emotion engine. For example, the analysis results might identify the emotion as "anger."

[1078] Step 6:

[1079] The server sends the analyzed query content and the results of the emotion engine to the artificial intelligence model. Here, the server sends the following data:

[1080] json

[1081] {

[1082] "prompt": "User question: Why is my order delayed?\nEmotion: Anger\nAI answer:",

[1083] "max_tokens": 100

[1084] }

[1085] Step 7:

[1086] The artificial intelligence model receives data sent from the server and generates an appropriate response. In this case, the AI ​​model generates a response in a tone that takes the user's feelings into consideration, such as, "We apologize for the wait. We are currently checking the status of your order."

[1087] Step 8:

[1088] The server receives the response sent back from the artificial intelligence model. The received response might be text such as, "We apologize for the delay. We are currently checking the order status."

[1089] Step 9:

[1090] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will look like this:

[1091] json

[1092] {

[1093] "Answer": "We apologize for the delay. We are currently checking the status of your order."

[1094] }

[1095] Step 10:

[1096] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[1097] Step 11:

[1098] The terminal displays the extracted response to the user. This allows the user to visually confirm the response, "We apologize for the delay. We are currently checking the status of your order."

[1099] This series of steps ensures that users receive prompt, emotionally sensitive responses when they submit an inquiry.

[1100] (Example 2)

[1101] 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."

[1102] Modern inquiry systems are required to provide prompt, emotionally sensitive, and appropriate responses to user inquiries. However, conventional systems lack the ability to properly recognize user emotions, often providing mechanical and uniform answers. This makes it difficult to increase user satisfaction and trust. Therefore, there is a need for a system that can analyze user emotions and generate flexible responses accordingly.

[1103] 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.

[1104] In this invention, the server includes means for [analyzing received inquiry data as text and further analyzing the user's emotions using an emotion engine], [generating an appropriate response using an artificial intelligence model based on the analyzed data and the results of the emotion engine], and [encoding the generated response in JSON format and sending it to the terminal]. This makes it possible to [provide a quick and appropriate response that takes the user's emotions into consideration].

[1105] A "terminal" is a device that a user operates to input inquiry data and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[1106] "Inquiry data" refers to the content of questions and requests entered by the user into the device, and is usually information expressed in text format.

[1107] A "standard network protocol" refers to the technical standards used when sending and receiving data over the internet, and includes, for example, HTTP and HTTPS.

[1108] A "server" is a computer system that receives inquiry data entered by a user, performs text analysis and sentiment analysis, generates appropriate responses, and sends them to the terminal.

[1109] "Text analysis" is a method for analyzing received inquiry data and understanding its content, and it is performed using natural language processing technology.

[1110] An "emotion engine" is software or an algorithm that analyzes user inquiry data to identify the emotions contained in the text.

[1111] An "artificial intelligence model" is a system that uses machine learning techniques to generate appropriate answers based on inquiry data and analysis results.

[1112] "JSON format" is a lightweight, text-based data format for structuring and representing data, and it is an abbreviation for JavaScript Object Notation.

[1113] "Decoding" refers to the process of converting encoded data, such as JSON format, back to its original format, and is performed so that the device can display the data received from the server to the user.

[1114] "Emotion analysis results" refer to data indicating emotions identified by the emotion engine after analyzing user inquiry data.

[1115] "Visual display" refers to the device displaying the response data on the screen in a format that is easy for the user to understand.

[1116] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[1117] Users enter specific questions or requests using a device, which includes PCs, smartphones, and tablets. The user enters their inquiry into the input field and clicks the submit button to begin the process.

[1118] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request using a standard network protocol such as HTTPS.

[1119] The server receives the inquiry data and performs text analysis and sentiment analysis. Natural language processing techniques are used for text analysis to understand the content of the user's inquiry. A sentiment engine is used for sentiment analysis to identify the user's emotional state.

[1120] The server passes text data to the emotion engine, which analyzes the user's emotions. The results of this analysis are then used by the subsequent artificial intelligence model to generate responses. For example, the emotion engine might identify that the user is feeling dissatisfied or angry in response to the question, "Why is my order delayed?"

[1121] The server uses the analyzed data and the results of the sentiment engine to send a query to the artificial intelligence model. The generative AI model generates an appropriate response based on the query and the sentiment state. An example of a prompt is used: "Analyze the user's sentiment from the following text and generate a response appropriate to that sentiment. Input: 'Why is my order delayed?'" The model would generate a response such as, "We apologize for the delay. We are currently checking the status of your order."

[1122] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal decodes this data and displays it visually to the user. This allows the user to feel that their emotions are understood and to have a better support experience.

[1123] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[1124] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1125] Step 1:

[1126] The user enters a question into the input field on the device and clicks the submit button.

[1127] Specific action: The user types "Why is my order delayed?" and clicks the submit button.

[1128] Input: Text data entered by the user (question content).

[1129] Output: The entered text data is temporarily stored on the device.

[1130] Step 2:

[1131] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request.

[1132] Specific operation: The program on the terminal converts the query data into JSON format and sends an HTTP POST request to the specified server URL.

[1133] Input: Text data entered by the user.

[1134] Output: The encoded JSON data is sent to the server as an HTTP POST request.

[1135] Step 3:

[1136] The system extracts JSON data from HTTP POST requests received by the server and performs text analysis. It also analyzes user emotions using an emotion engine.

[1137] Specific operation: The server parses the JSON data from the request body and extracts the text portion. Then, it performs text analysis using natural language processing techniques and sentiment analysis using a sentiment engine.

[1138] Input: Encoded JSON data.

[1139] Output: Text analysis results and sentiment analysis results.

[1140] Step 4:

[1141] The server sends a query to an artificial intelligence model based on the text analysis results and sentiment analysis results, and generates an answer.

[1142] Specific operation: The server generates prompts for the generative AI model and inputs them along with the sentiment analysis results. For example, it might use the prompt: "Analyze the user's sentiment from the following text and generate an appropriate response. Input: 'Why is my order delayed?'" The generative AI model then generates an appropriate response.

[1143] Input: Text analysis results, sentiment analysis results, prompt text.

[1144] Output: Generated answer text.

[1145] Step 5:

[1146] The server encodes the generated response text into JSON format and sends it to the terminal as an HTTP response.

[1147] Specific operation: The server-side program converts the response text into JSON format and sends it back to the terminal as an HTTP response.

[1148] Input: Generated response text.

[1149] Output: Encoded JSON data is sent to the terminal as an HTTP response.

[1150] Step 6:

[1151] The device decodes JSON data from the HTTP response it receives and displays it visually to the user.

