system
The system addresses the issue of incorrect address entry by using real-time monitoring and generative AI to generate and display address candidates, ensuring accurate and efficient address registration.
Patent Information
- Application Number
- JP2024138787
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-08-20
- Publication Date
- 2026-03-05
AI Technical Summary
Current online address change systems face issues with users entering incorrect or incomplete addresses due to free-text input, leading to misdirected mail and services, and lack efficient methods to ensure accurate address registration.
A system that uses real-time monitoring of user input, sends data to a generative AI model for address candidate generation, and displays these candidates as a pull-down menu for selection, reducing errors and enabling accurate address entry.
This system significantly reduces user input errors and facilitates quick, accurate address registration by providing address candidates based on map information, enhancing user experience and reducing delivery errors.
Smart Images

Figure 2026036260000001_ABST
Abstract
Description
[Technical Field]
[0001] The technology of the present disclosure relates to a system. [Background technology]
[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance. [Prior art documents] [Patent documents]
[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]
[0004] In the current online address change procedure, customers enter their address using free words, which creates the risk of inputting an incorrect or incomplete address. This can result in mail and services being misdirected or not being delivered. Therefore, there is a need for a system that can reduce user input errors and efficiently input and register accurate addresses. [Means for solving the problem]
[0005] The present invention provides a system that monitors the input content in real time when a user begins to input an address, sends the input address data to a server, and the server then sends the data to a generative AI model, which then generates address candidates. The generated candidate addresses are sent to the user's terminal via the server, and the user terminal displays them as a pull-down menu. The user selects the correct address from the pull-down menu and finally registers it. This configuration reduces user address input errors and enables users to quickly input accurate addresses.
[0006] "User" refers to the person who enters the address and carries out the change procedure.
[0007] An "input field" refers to a text box or form on a web page that allows a user to enter address information.
[0008] "Real-time monitoring" refers to the ability to instantly check the content of each character entered by a user into an input field.
[0009] "Entered address data" refers to the address string entered by the user into the input field.
[0010] "Server" refers to the computer system that receives and processes user input data and transmits the data to the generative AI model.
[0011] A "generative AI model" refers to an artificial intelligence algorithm that uses map information to generate appropriate address candidates based on input address data.
[0012] "Map information" refers to the geographical data used to determine addresses and generate candidates, and is the basic data used to provide highly accurate address candidates.
[0013] "Candidate Addresses" refers to a list of multiple possible addresses presented by a generative AI model based on user input.
[0014] "Pull-down menu" refers to a style of interface displayed to a user to allow them to select from suggested addresses.
[0015] "Means for final address registration" refers to the function of saving the exact address selected by the user within the system and confirming it as official data.
[0016] "Yahoo map information" refers to map data acquired from a publicly available geographic information service, and is the base data used to generate address candidates in the present invention. [Brief explanation of the drawings]
[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11]FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION
[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.
[0019] First, the terms used in the following description will be explained.
[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).
[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.
[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.
[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.
[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."
[0025] [First embodiment]
[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.
[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.
[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.
[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.
[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.
[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.
[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.
[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0038] This invention is a system that uses generative AI to present correct address candidates and prevent input errors when a user changes their address online. This system consists of a user terminal, a server, and a generative AI model. The program processing of this system is explained below in natural language.
[0039] Natural language processing explanation
[0040] 1. User input detection
[0041] When a user starts to enter characters into the address input field, the device monitors this entry in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check this entry as it goes along.
[0042] 2. Send input data to the server
[0043] When a user enters data of a certain number of characters or more (for example, three characters or more) into an input field, the device prepares a request to send this input data to the server. Specifically, it sends the input data to the server using Ajax or the Fetch API.
[0044] 3. Data transfer to generative AI
[0045] The server sends the input data received from the device to the generative AI model. For example, when the data "Shibuya-ku, Tokyo" arrives at the server, the server converts it into the required format and calls an API endpoint to send it to the generative AI model.
[0046] 4. Generate address candidates
[0047] The generative AI model generates candidate addresses by referencing map information based on the input data received from the server. Specifically, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0048] 5. Server return of candidate data
[0049] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate data to the device in JSON format.
[0050] 6. Displaying the drop-down menu
[0051] The user's device analyzes the candidate data received from the server and displays it as a pull-down menu. For example, the device displays candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" in a pull-down menu.
[0052] 7. User Choices and Registration
[0053] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field of the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration.
[0054] Specific examples
[0055] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps would be as follows:
[0056] 1. The user begins typing "Shibuya Ward, Tokyo."
[0057] 2. The device detects this in real time and sends the data to the server.
[0058] 3. The server transfers this data to the generative AI model.
[0059] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0060] 5. The server returns these candidates to the device.
[0061] 6. The terminal displays the candidate addresses as a pull-down menu.
[0062] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and finally registers.
[0063] This series of steps allows users to change their address easily and accurately.
[0064] The processing flow will be explained below.
[0065] Step 1:
[0066] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0067] Step 2:
[0068] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0069] Step 3:
[0070] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[0071] Step 4:
[0072] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0073] Step 5:
[0074] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[0075] Step 6:
[0076] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0077] Step 7:
[0078] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[0079] Step 8:
[0080] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[0081] Step 9:
[0082] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[0083] Step 10:
[0084] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data sent by the terminal and completes the address change procedure.
[0085] Example 1
[0086] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0087] Conventional address change systems have a high risk of users making input errors. Input errors are particularly likely when complex notations such as kanji characters and place names are involved, making it difficult to accurately register an address. Furthermore, appropriate candidate addresses are not presented promptly, often resulting in a poor user experience. There is a need for a system that can solve these problems and allow users to change their address easily and accurately.
[0088] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[0089] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for the generative AI model to generate address candidates based on map information, means for the server to return the candidate addresses generated by the generative AI model to the server, means for the server to transmit the generated candidate addresses to a user terminal, and means for the user terminal to display the candidate addresses as a pull-down menu and finally register the address selected by the user from the pull-down menu. This makes it easier for the user to refer to the candidate addresses when inputting an address, preventing incorrect input and enabling accurate address changes.
[0090] A "user terminal" is a device that provides an interface for a user to input an address, monitors the input content in real time, and communicates with the server.
[0091] The "server" is a device that receives address data sent from the user device, transfers it to the generative AI model, and returns the results to the user device.
[0092] An "input field" is an interface element such as a text box or input area into which a user enters an address.
[0093] A "generative AI model" is an algorithm or machine learning model that references map information based on input address data and generates candidate addresses.
[0094] "Map information" is a dataset that includes geographic address data and area information, and is the reference data used by generative AI models to generate address candidates.
[0095] A "pull-down menu" is a drop-down menu that is displayed on a user's terminal and allows the user to select from among candidate addresses.
[0096] A "prompt sentence" is a text sentence that contains instructions for the generative AI model to generate address candidates.
[0097] This invention is a system that uses a generative AI model to present correct address candidates and prevent input errors when a user changes their address online. The system consists of a user terminal, a server, and a generative AI model.
[0098] Hardware and Software
[0099] The user device can be a computer, smartphone, tablet, or other input device. The server is a high-performance computer system with an appropriate database and network connection. The generative AI model is software that implements machine learning algorithms to generate address candidates based on map information.