[1152] Specific operation: The program on the terminal extracts JSON data from the HTTP response body and decodes it back into its original text format. Then, it displays it on the screen. For example, it might display, "We apologize for the wait. We are currently checking your order status."

[1153] Input: Encoded JSON data.

[1154] Output: The response text that is visually displayed to the user.

[1155] (Application Example 2)

[1156] 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."

[1157] Traditional inquiry systems often provide mechanical responses without considering the user's emotions, leading to decreased user satisfaction. Furthermore, the lack of responses in an appropriate tone based on emotions made it difficult to address users' psychological states.

[1158] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1159] In this invention, the server includes means for analyzing received inquiry data, recognizing the user's emotions using an emotion analysis engine based on that data, generating inquiries for an artificial intelligence model, and obtaining an answer appropriate to the emotions; means for transmitting the obtained answer to a terminal; and means for displaying the received answer to the user. This makes it possible to provide answers that take the user's emotions into consideration and improve the user experience.

[1160] A "terminal" is a device used by a user for input, such as a smartphone, personal computer, or tablet.

[1161] "Inquiry data" refers to information about questions and requests that users input and send through their devices.

[1162] A "server" is a central data processing unit that analyzes inquiry data, generates responses, and transmits them.

[1163] A "sentiment analysis engine" is a software program that identifies emotions from user inquiry data and determines their emotional state.

[1164] An "artificial intelligence model" is an artificial intelligence algorithm that generates the optimal response for a user based on inquiry data and the results of an emotion analysis engine.

[1165] "Answer" refers to the information provided or the response content generated based on the user's inquiry data.

[1166] "Transmission" refers to the act of transferring data between different devices, such as terminals and servers.

[1167] "Receiving" refers to the act of a terminal or server acquiring data sent from another party.

[1168] "Display" refers to the act of outputting received information to the device screen so that the user can visually confirm it.

[1169] The system implementing this invention consists of a terminal, a server, an emotion analysis engine, an artificial intelligence model, and a user. The terminal is a device used by the user to input inquiry data, and includes smartphones, personal computers, tablets, and the like.

[1170] Overall system flow

[1171] 1. Inquiry input by the user

[1172] The user enters their question or request into the input field on the terminal and clicks the submit button.

[1173] 2. Data transmission from terminal to server

[1174] The entered query data is encoded in JSON format and sent to the server. The HTTP POST protocol is used for transmission.

[1175] 3. Server analysis of query data

[1176] The server analyzes the received query data and converts it into an appropriate format. This analysis incorporates a sentiment analysis engine that identifies the user's emotions from the text data.

[1177] 4. Emotion analysis using an emotion analysis engine

[1178] The emotion analysis engine on the server recognizes the user's emotions based on the query data. For example, it identifies emotional states such as anger, anxiety, and joy.

[1179] 5. Answer generation using artificial intelligence models

[1180] The server uses the analyzed data and the results of the sentiment analysis engine to generate appropriate responses using an artificial intelligence model. This allows for responses to be output in a tone appropriate to the emotion.

[1181] 6. Sending responses from the server to the terminal.

[1182] The generated response is then encoded again in JSON format and sent to the terminal.

[1183] 7. Displaying responses via the device

[1184] The terminal decodes the received response data and presents it to the user. This display allows the user to visually confirm the answer to the question.

[1185] Hardware and software to be used

[1186] Hardware:

[1187] Devices such as smartphones, personal computers, and tablets

[1188] Server as a central data processing unit

[1189] software:

[1190] Python: The entire programming language

[1191] requests: A library for making HTTP requests.

[1192] JSON: Used for encoding and decoding data.

[1193] SentimentEngine: A software engine used for sentiment analysis.

[1194] AIResponseGenerator: An artificial intelligence model that generates responses based on emotions.

[1195] Specific example

[1196] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[1197] Example of a prompt

[1198] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[1199] As described above, this invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take user emotions into consideration.

[1200] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1201] Step 1:

[1202] User-initiated inquiry input: The user enters a question or request into the terminal's input field and clicks the submit button. The input data is in text format and constitutes the inquiry data. Input is made from the user to the terminal, and the output is the inquiry data.

[1203] Step 2:

[1204] Data transmission from terminal to server: The terminal encodes the input query data into JSON format and sends it to the server as an HTTP POST request. The terminal uses HTTP as the transmission protocol. The input is query data (in text format), and the output is encoded JSON data.

[1205] Step 3:

[1206] Server reception and parsing of query data: The server receives JSON data sent from the terminal and decodes it to obtain query data in text format. This data contains the user's questions and requests. The server then parses this data. The input is encoded JSON data, and the output is query data in text format.

[1207] Step 4:

[1208] Emotional analysis by the emotion analysis engine: The emotion analysis engine on the server identifies the user's emotions based on the analyzed query data. For example, it identifies emotional states such as anger, anxiety, and joy. In this step, the input is query data in text format, and the output is the emotional state.

[1209] Step 5:

[1210] AI-powered response generation: The server uses the analyzed query data and the results of the sentiment analysis engine to provide prompts to the generating AI model, which then generates an appropriate response. The input is the query data and sentiment state, and the output is a response (in text format) corresponding to the sentiment.

[1211] Example of a prompt:

[1212] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[1213] Step 6:

[1214] Sending the response from the server to the terminal: The generated response is re-encoded in JSON format and sent to the terminal as an HTTP response. The input is the generated text-formatted response, and the output is encoded JSON data.

[1215] Step 7:

[1216] Receiving and displaying responses by the terminal: The terminal decodes the JSON data received from the server and obtains the generated response in text format. This response is then displayed on the screen for presentation to the user. The input is encoded JSON data, and the output is the text-formatted response displayed to the user.

[1217] By following these steps, users can receive prompt and appropriate responses to their inquiries, thereby improving the user experience.

[1218] 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.

[1219] 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.

[1220] 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.

[1221] [Fourth Embodiment]

[1222] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1223] 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.

[1224] 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).

[1225] 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.

[1226] 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.

[1227] 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).

[1228] 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.

[1229] 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.

[1230] 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.

[1231] 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.

[1232] 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.

[1233] 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.

[1234] 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".

[1235] This invention provides a system that provides quick and efficient answers to user inquiries. In this system, the user inputs inquiry data through a terminal and sends it to a server, the server generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[1236] System Configuration

[1237] 1. Inquiry input by the user

[1238] Users use individual devices to enter specific questions or requests. These devices include personal computers, smartphones, and tablets. Input is typically done through web forms or application input fields.