[0100] The terminal provides an address input interface using JavaScript (registered trademark), HTML, and CSS. Specifically, it implements a text input field, real-time input detection, and JavaScript functions for sending input content. Data is sent using Ajax and the Fetch API.
[0101] The server is implemented using a server-side programming language such as Python, Java (registered trademark), or Node.js. The server transfers input data received from the device to the generative AI model and then sends the results back to the device. A RESTful API is used to send and receive data to the server.
[0102] The generative AI model is implemented in Python or other machine learning frameworks (e.g., TENSORFLOW® or PyTorch). The model generates candidate addresses based on a prompt and returns the results in JSON format.
[0103] Specific examples of processing
[0104] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps to follow are:
[0105] 1. The user begins typing "Shibuya Ward, Tokyo."
[0106] 2. The device detects the input content in real time and sends the data "Shibuya-ku, Tokyo" to the server.
[0107] 3. The server transfers this data to the generative AI model.
[0108] 4. The generative AI model generates candidate addresses using prompts like the following:
[0109] Generate address suggestions: List all addresses that match "Shibuya-ku, Tokyo."
[0110] 5. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" or "Jinnan 1-chome, Shibuya-ku, Tokyo" and sends them back to the server.
[0111] 6. The server returns these candidates to the device.
[0112] 7. The terminal displays the candidate addresses as a pull-down menu.
[0113] 8. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and presses the submit button to complete the final registration.
[0114] This system allows users to accurately register their address while checking candidate addresses, reducing input errors compared to conventional systems and enabling quick and accurate address changes.
[0115] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0116] Step 1:
[0117] User starts typing
[0118] When the user starts typing characters into the address input field, the device monitors the input in real time. Specifically, using a JavaScript input event listener, the device captures the input as soon as the user starts typing "Tokyo". Input: "Tokyo". Output: "Tokyo"
[0119] Step 2:
[0120] Sending input data to the server
[0121] When the user enters a certain number of characters (e.g., 3 or more characters) in the input field, the device sends that data to the server. Specifically, it uses the JavaScript fetch API to send data to the server asynchronously. Input: "Tokyo". Output: Server send request (POST)
[0122] Step 3:
[0123] Receiving data on the server
[0124] The server receives the data sent from the device. It parses the received data into JSON format and prepares it for the next process. Input: "Tokyo" (JSON format). Output: "Tokyo" (structured data)
[0125] Step 4:
[0126] Data transfer to generative AI
[0127] The server sends the received data to the generative AI model. Specifically, it formats this data in a format that can be used by the generative AI model and forwards it as an API request. Input: "Tokyo" (structured data). Output: "Tokyo" (request to the generative AI model)
[0128] Step 5:
[0129] Generate address candidates
[0130] The generative AI model generates candidate addresses using prompts based on data sent from the server. For example, the prompt is "Generate address input candidates: List all addresses that match "Tokyo."" Input: "Tokyo" (request to the generative AI model). Output: "Chiyoda-ku, Tokyo," "Shibuya-ku, Tokyo" (candidate addresses)
[0131] Step 6:
[0132] Return candidate data to the server
[0133] The server receives address candidate data from the generative AI model and prepares to send the data to the user's device. The candidate data is converted to JSON format and sent back to the device via the server's API endpoint. Input: "Chiyoda-ku, Tokyo" and "Shibuya-ku, Tokyo" (candidate addresses). Output: Candidate address data (JSON format)
[0134] Step 7:
[0135] Displaying the drop-down menu
[0136] The terminal analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, it performs DOM manipulation using JavaScript to create a new <option>Create a tag and add it to the drop-down menu. Input: Candidate address data (JSON format). Output: Candidate addresses added to the drop-down menu
[0137] Step 8:
[0138] User Selection and Registration
[0139] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field on the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration. Input: Address selected by the user (e.g., "Shibuya-ku, Tokyo"). Output: Server transmission request (POST) for the selected address data
[0140] This series of steps allows users to change their address easily and accurately.
[0141] (Application example 1)
[0142] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0143] In conventional address entry systems, users frequently made input errors when manually entering addresses, resulting in incorrect delivery of goods and delivery delays. Furthermore, the input burden on users was high, making it difficult to provide a comfortable user experience. There is a need for a system that can solve these problems and support accurate and fast address entry.
[0144] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0145] In this invention, the server includes a means for monitoring the input content in real time when a user begins to enter an address into an input field, a means for transmitting the entered address data to the server, and a means for the server to transmit the input data to a generative AI model. This allows the generative AI model to generate address candidates based on map information and prompt text, and transmits the candidate addresses to the user's terminal to display them as a pull-down menu, enabling the user to quickly enter an accurate address. Furthermore, by providing a means for finally registering the address selected by the user from the pull-down menu and reflecting it on the online shopping site, delivery errors can be significantly reduced and user convenience can be improved.
[0146] A "user terminal" is a device used by a user to enter an address, and may include a smartphone, tablet, or personal computer.
[0147] "Address data" is the address information that a user enters into an input field.
[0148] The "server" is a computer system that processes address data received from a user device and sends it to the generative AI model.
[0149] A "generative AI model" is an artificial intelligence model that generates address candidates by referencing map information and prompt text based on input data sent from the server.
[0150] "Map information" is a geographic database that the generative AI model references when generating address candidates.
[0151] A "prompt sentence" is auxiliary text that a generative AI model uses when generating address candidates.
[0152] A "pull-down menu" is an interface element that allows a user terminal to display generated candidate addresses in a user-selectable format.
[0153] "Candidate addresses" are multiple address suggestions for the user to choose from that are generated by the generative AI model based on input data.
[0154] "Finally registering" refers to the act of the user finalizing the candidate address selected from the pull-down menu and saving it in the system.
[0155] "Mail Order Site" means an online shopping platform that a user accesses to complete the purchase process for a product.
[0156] This invention is a system that uses a generative AI model to present accurate address candidates in real time when a user enters an address on an online shopping site, preventing input errors.
[0157] 1. System Configuration
[0158] The system consists of the following hardware and software:
[0159] User devices: Smartphones, tablets, personal computers, etc.
[0160] Server: Backend system using Node.js and Express.
[0161] Generative AI model: OpenAI (registered trademark) GPT-4 (registered trademark).
[0162] Database: MongoDB.
[0163] 2. Natural language description of the process
[0164] When a user starts to enter characters into an address input field, the user's device monitors the input in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device checks the input as it goes along, and once a certain number of characters (e.g., three characters) have been entered, the input data is sent to the server.
[0165] The server sends the received input data to the generative AI model. Specifically, it calls OpenAI GPT-4 and sends a prompt saying, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates." Based on the input data and the prompt, the generative AI model references map information and generates candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo."
[0166] The server receives the candidate addresses returned by the generative AI model and sends them to the user's device. The user's device displays the received candidate addresses as a drop-down menu, allowing the user to select the correct address. The user selects the correct address from the drop-down menu, and the selected address is ultimately registered in the system. This series of steps minimizes delivery errors and increases user convenience.