[1239] 2. Data transmission from terminal to server

[1240] The terminal has the functionality to send user-entered inquiry data to the server. HTTP POST requests are commonly used for data transmission. The terminal encodes this request in JSON format and sends it to the server.

[1241] 3. Server analysis of query data

[1242] The server has the function of receiving and appropriately analyzing the inquiry data. Specifically, it analyzes the content of the inquiry and identifies what kind of answer is needed. Based on the analysis results, the server generates an inquiry for the artificial intelligence model.

[1243] 4. Answer generation using artificial intelligence models

[1244] The server uses an artificial intelligence model (e.g., a natural language processing model) to generate appropriate answers to user inquiries. This AI model has the ability to generate optimal answers based on past data and a knowledge base.

[1245] 5. Sending responses from the server to the terminal.

[1246] The server-generated response is re-encoded in JSON format and sent to the terminal. The terminal receives this response data and displays it for the user.

[1247] Program processing

[1248] Question data collection

[1249] The user enters a question into the terminal's input field and clicks the submit button. The terminal retrieves the entered data and prepares it for transmission to the server in JSON format. The terminal then sends the data to the server as an HTTP POST request.

[1250] Receiving and analyzing query data on the server.

[1251] The server receives data in JSON format sent from the terminal. After receiving the data, the server analyzes the JSON data and extracts the question. The server then passes this question to an artificial intelligence model to generate an appropriate answer.

[1252] Linking text with artificial intelligence models

[1253] The server calls an AI API and queries the AI ​​model with the extracted question content. The AI ​​model generates an answer based on the received question and returns the result to the server.

[1254] Providing answers to users

[1255] The server receives the response from the artificial intelligence model and encodes it again in JSON format. The server sends this data to the terminal, which parses the received data and displays the response to the user.

[1256] Specific example

[1257] For example, consider a scenario where a user enters the question "What are your business hours?" into a terminal and clicks the send button. The terminal sends this question to a server, which analyzes the question and queries an artificial intelligence model. The AI ​​model generates the answer, "Our weekday business hours are from 9 AM to 6 PM," and returns it to the server. The server sends this answer to the terminal, which then displays the answer to the user. The user can quickly obtain the necessary information without having to make a phone call.

[1258] Thus, the present invention significantly improves user convenience and streamlines the handling of inquiries by companies and organizations.

[1259] The following describes the processing flow.

[1260] Step 1:

[1261] The user enters their inquiry into the input field on the device and clicks the submit button. This retrieves the inquiry data on the device.

[1262] Step 2:

[1263] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data structure will be as follows:

[1264] json

[1265] {

[1266] "query": "What are your opening hours?"

[1267] }

[1268] Step 3:

[1269] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the inquiry content (in this case, "What are your business hours?").

[1270] Step 4:

[1271] The server extracts the query content and analyzes it using natural language processing. This analysis includes preprocessing to understand the intent of the question. The analyzed data is then used to query the AI ​​model.

[1272] Step 5:

[1273] The server sends the analyzed query to the artificial intelligence model. Here, it calls the AI ​​model's API and sends data like the following:

[1274] json

[1275] {

[1276] "prompt": "User question: What are your opening hours?\nAI's answer:",

[1277] "max_tokens": 100

[1278] }

[1279] Step 6:

[1280] The artificial intelligence model receives data sent from the server and generates an appropriate response. This process is carried out by an algorithm within the model. The generated response is then sent back to the server.

[1281] Step 7:

[1282] The server receives the response sent back from the artificial intelligence model. The received response is, for example, the text: "Our weekday business hours are from 9:00 AM to 6:00 PM."

[1283] Step 8:

[1284] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will be in the following format:

[1285] json

[1286] {

[1287] "Answer": "Our weekday business hours are from 9:00 AM to 6:00 PM."

[1288] }

[1289] Step 9:

[1290] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[1291] Step 10:

[1292] The device displays the extracted answer to the user. This allows the user to visually confirm the answer, "Our weekday business hours are from 9:00 AM to 6:00 PM."

[1293] This series of steps allows users to quickly obtain the necessary information through their device without having to make a phone call.

[1294] (Example 1)

[1295] 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".

[1296] Conventional inquiry handling systems struggle to provide quick and accurate answers to user inquiries, and in situations where efficient handling of a large volume of inquiries is required, the response time was often excessive. Furthermore, the lack of artificial intelligence technology to properly understand the content of inquiries and generate optimal answers based on that understanding could lead to decreased user satisfaction.

[1297] 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.

[1298] In this invention, the server includes means for parsing the received JSON-formatted query data, generating a prompt statement, querying an artificial intelligence model, and obtaining a response; means for re-encoding the generated response into JSON format and sending it to the terminal as an HTTP response; and means for the terminal to parsing the received response and displaying it to the user. This makes it possible to provide quick and accurate answers to user inquiries.

[1299] A "user" is the entity that accesses the system and makes inquiries, and refers to the person who uses a terminal to input information.

[1300] A "device" refers to a hardware device used by a user, such as a personal computer, smartphone, or tablet.

[1301] "Inquiry data" refers to information about questions and requests that users input using their devices and send to the system.

[1302] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a data format used to exchange inquiry data and response data between systems.

[1303] An "HTTP POST request" refers to a type of HTTP request that uses the HTTP protocol to send data from a client terminal to a server.

[1304] A "server" refers to a hardware and software system that receives, analyzes, and generates responses to inquiry data sent from terminals.

[1305] "Analysis" refers to the process by which a server interprets the content of received query data and performs appropriate processing in order to understand it.

[1306] A "prompt message" refers to a sentence generated for input into an artificial intelligence model, specifically text that clearly conveys the content of the inquiry.

[1307] An "artificial intelligence model" refers to a machine learning model that understands problems and generates answers in a way similar to a human.

[1308] "Answer" refers to an appropriate response to a user's inquiry, generated based on the analysis results performed by an artificial intelligence model.

[1309] An "HTTP response" refers to the response data sent from a server to a client terminal based on the HTTP protocol.

[1310] "Display" refers to the process by which the device presents the acquired response to the user.

[1311] This invention provides a system that provides quick and efficient answers to user inquiries. This system transmits inquiry data entered by the user via a terminal to a server, the server generates an answer using a generated AI model, and then provides that answer back to the user. Specific embodiments of this system are described below.

[1312] 1. User inquiry input

[1313] Users access the system interface using devices such as PCs, smartphones, and tablets. For example, they access a specified URL using a web browser and enter a question such as "What are your business days?" into an input form. Then they click the submit button.

[1314] 2. Preparing the terminal to send data

[1315] The terminal retrieves the question data entered by the user and encodes it in JSON format. Specifically, it uses the JSON.stringify method internally to generate JSON data in the format {"query": "What are your business days?"}.

[1316] 3. Sending data from the terminal to the server

[1317] The device sends the generated JSON data to the server as an HTTP POST request. The request includes the header information Content-Type: application / json.

[1318] 4. Receiving and analyzing data on the server

[1319] The server receives the HTTP POST request sent from the terminal and extracts JSON data from the request body. The JSON.parse method is used to parse the retrieved JSON data and extract the inquiry content, "What are your business days?".

[1320] 5. Generating queries for artificial intelligence models

[1321] The server generates a prompt based on the analyzed query. An example of a prompt is, "Please answer the following question: What are your business days?" The server then sends this prompt to the artificial intelligence model.

[1322] 6. Answer generation using artificial intelligence models

[1323] The server uses a generative AI model (for example, a natural language processing model) to generate the best response based on the submitted prompt. In this example, the generative AI model generates the response "Weekday business days are Monday through Friday" and sends it back to the server.

[1324] 7. Server encoding of data

[1325] The server then re-encodes the retrieved answer into JSON format. Specifically, it uses the JSON.stringify method again to generate JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."}.

[1326] 8. Sending responses from the server to the terminal.

[1327] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message.

[1328] 9. Data reception and analysis on the terminal.

[1329] The terminal receives the HTTP response sent from the server and parses the data using the JSON.parse method. As a result of the parsing, it extracts the answer {"answer": "Weekday business days are Monday to Friday."}.

[1330] 10. Providing answers to users

[1331] The device displays the answer to the user based on the analysis results. The user can see the answer "Weekday business days are Monday through Friday" on the device screen.

[1332] This invention allows users to quickly and accurately obtain the necessary information through a series of simple operations, and enables companies and organizations to significantly improve the efficiency of handling inquiries.

[1333] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1334] Step 1:

[1335] The user enters inquiry data using a terminal. They enter "What are your business days?" into the input field and click the submit button. The entered data ("What are your business days?") becomes input data for the terminal.

[1336] Step 2:

[1337] The terminal retrieves the inquiry data entered by the user ("What are your business days?") and encodes it in JSON format. This generates JSON data in the format {"query": "What are your business days?"}. This data becomes the output data sent from the terminal to the server.

[1338] Step 3:

[1339] The device sends the generated JSON data to the server as an HTTP POST request. This request includes the header information Content-Type: application / json. The data is sent over the internet to a specific endpoint on the server.

[1340] Step 4:

[1341] The server receives an HTTP POST request sent from the terminal. It extracts JSON data ({"query": "What are your business days?"}) from the request body and parses the data using the JSON.parse method. As a result of the parsing, the query content ("What are your business days?") is extracted. This extracted content becomes the output data for the server.

[1342] Step 5:

[1343] The server generates a prompt based on the analyzed inquiry ("What are your business days?"). Specifically, it generates a prompt in the form of "Please answer the following question: What are your business days?". This prompt becomes the input data for the artificial intelligence model.

[1344] Step 6:

[1345] The server sends a prompt ("Please answer the following question: What are your business days?") to an artificial intelligence model (for example, a natural language processing model). The generative AI model generates the best possible answer based on the prompt. Specifically, the generative AI model outputs the answer "Our business days are Monday through Friday." This answer becomes the input data for the server.

[1346] Step 7:

[1347] The server re-encodes the response obtained from the generating AI model ("Business days on weekdays are Monday through Friday.") into JSON format. Specifically, JSON data in the format {"answer": "Business days on weekdays are Monday through Friday."} is generated. This data becomes the output data sent to the terminal.

[1348] Step 8:

[1349] The server sends the generated JSON data to the terminal as an HTTP response. This uses an HTTP response message. The sent JSON data becomes the input data for the terminal.

[1350] Step 9:

[1351] The terminal receives the HTTP response sent from the server. It parses the data ({"answer": "Business days on weekdays are Monday through Friday."}) using the JSON.parse method. As a result of the parsing, the answer ("Business days on weekdays are Monday through Friday.") is extracted. This parsing result becomes the output data for the terminal.

[1352] Step 10:

[1353] The device displays the retrieved answer to the user. The user is shown the answer "Weekday business days are Monday through Friday." on the device screen. The user can confirm this answer.

[1354] (Application Example 1)

[1355] 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".

[1356] In modern brick-and-mortar stores, a problem exists where customers spend a lot of time searching for specific products or locations within the store, leading to increased inquiries to store staff and reduced operational efficiency. This problem is particularly pronounced in large stores and those carrying a wide variety of products, and it contributes to decreased customer satisfaction.

[1357] 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.

[1358] In this invention, the server includes means for collecting inquiry data entered by a user from a terminal; means for transmitting the collected inquiry data to the server; means for analyzing the received inquiry data, generating inquiries from an artificial intelligence model based on that data, and obtaining answers; means for transmitting the obtained answers from the server to the terminal; means for displaying the received answers to the user; and means for generating answers and providing guidance based on the user's inquiry regarding specific locations or product locations within a physical store. This enables quick and efficient responses to customer inquiries within the store, improving customer satisfaction and streamlining store operations.

[1359] A "device" refers to a device operated by a user, and includes smartphones, tablets, personal computers, and other similar devices.

[1360] A "user" refers to an individual or legal entity that makes an inquiry using the system.

[1361] "Inquiry data" refers to data that includes questions and requests entered by the user through their device and sent to the server.

[1362] A "server" is a computing system that analyzes received inquiry data, generates answers using artificial intelligence models, and then sends those answers to terminals.

[1363] "Means of collection" refers to the function of a terminal that acquires and stores inquiry data entered by the user.

[1364] "Means of transmission" refers to the function of a device or software that sends the collected query data to the server.

[1365] "Means of analysis" refers to the process by which a server analyzes the query data it receives and understands its content.

[1366] "Means for generating queries" refers to a function that makes appropriate queries to the artificial intelligence model based on data analyzed by the server.

[1367] "Means of obtaining answers" refers to the function that allows the server to receive answers generated from the artificial intelligence model.

[1368] "Means of display" refers to a function that displays the response sent from the server to the terminal in a format that is easy for the user to read.

[1369] An "artificial intelligence model" is an algorithm that generates appropriate answers based on user inquiries, utilizing past data and knowledge bases.

[1370] A "physical store" refers to a physical location for sales or service provision, where customers can directly purchase goods or services.