[0167] 3. Specific Examples
[0168] Example of address input and candidate display
[0169] For example, if a user wants to register "Jinnan 1-chome, Shibuya-ku, Tokyo" on an online shopping site, the steps would be as follows:
[0170] 1. The user begins typing "Shibuya-ku, Tokyo" into the address input field.
[0171] 2. The user device detects this in real time and sends the data to the server.
[0172] 3. The server transfers this data to the generative AI model.
[0173] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0174] 5. The server returns these candidate addresses to the terminal.
[0175] 6. The user device displays candidate addresses as a pull-down menu.
[0176] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" from the drop-down menu and finally registers the address.
[0177] In this way, by utilizing a generative AI model, users can input addresses accurately and quickly. An example of a prompt sentence is, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates."
[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0179] Step 1:
[0180] When a user starts typing characters into the address input field, the device monitors this input in real time. When three or more characters are entered into the input field, the device collects the input data. For example, if a user types "Shibu, Tokyo," the text data will be collected.
[0181] Step 2:
[0182] The device sends the collected input data to the server. Ajax or Fetch API is used to send the input data to the server as an HTTP POST request. Specifically, the data for "Shibu, Tokyo" is sent from the device to the server.
[0183] Step 3:
[0184] The server prepares to send the input data received from the device to the generative AI model. The server generates the input data as a prompt sentence and sends it to the generative AI. For example, a prompt sentence such as "The user has entered 'Shibu, Tokyo'. Please generate address candidates" is generated and sent to the generative AI model.
[0185] Step 4:
[0186] The generative AI model references a map information database based on the received prompt text and generates multiple address candidates. For example, candidates such as "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo" are generated. In this generation process, the input data is combined with map information to create a list of matching candidate addresses.
[0187] Step 5:
[0188] The server receives the candidate addresses generated by the generative AI model and processes them into JSON format. The server then sends the processed data to the user's device. For example, the generated address candidates are sent as {"addresses": ["Ebisu, Shibuya-ku, Tokyo", "Daikanyama, Shibuya-ku, Tokyo", "Shinsen, Shibuya-ku, Tokyo"]}.
[0189] Step 6:
[0190] The device analyzes the JSON format candidate address data received from the server and displays it as a pull-down menu. The user can select the appropriate address from the pull-down menu displayed at the bottom of the address input field. Specifically, the options are "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo."
[0191] Step 7:
[0192] The address selected by the user from the pull-down menu is automatically reflected in the input field and final registration is performed. The terminal then sends this selected address data back to the server and saves it in the database, allowing the user to register accurate address information.
[0193] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.
[0194] This invention is a system that, when a user changes their address online, presents correct address candidates based on generative AI and combines it with an emotion engine that recognizes the user's emotions, thereby preventing input errors and improving the user experience. The system is composed of a user terminal, a server, a generative AI model, and an emotion engine.
[0195] Natural language processing explanation
[0196] 1. User input detection
[0197] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0198] 2. Send input data to the server
[0199] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0200] 3. Data transfer to generative AI
[0201] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0202] 4. Generate address candidates
[0203] The generative AI model generates candidate addresses from the input data based on map information. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0204] 5. Emotion Recognition by Emotion Engine
[0205] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, for example, by determining their emotional state based on input speed, intervals, and frequency of input corrections.
[0206] 6. Server return of candidate data
[0207] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate addresses in JSON format to the device.
[0208] 7. Adjusting candidate priorities
[0209] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[0210] 8. Displaying the drop-down menu
[0211] The user's device analyzes the candidate address data received from the server and displays it as a pull-down menu. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are set and displayed in a pull-down menu.
[0212] 9. User Choices and Registration
[0213] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[0214] 10. Displaying Emotion-Based Guidance Messages
[0215] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if the emotion engine detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[0216] 11. Final Registration
[0217] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[0218] Specific examples
[0219] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," they would follow these steps:
[0220] 1. The user begins typing "Shibuya Ward, Tokyo."
[0221] 2. The device detects this input in real time and sends the data to the server.
[0222] 3. The server sends this data to a generative AI model to generate candidate addresses.
[0223] 4. The emotion engine analyzes the user's input patterns and recognizes their emotional state.
[0224] 5. The server sends the generated candidate addresses to the device and adjusts the priority based on the emotion.
[0225] 6. The terminal displays the candidate addresses as a pull-down menu.
[0226] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and the selection is reflected in the input field.
[0227] 8. The emotion engine displays guide messages according to the user's emotions.
[0228] 9. The user presses the submit button, the device sends the selected address to the server, and the address change is finally completed.
[0229] This series of steps allows users to change their address easily and accurately, and the system can provide a better user experience by taking user feelings into consideration.
[0230] The processing flow will be explained below.
[0231] Step 1:
[0232] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0233] Step 2:
[0234] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0235] Step 3:
[0236] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[0237] Step 4:
[0238] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0239] Step 5:
[0240] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[0241] Step 6:
[0242] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0243] Step 7:
[0244] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[0245] Step 8:
[0246] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[0247] Step 9:
[0248] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, determining their emotional state based on factors such as input speed, intervals, and frequency of input corrections.
[0249] Step 10:
[0250] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[0251] Step 11:
[0252] The device redisplays the adjusted candidate addresses as a drop-down menu, making it easier for the user to select from the displayed candidate addresses.
[0253] Step 12:
[0254] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal will update the input field with that information.
[0255] Step 13:
[0256] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if it detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[0257] Step 14:
[0258] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[0259] Example 2
[0260] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0261] In conventional address entry systems, users were prone to making mistakes when entering the correct address, and the entry process was cumbersome. This led to problems that reduced user satisfaction when changing their address. Furthermore, there was a lack of means to reduce the stress and frustration users felt when entering addresses.
[0262] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0263] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for an emotion engine to analyze and recognize the user's emotion, means for the generative AI model to generate address candidates based on map information, means for the server to transmit the generated candidate addresses to a user terminal, means for the server to adjust the priority of the candidate addresses based on the user's emotion, means for the user terminal to display the candidate addresses as a pull-down menu, means for the user terminal to finally register the address selected by the user from the pull-down menu, and means for the emotion engine to display a guide message as necessary. This allows the user to change their address quickly and accurately while preventing input errors, and further improves the user experience by providing guide messages that take the user's emotion into consideration.
[0264] "User" refers to an individual who uses the System to make a change of address.
[0265] An "input field" refers to a text box or form on a web page where a user can enter an address.
[0266] "Real-time" refers to a process that processes each user input immediately.
[0267] "Means for monitoring input content" refers to means for sequentially checking characters entered by a user into a text field and detecting changes in input.
[0268] "Entered Address Data" refers to address information entered by a user into an input field.
[0269] "Server" refers to the computer system responsible for receiving data sent from a user device and transmitting the data to the processing and generative AI model.
[0270] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze input data and generate appropriate address candidates.
[0271] "Map information" refers to information including geographical data and location information for generating address candidates.
[0272] "Emotion engine" refers to a software module for analyzing a user's input patterns and inferring the user's emotional state.
[0273] "Candidate addresses" refers to a list of candidate addresses generated by a generative AI model based on address data.
[0274] "Means for adjusting priority" refers to a function that changes the display order of candidate addresses generated based on the user's emotional data.
[0275] "Pull-down menu" refers to a drop-down menu that displays candidate addresses that a user can select from.