[1371] This invention is a system for providing information quickly and efficiently to users when they are searching for specific products or locations within a physical store. In this system, the user inputs inquiry data using a terminal, a server analyzes that data, generates an answer using an artificial intelligence model, and then provides that answer back to the user.

[1372] System Configuration

[1373] 1. Inquiry input by the user

[1374] Users use their smartphones or other devices within the physical store to enter questions about specific products or locations. These devices have a dedicated application installed, and users input their inquiry data through its input fields.

[1375] 2. Data transmission from terminal to server

[1376] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. The terminal program automatically formats and sends the data.

[1377] 3. Server analysis of query data

[1378] The server parses the received query data in JSON format and extracts its contents. Based on the parsed data, it generates appropriate queries that meet the demand and passes them to the artificial intelligence model.

[1379] 4. Answer generation using artificial intelligence models

[1380] The server uses an artificial intelligence model (for example, a natural language processing model built with TensorFlow) to generate answers to incoming inquiries. The AI ​​model has the ability to generate the optimal answer based on past data and a knowledge base.

[1381] 5. Sending responses from the server to the terminal.

[1382] The generated response is re-encoded in JSON format and sent from the server to the terminal. The terminal receives this response data and presents it to the user.

[1383] Hardware and software to be used

[1384] Hardware:

[1385] Smartphones (iOS, Android)

[1386] software:

[1387] Python (Server application using Flask)

[1388] TensorFlow (for artificial intelligence models)

[1389] Specific example

[1390] For example, consider a scenario where a user enters the question "Where is the bread section?" into their device and clicks the submit button. The user's device sends this inquiry to the server, which analyzes the inquiry and queries an artificial intelligence model. The AI ​​model generates the answer "The bread section is in the third row of the food section." The server sends this answer to the user's device, which then displays the answer to the user.

[1391] Example of a prompt:

[1392] User input: "Where is the bread section?"

[1393] Prompt to the generating AI model: Generate the best answer to the user's question, "Where is the bread section?"

[1394] Thus, the system of the present invention improves customer service within stores and streamlines the handling of inquiries.

[1395] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1396] Step 1:

[1397] The user opens the application on their smartphone, enters the question in the input field, and presses the submit button.

[1398] Input: Inquiry data entered by the user (e.g., "Where is the bread section?")

[1399] Operation: The application retrieves input data and encodes it in JSON format.

[1400] Output: Encoded JSON data

[1401] Step 2:

[1402] The device sends JSON data to the server as an HTTP POST request.

[1403] Input: Encoded JSON data

[1404] Operation: The device configures an HTTP POST request and sends data to the specified URL on the server.

[1405] Output: HTTP POST request sent to the server

[1406] Step 3:

[1407] The server receives an HTTP request and parses the query data in JSON format.

[1408] Input: JSON data included in an HTTP POST request

[1409] Operation: The server analyzes the received data and extracts the query content (e.g., "Where is the bread section?").

[1410] Output: Analyzed query content

[1411] Step 4:

[1412] The server generates queries for the artificial intelligence model based on the analyzed data.

[1413] Input: Analyzed query content

[1414] Operation: The server passes the query content to the AI ​​model in an appropriate format (e.g., a prompt like "Where is the bread section?").

[1415] Output: Generated prompt message

[1416] Step 5:

[1417] The server uses an artificial intelligence model (e.g., TensorFlow) to generate answers based on the query.

[1418] Input: Generated prompt message

[1419] Operation: The artificial intelligence model generates an answer based on the prompt sentence (e.g., "The bread section is in the third row of the food section.").

[1420] Output: Generated answer

[1421] Step 6:

[1422] The server re-encodes the generated response into JSON format and sends it to the terminal.

[1423] Input: Generated answer

[1424] Operation: The server encodes the response in JSON format and sends it to the terminal as an HTTP response.

[1425] Output: Encoded JSON format response data

[1426] Step 7:

[1427] The device parses the received JSON data and displays the answer to the user.

[1428] Input: Response data in encoded JSON format

[1429] Operation: The terminal analyzes the received data and displays it in a user-friendly format (e.g., "The bread section is in the third row of the food section.").

[1430] Output: Answer displayed to the user

[1431] Through these steps, users can quickly obtain information about specific products or locations within a physical store.

[1432] 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.

[1433] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[1434] System Configuration

[1435] 1. Inquiry input by the user

[1436] Users use a device to enter specific questions or requests. This device includes PCs, smartphones, and tablets. The process begins when the user fills in the inquiry field and clicks the submit button.

[1437] 2. Data transmission from terminal to server

[1438] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request. Standard network protocols are used for transmission.

[1439] 3. Server analysis of query data

[1440] The server receives the query data, converts it to the appropriate data format, and analyzes it. The analysis process also incorporates an emotion engine that recognizes the user's emotions. The emotion engine analyzes the text data to identify the user's emotional state, such as anger, anxiety, or joy.

[1441] 4. Emotional analysis using an emotion engine

[1442] An emotion engine implemented within the server analyzes user emotions based on their inquiry data. The results of this analysis are then used in subsequent processing.

[1443] 5. Answer generation using artificial intelligence models

[1444] The server uses the analyzed data and the results of the emotion engine to generate a query for the artificial intelligence model. The AI ​​model generates an appropriate response based on the query and the emotional state. Because the response is output in an emotion-appropriate tone, the response is tailored to the user's emotions.

[1445] 6. Sending responses from the server to the terminal.

[1446] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal receives this response data and decodes it to present it to the user.

[1447] 7. Displaying responses via the device

[1448] The terminal analyzes the response data received from the server and displays it to the user. This allows the user to visually confirm the answer to the question.

[1449] Program processing

[1450] Question data collection

[1451] The user enters their question into the input field on the terminal and clicks the submit button. This prepares the inquiry data to be sent to the server in JSON format.

[1452] Receiving and analyzing query data on the server.

[1453] The server receives JSON data sent from the terminal and performs text analysis. Simultaneously, it also performs sentiment analysis to identify the user's emotional state.

[1454] Integration with the emotion engine

[1455] Text data is passed to an emotion engine to analyze the user's emotions. The results of the emotion analysis are then used in an artificial intelligence model.

[1456] Answer generation using artificial intelligence models

[1457] The server sends inquiry data, including sentiment analysis results, to an artificial intelligence model to generate an appropriate response based on the emotions.

[1458] Submit and display of responses

[1459] The server sends the generated response to the terminal, which then decodes and displays it to the user.

[1460] Specific example

[1461] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[1462] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[1463] The following describes the processing flow.

[1464] Step 1:

[1465] The user enters their inquiry into the input field on the device and clicks the submit button. This action retrieves the inquiry data on the device.