[0276] "Guide messages" refer to messages of assistance and advice provided by the system when the user is performing input tasks.
[0277] The present invention relates to a system that improves input accuracy and user experience when users change their address online, by integrating a generative AI model and an emotion engine. The system mainly consists of a user terminal, a server, a generative AI model, and an emotion engine.
[0278] 1. User Device
[0279] A user terminal is a device (such as a PC, smartphone, or tablet) that accesses the system through a web browser. When a user starts to enter text into an address input field on a web page, the terminal monitors the input in real time.
[0280] Specifically, when a user starts typing "Shibuya-ku, Tokyo," a JavaScript program on the device catches keyboard events and sequentially analyzes the input characters. The analysis results are prepared to be sent to the server as JSON-formatted data.
[0281] 2. Server
[0282] The server receives input data from the user device and sends it to the generative AI model. The server analyzes the received data and sends it to the generative AI model based on the appropriate prompt.
[0283] For example, the server might send the following prompt to the generative AI model:
[0284] "Generate suggestions based on the address entered by the user: Shibuya-ku, Tokyo."
[0285] 3. Generative AI Models
[0286] The generative AI model receives the prompt sent from the server and generates address candidates by referencing a map information database. The generative AI model uses a machine learning algorithm to analyze the input data and generate the optimal address candidates.
[0287] For example, candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," "Ebisu 1-chome, Shibuya-ku, Tokyo," etc. are generated. The generated results are sent back to the server.
[0288] 4. Emotion Engine
[0289] The emotion engine analyzes the user's input patterns (speed, frequency of corrections, etc.) and recognizes the user's emotional state in real time. If the emotion engine recognizes that the user is frustrated, the server adjusts the priority of candidate addresses.
[0290] For example, if the emotion engine detects irritation, it will instruct the server to display the simplest and most accurate candidate addresses at the top. It will also generate and send guide messages to the user's device as needed.
[0291] 5. Displaying the drop-down menu and final registration
[0292] The server sends the data received from the generative AI model and emotion engine to the user's device. The device analyzes the received candidate address data and displays it as a drop-down menu. If the user selects the correct address, that address is reflected in the input field. Finally, when the user presses the send button, the device sends the selected address data to the server, which then finally registers the data.
[0293] Specific examples
[0294] For example, if a user wants to register "Tokyo, Shibuya-ku, Jinnan 1-chome," the following steps are performed:
[0295] 1. The user begins typing "Shibuya-ku, Tokyo."
[0296] 2. The device detects the input content in real time and prepares to send the data to the server in JSON format.
[0297] 3. The server sends the received data to the generative AI model with the following prompt: "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[0298] 4. The generative AI model generates candidate addresses and sends them back to the server.
[0299] 5. The sentiment engine recognizes the user's sentiment and adjusts the priority of candidate addresses as needed.
[0300] 6. The server sends the generated candidate addresses to the user terminal.
[0301] 7. The device displays candidate addresses as a pull-down menu, and the user selects "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0302] 8. If necessary, the emotion engine displays a guide message (e.g., "If you have any questions, please contact support").
[0303] 9. The user presses the send button, the terminal sends the selected address data to the server, and the server finally registers the address change.
[0304] Through the above process, users can quickly and accurately change their address, and the system can take users' feelings into consideration to provide a more comfortable user experience.
[0305] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0306] System program processing flow
[0307] Step 1:
[0308] When a user starts to enter text into an address input field, the terminal monitors the input in real time. Specifically, it catches keyboard press events and acquires the entered characters sequentially. The input data is in text format, and each character is added to a variable in the terminal as it is entered. For example, if a user starts to enter "Shibuya-ku, Tokyo," the terminal stores this string in a variable.
[0309] Input: Each character the user types
[0310] Output: The input string updated in real time
[0311] Step 2:
[0312] When the entered data is three characters or more, the device converts the data to JSON format and prepares to send it to the server. Specifically, it uses JavaScript's JSON.stringify function to convert the input string to JSON format. For example, if "Shibuya-ku, Tokyo" is entered, it is converted to a JSON object called {"address": "Shibuya-ku, Tokyo"}.
[0313] Input: Real-time updated input string
[0314] Output: JSON format data {"address": "Shibuya-ku, Tokyo"}
[0315] Step 3:
[0316] The server analyzes the JSON data received from the device and generates a prompt to send to the generative AI model. Specifically, it analyzes the received data and constructs a prompt. For example, if the data received is {"address": "Shibuya-ku, Tokyo"}, it creates a prompt that reads, "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[0317] Input: JSON format data {"address": "Shibuya-ku, Tokyo"}
[0318] Output: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[0319] Step 4:
[0320] The generative AI model receives the prompt sent from the server and generates address candidates. The generative AI model references a map information database and generates the most suitable address candidate based on the prompt. For example, based on "Shibuya Ward, Tokyo," it generates candidates such as "Ato 1-chome, Shibuya Ward, Tokyo," "Jinnan 1-chome, Shibuya Ward, Tokyo," and "Ebisu 1-chome, Shibuya Ward, Tokyo."
[0321] Input: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[0322] Output: Candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0323] Step 5:
[0324] The emotion engine analyzes data such as the user's input speed and correction frequency to recognize the user's emotions. Based on these input parameters, the emotion engine infers the user's emotional state and identifies emotions such as "irritation," "confusion," and "normal."
[0325] Input: Data such as user typing speed and correction frequency
[0326] Output: User's emotional state (e.g., "irritated")
[0327] Step 6:
[0328] The server receives the candidate address data generated by the generative AI model, converts it to JSON format, and prepares to send it to the user's device. Specifically, the candidate address list is converted to JSON format using the JSON.stringify function. For example, the candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"] is converted to the JSON object {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}.
[0329] Input: Candidate Address List ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0330] Output: JSON format data {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[0331] Step 7:
[0332] The server adjusts the priority of candidate addresses based on the emotion data it receives. For example, if the emotion engine determines that the user is frustrated, it will prioritize the easiest and most reliable address candidates.
[0333] Input: Emotional state (e.g., "irritated"), candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0334] Output: Adjusted candidate address list ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0335] Step 8:
[0336] The user device analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, candidate addresses are extracted from the received JSON data and an HTML pull-down menu is dynamically generated.
[0337] Input: JSON format data {"candidates": ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[0338] Output: HTML element of the drop-down menu
[0339] Step 9:
[0340] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the selected address is reflected in the input field.
[0341] Input: User selection event
[0342] Output: The selected address is reflected in the input field.
[0343] Step 10:
[0344] If necessary, the emotion engine will display a guide message based on the user's emotions. For example, if the user feels confused, the message "If you have any questions, please contact support" will be displayed.
[0345] Input: User's emotional state (e.g., "confused")
[0346] Output: Display guide message
[0347] Step 11:
[0348] When the user confirms the input and presses the send button, the device sends the selected address data back to the server in JSON format. The server then registers the received data and the address change procedure is complete.
[0349] Input: Selected address data, Submit button click event
[0350] Output: Final registration completion notification
[0351] (Application example 2)
[0352] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."