[1466] Step 2:

[1467] The terminal encodes the inquiry data obtained from the user into JSON format and sends it to the server as an HTTP POST request. Specifically, the data is sent as follows:

[1468] json

[1469] {

[1470] "query": "Why is my order delayed?"

[1471] }

[1472] Step 3:

[1473] The server receives an HTTP POST request sent from the terminal. The server extracts JSON data from the request body and obtains the query content (in this case, "Why is my order delayed?").

[1474] Step 4:

[1475] The server extracts the query content and passes it to the emotion engine to analyze the user's emotions. The emotion engine analyzes the text data and identifies emotional states such as anger and dissatisfaction.

[1476] Step 5:

[1477] The server retrieves the analysis results from the emotion engine. For example, the analysis results might identify the emotion as "anger."

[1478] Step 6:

[1479] The server sends the analyzed query content and the results of the emotion engine to the artificial intelligence model. Here, the server sends the following data:

[1480] json

[1481] {

[1482] "prompt": "User question: Why is my order delayed?\nEmotion: Anger\nAI answer:",

[1483] "max_tokens": 100

[1484] }

[1485] Step 7:

[1486] The artificial intelligence model receives data sent from the server and generates an appropriate response. In this case, the AI ​​model generates a response in a tone that takes the user's feelings into consideration, such as, "We apologize for the wait. We are currently checking the status of your order."

[1487] Step 8:

[1488] The server receives the response sent back from the artificial intelligence model. The received response might be text such as, "We apologize for the delay. We are currently checking the order status."

[1489] Step 9:

[1490] The server encodes the received response in JSON format and sends it back to the terminal. The encoded data will look like this:

[1491] json

[1492] {

[1493] "Answer": "We apologize for the delay. We are currently checking the status of your order."

[1494] }

[1495] Step 10:

[1496] The device receives JSON data sent from the server. The device parses the JSON data and extracts the response in the format necessary to display it to the user.

[1497] Step 11:

[1498] The terminal displays the extracted response to the user. This allows the user to visually confirm the response, "We apologize for the delay. We are currently checking the status of your order."

[1499] This series of steps ensures that users receive prompt, emotionally sensitive responses when they submit an inquiry.

[1500] (Example 2)

[1501] 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".

[1502] Modern inquiry systems are required to provide prompt, emotionally sensitive, and appropriate responses to user inquiries. However, conventional systems lack the ability to properly recognize user emotions, often providing mechanical and uniform answers. This makes it difficult to increase user satisfaction and trust. Therefore, there is a need for a system that can analyze user emotions and generate flexible responses accordingly.

[1503] 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.

[1504] In this invention, the server includes means for [analyzing received inquiry data as text and further analyzing the user's emotions using an emotion engine], [generating an appropriate response using an artificial intelligence model based on the analyzed data and the results of the emotion engine], and [encoding the generated response in JSON format and sending it to the terminal]. This makes it possible to [provide a quick and appropriate response that takes the user's emotions into consideration].

[1505] A "terminal" is a device that a user operates to input inquiry data and communicate with a server, and includes personal computers, smartphones, tablets, and other similar devices.

[1506] "Inquiry data" refers to the content of questions and requests entered by the user into the device, and is usually information expressed in text format.

[1507] A "standard network protocol" refers to the technical standards used when sending and receiving data over the internet, and includes, for example, HTTP and HTTPS.

[1508] A "server" is a computer system that receives inquiry data entered by a user, performs text analysis and sentiment analysis, generates appropriate responses, and sends them to the terminal.

[1509] "Text analysis" is a method for analyzing received inquiry data and understanding its content, and it is performed using natural language processing technology.

[1510] An "emotion engine" is software or an algorithm that analyzes user inquiry data to identify the emotions contained in the text.

[1511] An "artificial intelligence model" is a system that uses machine learning techniques to generate appropriate answers based on inquiry data and analysis results.

[1512] "JSON format" is a lightweight, text-based data format for structuring and representing data, and it is an abbreviation for JavaScript Object Notation.

[1513] "Decoding" refers to the process of converting encoded data, such as JSON format, back to its original format, and is performed so that the device can display the data received from the server to the user.

[1514] "Emotion analysis results" refer to data indicating emotions identified by the emotion engine after analyzing user inquiry data.

[1515] "Visual display" refers to the device displaying the response data on the screen in a format that is easy for the user to understand.

[1516] This invention provides a system that offers rapid and emotion-sensitive responses to user inquiries. The system collects inquiry data entered by the user via a terminal and sends it to a server. The server analyzes the inquiry data and uses an emotion engine to recognize the user's emotions. It then generates an appropriate response based on those emotions and sends it back to the terminal for presentation to the user.

[1517] Users enter specific questions or requests using a device, which includes PCs, smartphones, and tablets. The user enters their inquiry into the input field and clicks the submit button to begin the process.

[1518] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request using a standard network protocol such as HTTPS.

[1519] The server receives the inquiry data and performs text analysis and sentiment analysis. Natural language processing techniques are used for text analysis to understand the content of the user's inquiry. A sentiment engine is used for sentiment analysis to identify the user's emotional state.

[1520] The server passes text data to the emotion engine, which analyzes the user's emotions. The results of this analysis are then used by the subsequent artificial intelligence model to generate responses. For example, the emotion engine might identify that the user is feeling dissatisfied or angry in response to the question, "Why is my order delayed?"

[1521] The server uses the analyzed data and the results of the sentiment engine to send a query to the artificial intelligence model. The generative AI model generates an appropriate response based on the query and the sentiment state. An example of a prompt is used: "Analyze the user's sentiment from the following text and generate a response appropriate to that sentiment. Input: 'Why is my order delayed?'" The model would generate a response such as, "We apologize for the delay. We are currently checking the status of your order."

[1522] The server-generated response is re-encoded into JSON format and sent to the terminal. The terminal decodes this data and displays it visually to the user. This allows the user to feel that their emotions are understood and to have a better support experience.

[1523] Thus, the present invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take into account the user's emotions.

[1524] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1525] Step 1:

[1526] The user enters a question into the input field on the device and clicks the submit button.

[1527] Specific action: The user types "Why is my order delayed?" and clicks the submit button.

[1528] Input: Text data entered by the user (question content).

[1529] Output: The entered text data is temporarily stored on the device.

[1530] Step 2:

[1531] The terminal encodes the user's input data into JSON format and sends it to the server as an HTTP POST request.

[1532] Specific operation: The program on the terminal converts the query data into JSON format and sends an HTTP POST request to the specified server URL.

[1533] Input: Text data entered by the user.