[0353] In recent years, the number of online address change procedures has increased, but the tendency for users to make input errors during the process has become a problem. Furthermore, systems that do not consider the user's emotional state during operation can result in a poor user experience, making it difficult to enter information accurately, especially in stressful situations. Therefore, there is a need for a system that can prevent input errors when changing addresses and provide a better user experience by considering the user's emotional state.
[0354] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[0355] In this invention, the server is equipped with an emotion engine that analyzes a user's input operations and patterns to recognize emotions, and includes a means for adjusting the priority of candidate addresses based on the user's emotional state, a means for transmitting the input address data to the server, and a means for a generative AI model to generate address candidates based on map information. This allows users to change their address with peace of mind while preventing input errors. It also reduces user stress and confusion, promoting a comfortable user experience.
[0356] An "input field" is an interface for a user to enter data.
[0357] "Real-time" is a technical term that means that data processing and communication occurs immediately.
[0358] "Means for monitoring input content" refers to means for sequentially checking data entered by the user.
[0359] "Means for sending input data" refers to a mechanism for sending information entered by a user to an external system such as a server.
[0360] A "generative AI model" is an algorithm or system that uses machine learning or deep learning to generate data.
[0361] "Map information" refers to data that includes location information and geographical information.
[0362] A "means for generating candidates" is a mechanism for generating multiple options based on user input.
[0363] An "emotion engine" is a system or software that analyzes and recognizes a user's emotional state.
[0364] "Emotional state" refers to the user's psychological and emotional state.
[0365] The "means for adjusting priority" is a method for changing the order in which candidates are displayed depending on conditions or circumstances.
[0366] "Secure Method" refers to the technology and means used to securely transmit and store information.
[0367] The "means of final registration" is the method for determining the selected data and storing it in a database or system.
[0368] The system for implementing this invention is composed of a user terminal, a server, a generative AI model, and an emotion engine. Each component and their interactions will be described below.
[0369] System configuration
[0370] 1. User Device:
[0371] Provides an interface for the user to enter an address.
[0372] Its role is to monitor the input content in real time and send the address data to the server.
[0373] The user device is a smartphone (iOS / ANDROID (registered trademark)).
[0374] 2. Server:
[0375] Data received from the user device is sent to the generative AI model and emotion engine.
[0376] The priority of the candidate addresses is adjusted based on the generated candidate addresses and the user's sentiment information.
[0377] The adjusted data is then sent back to the user's device, and finally the address information selected by the user is securely stored.
[0378] The server uses a cloud infrastructure (for example, AWS (registered trademark) or Google (registered trademark) Cloud).
[0379] 3. Generative AI Model:
[0380] Based on partial address data entered by the user, map information is used to generate candidate addresses.
[0381] Generative AI models used include, for example, GPT-4.
[0382] 4. Emotion Engine:
[0383] Analyzes input operations and patterns to recognize the user's emotional state.
[0384] The analysis results are sent to the server and used to adjust the priority of the candidate addresses.
[0385] The emotion engine uses Affectiva and Microsoft (registered trademark) Azure (registered trademark) Emotion API.
[0386] Specific operation of each element
[0387] For example, if the user enters an address:
[0388] 1. The user begins typing "Shibuya-ku, Tokyo."
[0389] 2. The user's device detects this input in real time and sends it to the server when the input data reaches a certain number of characters (for example, three or more characters).
[0390] 3. The server forwards the received data to the generative AI model and generates a prompt. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: 'Shibuya-ku, Tokyo'."
[0391] 4. The generative AI model generates candidate addresses and sends the results back to the server.
[0392] 5. In parallel, the emotion engine analyzes the user's input pattern and speed, and transmits the user's emotional state to the server.
[0393] 6. The server adjusts the priority based on the generated candidate addresses and the analysis results of the emotion engine.
[0394] 7. The adjusted candidate addresses are sent to the user's terminal and displayed in a pull-down menu format.
[0395] 8. The user selects the appropriate address, which is finally sent securely to the server to complete the registration.
[0396] In this way, the system can prevent input errors when users go through the change of address process and provide a better user experience that takes into account the user's emotional state.
[0397] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0398] Step 1:
[0399] As users begin to type their address into the input field, the device monitors this input in real time, updating the data as each character is entered and retaining it until a certain number of characters is reached.
[0400] Step 2:
[0401] When the entered address data reaches a certain number of characters (for example, three or more characters), the terminal converts the data into JSON format and sends it to the server. The input data (for example, "Shibuya-ku, Tokyo") is processed into an appropriate format for transmission to the server.
[0402] Step 3:
[0403] The server receives the address data sent from the device and generates a prompt to send to the generative AI model. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: Shibuya-ku, Tokyo." This prompt is generated and sent to the generative AI model.
[0404] Step 4:
[0405] The generative AI model generates multiple candidate addresses based on the received prompt by referencing map information. Based on the input data, it generates a list of candidate addresses, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," and returns it to the server.
[0406] Step 5:
[0407] The server receives the candidate address list returned by the generative AI model and, in parallel, receives the user's input operation data analyzed by the emotion engine. The emotion engine analyzes the user's emotional state using data such as input speed and timing, and sends the results to the server.
[0408] Step 6:
[0409] The server adjusts the priority of candidate addresses based on the analysis results from the emotion engine. For example, if the user is feeling frustrated, it will prioritize more accurate and general candidates by placing them at the top of the list. The adjusted candidate address list is sent to the user's device in JSON format.
[0410] Step 7:
[0411] The terminal receives the adjusted candidate address list sent from the server and displays it in the user interface as a pull-down menu. The candidates are presented in list format to make selection easier for the user.
[0412] Step 8:
[0413] Once the user selects the correct address from the drop-down menu and confirms it, the device updates the input fields with the selected data. This final confirmation data is then reprocessed into JSON format and securely sent to the server.
[0414] Step 9:
[0415] The server receives the final address data sent by the user and stores it in the database. This completes the address change procedure, and a completion message is displayed to the user on the terminal.
[0416] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0417] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0418] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.
[0419] [Second embodiment]
[0420] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.
[0421] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.
[0422] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0423] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.
[0424] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[0425] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[0426] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[0427] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[0428] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0429] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0430] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0431] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."
[0432] This invention is a system that uses generative AI to present correct address candidates and prevent input errors when a user changes their address online. This system consists of a user terminal, a server, and a generative AI model. The program processing of this system is explained below in natural language.
[0433] Natural language processing explanation
[0434] 1. User input detection
[0435] When a user starts to enter characters into the address input field, the device monitors this entry in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check this entry as it goes along.
[0436] 2. Send input data to the server
[0437] When a user enters data of a certain number of characters or more (for example, three characters or more) into an input field, the device prepares a request to send this input data to the server. Specifically, it sends the input data to the server using Ajax or the Fetch API.
[0438] 3. Data transfer to generative AI
[0439] The server sends the input data received from the device to the generative AI model. For example, when the data "Shibuya-ku, Tokyo" arrives at the server, the server converts it into the required format and calls an API endpoint to send it to the generative AI model.
[0440] 4. Generate address candidates
[0441] The generative AI model generates candidate addresses by referencing map information based on the input data received from the server. Specifically, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0442] 5. Server return of candidate data
[0443] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate data to the device in JSON format.
[0444] 6. Displaying the drop-down menu
[0445] The user's device analyzes the candidate data received from the server and displays it as a pull-down menu. For example, the device displays candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" in a pull-down menu.
[0446] 7. User Choices and Registration
[0447] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field of the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration.
[0448] Specific examples
[0449] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps would be as follows:
[0450] 1. The user begins typing "Shibuya Ward, Tokyo."
[0451] 2. The device detects this in real time and sends the data to the server.
[0452] 3. The server transfers this data to the generative AI model.
[0453] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0454] 5. The server returns these candidates to the device.
[0455] 6. The terminal displays the candidate addresses as a pull-down menu.
[0456] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and finally registers.
[0457] This series of steps allows users to change their address easily and accurately.
[0458] The processing flow will be explained below.
[0459] Step 1:
[0460] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0461] Step 2:
[0462] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0463] Step 3:
[0464] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[0465] Step 4:
[0466] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0467] Step 5:
[0468] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[0469] Step 6:
[0470] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0471] Step 7:
[0472] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[0473] Step 8:
[0474] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[0475] Step 9:
[0476] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[0477] Step 10:
[0478] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data sent by the terminal and completes the address change procedure.
[0479] Example 1
[0480] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0481] Conventional address change systems have a high risk of users making input errors. Input errors are particularly likely when complex notations such as kanji characters and place names are involved, making it difficult to accurately register an address. Furthermore, appropriate candidate addresses are not presented promptly, often resulting in a poor user experience. There is a need for a system that can solve these problems and allow users to change their address easily and accurately.
[0482] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[0483] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for the generative AI model to generate address candidates based on map information, means for the server to return the candidate addresses generated by the generative AI model to the server, means for the server to transmit the generated candidate addresses to a user terminal, and means for the user terminal to display the candidate addresses as a pull-down menu and finally register the address selected by the user from the pull-down menu. This makes it easier for the user to refer to the candidate addresses when inputting an address, preventing incorrect input and enabling accurate address changes.
[0484] A "user terminal" is a device that provides an interface for a user to input an address, monitors the input content in real time, and communicates with the server.
[0485] The "server" is a device that receives address data sent from the user device, transfers it to the generative AI model, and returns the results to the user device.
[0486] An "input field" is an interface element such as a text box or input area into which a user enters an address.
[0487] A "generative AI model" is an algorithm or machine learning model that references map information based on input address data and generates candidate addresses.
[0488] "Map information" is a dataset that includes geographic address data and area information, and is the reference data used by generative AI models to generate address candidates.
[0489] A "pull-down menu" is a drop-down menu that is displayed on a user's terminal and allows the user to select from among candidate addresses.
[0490] A "prompt sentence" is a text sentence that contains instructions for the generative AI model to generate address candidates.
[0491] This invention is a system that uses a generative AI model to present correct address candidates and prevent input errors when a user changes their address online. The system consists of a user terminal, a server, and a generative AI model.
[0492] Hardware and Software
[0493] The user device can be a computer, smartphone, tablet, or other input device. The server is a high-performance computer system with an appropriate database and network connection. The generative AI model is software that implements machine learning algorithms to generate address candidates based on map information.
[0494] The terminal provides an address input interface using JavaScript, HTML, and CSS. Specifically, it implements a text input field, real-time input detection, and JavaScript functions for submitting input. Data is submitted using Ajax and the Fetch API.
[0495] The server is implemented using a server-side programming language such as Python, Java, or Node.js. The server forwards input data received from the device to the generative AI model and then sends the results back to the device. A RESTful API is used to send and receive data to the server.
[0496] The generative AI model is implemented in Python or other machine learning frameworks (e.g., TensorFlow or PyTorch). The model generates candidate addresses based on a prompt and returns the results in JSON format.
[0497] Specific examples of processing
[0498] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps to follow are:
[0499] 1. The user begins typing "Shibuya Ward, Tokyo."
[0500] 2. The device detects the input content in real time and sends the data "Shibuya-ku, Tokyo" to the server.
[0501] 3. The server transfers this data to the generative AI model.
[0502] 4. The generative AI model generates candidate addresses using prompts like the following:
[0503] Generate address suggestions: List all addresses that match "Shibuya-ku, Tokyo."
[0504] 5. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" or "Jinnan 1-chome, Shibuya-ku, Tokyo" and sends them back to the server.
[0505] 6. The server returns these candidates to the device.
[0506] 7. The terminal displays the candidate addresses as a pull-down menu.
[0507] 8. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and presses the submit button to complete the final registration.
[0508] This system allows users to accurately register their address while checking candidate addresses, reducing input errors compared to conventional systems and enabling quick and accurate address changes.
[0509] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0510] Step 1:
[0511] User starts typing
[0512] When the user starts typing characters into the address input field, the device monitors the input in real time. Specifically, using a JavaScript input event listener, the device captures the input as soon as the user starts typing "Tokyo". Input: "Tokyo". Output: "Tokyo"
[0513] Step 2:
[0514] Sending input data to the server
[0515] When the user enters a certain number of characters (e.g., 3 or more characters) in the input field, the device sends that data to the server. Specifically, it uses the JavaScript fetch API to send data to the server asynchronously. Input: "Tokyo". Output: Server send request (POST)
[0516] Step 3:
[0517] Receiving data on the server
[0518] The server receives the data sent from the device. It parses the received data into JSON format and prepares it for the next process. Input: "Tokyo" (JSON format). Output: "Tokyo" (structured data)
[0519] Step 4:
[0520] Data transfer to generative AI
[0521] The server sends the received data to the generative AI model. Specifically, it formats this data in a format that can be used by the generative AI model and forwards it as an API request. Input: "Tokyo" (structured data). Output: "Tokyo" (request to the generative AI model)
[0522] Step 5:
[0523] Generate address candidates
[0524] The generative AI model generates candidate addresses using prompts based on data sent from the server. For example, the prompt is "Generate address input candidates: List all addresses that match "Tokyo."" Input: "Tokyo" (request to the generative AI model). Output: "Chiyoda-ku, Tokyo," "Shibuya-ku, Tokyo" (candidate addresses)
[0525] Step 6:
[0526] Return candidate data to the server
[0527] The server receives address candidate data from the generative AI model and prepares to send the data to the user's device. The candidate data is converted to JSON format and sent back to the device via the server's API endpoint. Input: "Chiyoda-ku, Tokyo" and "Shibuya-ku, Tokyo" (candidate addresses). Output: Candidate address data (JSON format)
[0528] Step 7:
[0529] Displaying the drop-down menu
[0530] The terminal analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, it performs DOM manipulation using JavaScript to create a new <option>Create a tag and add it to the drop-down menu. Input: Candidate address data (JSON format). Output: Candidate addresses added to the drop-down menu
[0531] Step 8:
[0532] User Selection and Registration
[0533] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field on the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration. Input: Address selected by the user (e.g., "Shibuya-ku, Tokyo"). Output: Server transmission request (POST) for the selected address data
[0534] This series of steps allows users to change their address easily and accurately.
[0535] (Application example 1)
[0536] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0537] In conventional address entry systems, users frequently made input errors when manually entering addresses, resulting in incorrect delivery of goods and delivery delays. Furthermore, the input burden on users was high, making it difficult to provide a comfortable user experience. There is a need for a system that can solve these problems and support accurate and fast address entry.