[1534] Output: The encoded JSON data is sent to the server as an HTTP POST request.

[1535] Step 3:

[1536] The system extracts JSON data from HTTP POST requests received by the server and performs text analysis. It also analyzes user emotions using an emotion engine.

[1537] Specific operation: The server parses the JSON data from the request body and extracts the text portion. Then, it performs text analysis using natural language processing techniques and sentiment analysis using a sentiment engine.

[1538] Input: Encoded JSON data.

[1539] Output: Text analysis results and sentiment analysis results.

[1540] Step 4:

[1541] The server sends a query to an artificial intelligence model based on the text analysis results and sentiment analysis results, and generates an answer.

[1542] Specific operation: The server generates prompts for the generative AI model and inputs them along with the sentiment analysis results. For example, it might use the prompt: "Analyze the user's sentiment from the following text and generate an appropriate response. Input: 'Why is my order delayed?'" The generative AI model then generates an appropriate response.

[1543] Input: Text analysis results, sentiment analysis results, prompt text.

[1544] Output: Generated answer text.

[1545] Step 5:

[1546] The server encodes the generated response text into JSON format and sends it to the terminal as an HTTP response.

[1547] Specific operation: The server-side program converts the response text into JSON format and sends it back to the terminal as an HTTP response.

[1548] Input: Generated response text.

[1549] Output: Encoded JSON data is sent to the terminal as an HTTP response.

[1550] Step 6:

[1551] The device decodes JSON data from the HTTP response it receives and displays it visually to the user.

[1552] Specific operation: The program on the terminal extracts JSON data from the HTTP response body and decodes it back into its original text format. Then, it displays it on the screen. For example, it might display, "We apologize for the wait. We are currently checking your order status."

[1553] Input: Encoded JSON data.

[1554] Output: The response text that is visually displayed to the user.

[1555] (Application Example 2)

[1556] 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".

[1557] Traditional inquiry systems often provide mechanical responses without considering the user's emotions, leading to decreased user satisfaction. Furthermore, the lack of responses in an appropriate tone based on emotions made it difficult to address users' psychological states.

[1558] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1559] In this invention, the server includes means for analyzing received inquiry data, recognizing the user's emotions using an emotion analysis engine based on that data, generating inquiries for an artificial intelligence model, and obtaining an answer appropriate to the emotions; means for transmitting the obtained answer to a terminal; and means for displaying the received answer to the user. This makes it possible to provide answers that take the user's emotions into consideration and improve the user experience.

[1560] A "terminal" is a device used by a user for input, such as a smartphone, personal computer, or tablet.

[1561] "Inquiry data" refers to information about questions and requests that users input and send through their devices.

[1562] A "server" is a central data processing unit that analyzes inquiry data, generates responses, and transmits them.

[1563] A "sentiment analysis engine" is a software program that identifies emotions from user inquiry data and determines their emotional state.

[1564] An "artificial intelligence model" is an artificial intelligence algorithm that generates the optimal response for a user based on inquiry data and the results of an emotion analysis engine.

[1565] "Answer" refers to the information provided or the response content generated based on the user's inquiry data.

[1566] "Transmission" refers to the act of transferring data between different devices, such as terminals and servers.

[1567] "Receiving" refers to the act of a terminal or server acquiring data sent from another party.

[1568] "Display" refers to the act of outputting received information to the device screen so that the user can visually confirm it.

[1569] The system implementing this invention consists of a terminal, a server, an emotion analysis engine, an artificial intelligence model, and a user. The terminal is a device used by the user to input inquiry data, and includes smartphones, personal computers, tablets, and the like.

[1570] Overall system flow

[1571] 1. Inquiry input by the user

[1572] The user enters their question or request into the input field on the terminal and clicks the submit button.

[1573] 2. Data transmission from terminal to server

[1574] The entered query data is encoded in JSON format and sent to the server. The HTTP POST protocol is used for transmission.

[1575] 3. Server analysis of query data

[1576] The server analyzes the received query data and converts it into an appropriate format. This analysis incorporates a sentiment analysis engine that identifies the user's emotions from the text data.

[1577] 4. Emotion analysis using an emotion analysis engine

[1578] The emotion analysis engine on the server recognizes the user's emotions based on the query data. For example, it identifies emotional states such as anger, anxiety, and joy.

[1579] 5. Answer generation using artificial intelligence models

[1580] The server uses the analyzed data and the results of the sentiment analysis engine to generate appropriate responses using an artificial intelligence model. This allows for responses to be output in a tone appropriate to the emotion.

[1581] 6. Sending responses from the server to the terminal.

[1582] The generated response is then encoded again in JSON format and sent to the terminal.

[1583] 7. Displaying responses via the device

[1584] The terminal decodes the received response data and presents it to the user. This display allows the user to visually confirm the answer to the question.

[1585] Hardware and software to be used

[1586] Hardware:

[1587] Devices such as smartphones, personal computers, and tablets

[1588] Server as a central data processing unit

[1589] software:

[1590] Python: The entire programming language

[1591] requests: A library for making HTTP requests.

[1592] JSON: Used for encoding and decoding data.

[1593] SentimentEngine: A software engine used for sentiment analysis.

[1594] AIResponseGenerator: An artificial intelligence model that generates responses based on emotions.

[1595] Specific example

[1596] For example, consider a scenario where a user enters the question, "Why is my order delayed?" and clicks the submit button. The device sends this question to the server in JSON format, and the server passes this data to the emotion engine for analysis. The emotion engine identifies that the user is feeling dissatisfied or angry about this question. Based on the analysis, the artificial intelligence model generates a response that takes the user's feelings into consideration, such as, "We apologize for the delay. We are currently checking the status of your order." The server sends this response to the device, which then displays it to the user. This allows the user to feel that their feelings are understood and provides a better support experience.

[1597] Example of a prompt

[1598] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[1599] As described above, this invention improves the quality of inquiry handling and realizes a better user experience by providing responses that take user emotions into consideration.

[1600] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1601] Step 1:

[1602] User-initiated inquiry input: The user enters a question or request into the terminal's input field and clicks the submit button. The input data is in text format and constitutes the inquiry data. Input is made from the user to the terminal, and the output is the inquiry data.

[1603] Step 2:

[1604] Data transmission from terminal to server: The terminal encodes the input query data into JSON format and sends it to the server as an HTTP POST request. The terminal uses HTTP as the transmission protocol. The input is query data (in text format), and the output is encoded JSON data.