[0538] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0539] In this invention, the server includes a means for monitoring the input content in real time when a user begins to enter an address into an input field, a means for transmitting the entered address data to the server, and a means for the server to transmit the input data to a generative AI model. This allows the generative AI model to generate address candidates based on map information and prompt text, and transmits the candidate addresses to the user's terminal to display them as a pull-down menu, enabling the user to quickly enter an accurate address. Furthermore, by providing a means for finally registering the address selected by the user from the pull-down menu and reflecting it on the online shopping site, delivery errors can be significantly reduced and user convenience can be improved.
[0540] A "user terminal" is a device used by a user to enter an address, and may include a smartphone, tablet, or personal computer.
[0541] "Address data" is the address information that a user enters into an input field.
[0542] The "server" is a computer system that processes address data received from a user device and sends it to the generative AI model.
[0543] A "generative AI model" is an artificial intelligence model that generates address candidates by referencing map information and prompt text based on input data sent from the server.
[0544] "Map information" is a geographic database that the generative AI model references when generating address candidates.
[0545] A "prompt sentence" is auxiliary text that a generative AI model uses when generating address candidates.
[0546] A "pull-down menu" is an interface element that allows a user terminal to display generated candidate addresses in a user-selectable format.
[0547] "Candidate addresses" are multiple address suggestions for the user to choose from that are generated by the generative AI model based on input data.
[0548] "Finally registering" refers to the act of the user finalizing the candidate address selected from the pull-down menu and saving it in the system.
[0549] "Mail Order Site" means an online shopping platform that a user accesses to complete the purchase process for a product.
[0550] This invention is a system that uses a generative AI model to present accurate address candidates in real time when a user enters an address on an online shopping site, preventing input errors.
[0551] 1. System Configuration
[0552] The system consists of the following hardware and software:
[0553] User devices: Smartphones, tablets, personal computers, etc.
[0554] Server: Backend system using Node.js and Express.
[0555] Generative AI model: OpenAI GPT-4.
[0556] Database: MongoDB.
[0557] 2. Natural language description of the process
[0558] When a user starts to enter characters into an address input field, the user's device monitors the input in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device checks the input as it goes along, and once a certain number of characters (e.g., three characters) have been entered, the input data is sent to the server.
[0559] The server sends the received input data to the generative AI model. Specifically, it calls OpenAI GPT-4 and sends a prompt saying, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates." Based on the input data and the prompt, the generative AI model references map information and generates candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo."
[0560] The server receives the candidate addresses returned by the generative AI model and sends them to the user's device. The user's device displays the received candidate addresses as a drop-down menu, allowing the user to select the correct address. The user selects the correct address from the drop-down menu, and the selected address is ultimately registered in the system. This series of steps minimizes delivery errors and increases user convenience.
[0561] 3. Specific Examples
[0562] Example of address input and candidate display
[0563] For example, if a user wants to register "Jinnan 1-chome, Shibuya-ku, Tokyo" on an online shopping site, the steps would be as follows:
[0564] 1. The user begins typing "Shibuya-ku, Tokyo" into the address input field.
[0565] 2. The user device detects this in real time and sends the data to the server.
[0566] 3. The server transfers this data to the generative AI model.
[0567] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0568] 5. The server returns these candidate addresses to the terminal.
[0569] 6. The user device displays candidate addresses as a pull-down menu.
[0570] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" from the drop-down menu and finally registers the address.
[0571] In this way, by utilizing a generative AI model, users can input addresses accurately and quickly. An example of a prompt sentence is, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates."
[0572] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0573] Step 1:
[0574] When a user starts typing characters into the address input field, the device monitors this input in real time. When three or more characters are entered into the input field, the device collects the input data. For example, if a user types "Shibu, Tokyo," the text data will be collected.
[0575] Step 2:
[0576] The device sends the collected input data to the server. Ajax or Fetch API is used to send the input data to the server as an HTTP POST request. Specifically, the data for "Shibu, Tokyo" is sent from the device to the server.
[0577] Step 3:
[0578] The server prepares to send the input data received from the device to the generative AI model. The server generates the input data as a prompt sentence and sends it to the generative AI. For example, a prompt sentence such as "The user has entered 'Shibu, Tokyo'. Please generate address candidates" is generated and sent to the generative AI model.
[0579] Step 4:
[0580] The generative AI model references a map information database based on the received prompt text and generates multiple address candidates. For example, candidates such as "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo" are generated. In this generation process, the input data is combined with map information to create a list of matching candidate addresses.
[0581] Step 5:
[0582] The server receives the candidate addresses generated by the generative AI model and processes them into JSON format. The server then sends the processed data to the user's device. For example, the generated address candidates are sent as {"addresses": ["Ebisu, Shibuya-ku, Tokyo", "Daikanyama, Shibuya-ku, Tokyo", "Shinsen, Shibuya-ku, Tokyo"]}.
[0583] Step 6:
[0584] The device analyzes the JSON format candidate address data received from the server and displays it as a pull-down menu. The user can select the appropriate address from the pull-down menu displayed at the bottom of the address input field. Specifically, the options are "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo."
[0585] Step 7:
[0586] The address selected by the user from the pull-down menu is automatically reflected in the input field and final registration is performed. The terminal then sends this selected address data back to the server and saves it in the database, allowing the user to register accurate address information.
[0587] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[0588] This invention is a system that, when a user changes their address online, presents correct address candidates based on generative AI and combines it with an emotion engine that recognizes the user's emotions, thereby preventing input errors and improving the user experience. The system is composed of a user terminal, a server, a generative AI model, and an emotion engine.
[0589] Natural language processing explanation
[0590] 1. User input detection
[0591] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0592] 2. Send input data to the server
[0593] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0594] 3. Data transfer to generative AI
[0595] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0596] 4. Generate address candidates
[0597] The generative AI model generates candidate addresses from the input data based on map information. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0598] 5. Emotion Recognition by Emotion Engine
[0599] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, for example, by determining their emotional state based on input speed, intervals, and frequency of input corrections.
[0600] 6. Server return of candidate data
[0601] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate addresses in JSON format to the device.
[0602] 7. Adjusting candidate priorities
[0603] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[0604] 8. Displaying the drop-down menu
[0605] The user's device analyzes the candidate address data received from the server and displays it as a pull-down menu. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are set and displayed in a pull-down menu.
[0606] 9. User Choices and Registration
[0607] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[0608] 10. Displaying Emotion-Based Guidance Messages
[0609] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if the emotion engine detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[0610] 11. Final Registration
[0611] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[0612] Specific examples
[0613] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," they would follow these steps:
[0614] 1. The user begins typing "Shibuya Ward, Tokyo."
[0615] 2. The device detects this input in real time and sends the data to the server.
[0616] 3. The server sends this data to a generative AI model to generate candidate addresses.
[0617] 4. The emotion engine analyzes the user's input patterns and recognizes their emotional state.
[0618] 5. The server sends the generated candidate addresses to the device and adjusts the priority based on the emotion.
[0619] 6. The terminal displays the candidate addresses as a pull-down menu.
[0620] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and the selection is reflected in the input field.