[1605] Step 3:

[1606] Server reception and parsing of query data: The server receives JSON data sent from the terminal and decodes it to obtain query data in text format. This data contains the user's questions and requests. The server then parses this data. The input is encoded JSON data, and the output is query data in text format.

[1607] Step 4:

[1608] Emotional analysis by the emotion analysis engine: The emotion analysis engine on the server identifies the user's emotions based on the analyzed query data. For example, it identifies emotional states such as anger, anxiety, and joy. In this step, the input is query data in text format, and the output is the emotional state.

[1609] Step 5:

[1610] AI-powered response generation: The server uses the analyzed query data and the results of the sentiment analysis engine to provide prompts to the generating AI model, which then generates an appropriate response. The input is the query data and sentiment state, and the output is a response (in text format) corresponding to the sentiment.

[1611] Example of a prompt:

[1612] Please generate an appropriate answer considering the user's question: 'Why is my order delayed?' and their sentiment: 'Dissatisfied'.

[1613] Step 6:

[1614] Sending the response from the server to the terminal: The generated response is re-encoded in JSON format and sent to the terminal as an HTTP response. The input is the generated text-formatted response, and the output is encoded JSON data.

[1615] Step 7:

[1616] Receiving and displaying responses by the terminal: The terminal decodes the JSON data received from the server and obtains the generated response in text format. This response is then displayed on the screen for presentation to the user. The input is encoded JSON data, and the output is the text-formatted response displayed to the user.

[1617] By following these steps, users can receive prompt and appropriate responses to their inquiries, thereby improving the user experience.

[1618] 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.

[1619] 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.

[1620] 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 robot 414.

[1621] 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.

[1622] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1623] 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.

[1624] 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.

[1625] 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.

[1626] 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."

[1627] 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.

[1628] 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.

[1629] 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.

[1630] 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.

[1631] 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.

[1632] 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.

[1633] 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.

[1634] 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.

[1635] 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.

[1636] 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.

[1637] 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.

[1638] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1639] The following is further disclosed regarding the embodiments described above.

[1640] (Claim 1)

[1641] [Means for collecting inquiry data entered by a user from a certain terminal,

[1642] [Means for sending collected query data to the server,

[1643] [A means of analyzing the query data received by the server, generating queries for an artificial intelligence model based on that data, and obtaining answers,

[1644] [Methods for sending the acquired response from the server to the terminal,

[1645] A system that includes means for displaying the response received by the terminal to the user.

[1646] (Claim 2)

[1647] [The system according to claim 1, wherein the terminal automatically sends the inquiry data entered by the terminal to the server.

[1648] (Claim 3)

[1649] [The system according to claim 1, wherein the server uses an artificial intelligence model to generate an answer to a query.

[1650] "Example 1"

[1651] (Claim 1)

[1652] [Means by which the user enters inquiry data using a terminal,

[1653] [Methods for encoding the input data from the terminal into JSON format and sending it to the server as an HTTP POST request,

[1654] [A means of analyzing the JSON-formatted query data received by the server, generating a prompt statement, querying an artificial intelligence model, and obtaining a response,

[1655] [Methods for the server to re-encode the generated response into JSON format and send it to the terminal as an HTTP response,

[1656] A system that includes means for analyzing the response received by the terminal and displaying it to the user.

[1657] (Claim 2)

[1658] [The system according to claim 1, wherein the terminal automatically sends the inquiry data entered by the terminal to the server.

[1659] (Claim 3)

[1660] [The system according to claim 1, wherein the server uses an artificial intelligence model to generate prompt sentences and generate answers to queries.

[1661] "Application Example 1"

[1662] (Claim 1)

[1663] [Means for collecting inquiry data entered by a user from a certain terminal,

[1664] [Means for sending collected query data to the server,

[1665] [A means of analyzing the query data received by the server, generating queries for an artificial intelligence model based on that data, and obtaining answers,

[1666] [Methods for sending the acquired response from the server to the terminal,

[1667] [Means of displaying the response received by the terminal to the user,

[1668] A system that includes a means of generating and guiding users to specific locations or product locations within a physical store based on their inquiries.

[1669] (Claim 2)

[1670] [The system according to claim 1, wherein the terminal automatically sends the inquiry data entered by the terminal to the server.

[1671] (Claim 3)

[1672] [The system according to claim 1, wherein the server uses an artificial intelligence model to generate an answer to a query.

[1673] "Example 2 of combining an emotion engine"

[1674] (Claim 1)

[1675] [Means for collecting inquiry data entered by a user from a certain terminal,

[1676] [Means for sending collected query data to a server using standard network protocols,

[1677] [A method for analyzing the user's emotions using a sentiment engine, based on text analysis of the query data received by the server.]

[1678] [A means of generating appropriate answers using an artificial intelligence model based on analyzed data and the results of an emotion engine,

[1679] [Methods for encoding the server-generated response into JSON format and sending it to the terminal,

[1680] A system that includes means for decoding the response received by the terminal and displaying it visually to the user.

[1681] (Claim 2)

[1682] [The system according to claim 1, wherein the terminal automatically sends the inquiry data entered by the terminal to the server.

[1683] (Claim 3)

[1684] [The system according to claim 1, wherein the server sends inquiry data including emotion analysis results to an artificial intelligence model and generates an emotion-appropriate response.

[1685] "Application example 2 when combining with an emotional engine"

[1686] (Claim 1)

[1687] [Means for collecting inquiry data entered by a user from a certain terminal,

[1688] [Means for sending collected query data to the server,

[1689] [A means of analyzing the inquiry data received by the server, using an emotion analysis engine to recognize the user's emotions based on that data, generating inquiries for an artificial intelligence model, and obtaining responses appropriate to those emotions.]

[1690] [Methods for sending the acquired response from the server to the terminal,

[1691] [A system that includes means for displaying the response received by the terminal to the user.]

[1692] (Claim 2)

[1693] [The system according to claim 1, wherein the terminal automatically sends the inquiry data entered by the terminal to the server.

[1694] (Claim 3)

[1695] The system according to claim 1, wherein the server uses an emotion analysis engine and an artificial intelligence model to generate an emotion-appropriate response to an inquiry. [Explanation of symbols]

[1696] 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 collecting inquiry data entered by a user from a terminal, A means of sending the collected query data to the server, A means of analyzing the query data received by the server, generating queries for an artificial intelligence model based on that data, and obtaining answers, A means of sending the acquired response from the server to the terminal, A system that includes means for displaying the responses received by the terminal to the user.

2. The system according to claim 1, wherein the terminal automatically transmits the inquiry data entered to the server.

3. The system according to claim 1, wherein the server uses an artificial intelligence model to generate an answer to a query.

Images