[0621] 8. The emotion engine displays guide messages according to the user's emotions.
[0622] 9. The user presses the submit button, the device sends the selected address to the server, and the address change is finally completed.
[0623] This series of steps allows users to change their address easily and accurately, and the system can provide a better user experience by taking user feelings into consideration.
[0624] The processing flow will be explained below.
[0625] Step 1:
[0626] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0627] Step 2:
[0628] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0629] Step 3:
[0630] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[0631] Step 4:
[0632] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0633] Step 5:
[0634] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[0635] Step 6:
[0636] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0637] Step 7:
[0638] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[0639] Step 8:
[0640] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[0641] Step 9:
[0642] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, determining their emotional state based on factors such as input speed, intervals, and frequency of input corrections.
[0643] Step 10:
[0644] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[0645] Step 11:
[0646] The device redisplays the adjusted candidate addresses as a drop-down menu, making it easier for the user to select from the displayed candidate addresses.
[0647] Step 12:
[0648] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal will update the input field with that information.
[0649] Step 13:
[0650] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if it detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[0651] Step 14:
[0652] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[0653] Example 2
[0654] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0655] In conventional address entry systems, users were prone to making mistakes when entering the correct address, and the entry process was cumbersome. This led to problems that reduced user satisfaction when changing their address. Furthermore, there was a lack of means to reduce the stress and frustration users felt when entering addresses.
[0656] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[0657] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for an emotion engine to analyze and recognize the user's emotion, means for the generative AI model to generate address candidates based on map information, means for the server to transmit the generated candidate addresses to a user terminal, means for the server to adjust the priority of the candidate addresses based on the user's emotion, means for the user terminal to display the candidate addresses as a pull-down menu, means for the user terminal to finally register the address selected by the user from the pull-down menu, and means for the emotion engine to display a guide message as necessary. This allows the user to change their address quickly and accurately while preventing input errors, and further improves the user experience by providing guide messages that take the user's emotion into consideration.
[0658] "User" refers to an individual who uses the System to make a change of address.
[0659] An "input field" refers to a text box or form on a web page where a user can enter an address.
[0660] "Real-time" refers to a process that processes each user input immediately.
[0661] "Means for monitoring input content" refers to means for sequentially checking characters entered by a user into a text field and detecting changes in input.
[0662] "Entered Address Data" refers to address information entered by a user into an input field.
[0663] "Server" refers to the computer system responsible for receiving data sent from a user device and transmitting the data to the processing and generative AI model.
[0664] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze input data and generate appropriate address candidates.
[0665] "Map information" refers to information including geographical data and location information for generating address candidates.
[0666] "Emotion engine" refers to a software module for analyzing a user's input patterns and inferring the user's emotional state.
[0667] "Candidate addresses" refers to a list of candidate addresses generated by a generative AI model based on address data.
[0668] "Means for adjusting priority" refers to a function that changes the display order of candidate addresses generated based on the user's emotional data.
[0669] "Pull-down menu" refers to a drop-down menu that displays candidate addresses that a user can select from.
[0670] "Guide messages" refer to messages of assistance and advice provided by the system when the user is performing input tasks.
[0671] The present invention relates to a system that improves input accuracy and user experience when users change their address online, by integrating a generative AI model and an emotion engine. The system mainly consists of a user terminal, a server, a generative AI model, and an emotion engine.
[0672] 1. User Device
[0673] A user terminal is a device (such as a PC, smartphone, or tablet) that accesses the system through a web browser. When a user starts to enter text into an address input field on a web page, the terminal monitors the input in real time.
[0674] Specifically, when a user starts typing "Shibuya-ku, Tokyo," a JavaScript program on the device catches keyboard events and sequentially analyzes the input characters. The analysis results are prepared to be sent to the server as JSON-formatted data.
[0675] 2. Server
[0676] The server receives input data from the user device and sends it to the generative AI model. The server analyzes the received data and sends it to the generative AI model based on the appropriate prompt.
[0677] For example, the server might send the following prompt to the generative AI model:
[0678] "Generate suggestions based on the address entered by the user: Shibuya-ku, Tokyo."
[0679] 3. Generative AI Models
[0680] The generative AI model receives the prompt sent from the server and generates address candidates by referencing a map information database. The generative AI model uses a machine learning algorithm to analyze the input data and generate the optimal address candidates.
[0681] For example, candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," "Ebisu 1-chome, Shibuya-ku, Tokyo," etc. are generated. The generated results are sent back to the server.
[0682] 4. Emotion Engine
[0683] The emotion engine analyzes the user's input patterns (speed, frequency of corrections, etc.) and recognizes the user's emotional state in real time. If the emotion engine recognizes that the user is frustrated, the server adjusts the priority of candidate addresses.
[0684] For example, if the emotion engine detects irritation, it will instruct the server to display the simplest and most accurate candidate addresses at the top. It will also generate and send guide messages to the user's device as needed.
[0685] 5. Displaying the drop-down menu and final registration
[0686] The server sends the data received from the generative AI model and emotion engine to the user's device. The device analyzes the received candidate address data and displays it as a drop-down menu. If the user selects the correct address, that address is reflected in the input field. Finally, when the user presses the send button, the device sends the selected address data to the server, which then finally registers the data.
[0687] Specific examples
[0688] For example, if a user wants to register "Tokyo, Shibuya-ku, Jinnan 1-chome," the following steps are performed:
[0689] 1. The user begins typing "Shibuya-ku, Tokyo."
[0690] 2. The device detects the input content in real time and prepares to send the data to the server in JSON format.
[0691] 3. The server sends the received data to the generative AI model with the following prompt: "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[0692] 4. The generative AI model generates candidate addresses and sends them back to the server.
[0693] 5. The sentiment engine recognizes the user's sentiment and adjusts the priority of candidate addresses as needed.
[0694] 6. The server sends the generated candidate addresses to the user terminal.
[0695] 7. The device displays candidate addresses as a pull-down menu, and the user selects "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0696] 8. If necessary, the emotion engine displays a guide message (e.g., "If you have any questions, please contact support").
[0697] 9. The user presses the send button, the terminal sends the selected address data to the server, and the server finally registers the address change.
[0698] Through the above process, users can quickly and accurately change their address, and the system can take users' feelings into consideration to provide a more comfortable user experience.
[0699] The flow of the identification process in the second embodiment will be described with reference to FIG.
[0700] System program processing flow
[0701] Step 1:
[0702] When a user starts to enter text into an address input field, the terminal monitors the input in real time. Specifically, it catches keyboard press events and acquires the entered characters sequentially. The input data is in text format, and each character is added to a variable in the terminal as it is entered. For example, if a user starts to enter "Shibuya-ku, Tokyo," the terminal stores this string in a variable.
[0703] Input: Each character the user types
[0704] Output: The input string updated in real time
[0705] Step 2:
[0706] When the entered data is three characters or more, the device converts the data to JSON format and prepares to send it to the server. Specifically, it uses JavaScript's JSON.stringify function to convert the input string to JSON format. For example, if "Shibuya-ku, Tokyo" is entered, it is converted to a JSON object called {"address": "Shibuya-ku, Tokyo"}.
[0707] Input: Real-time updated input string
[0708] Output: JSON format data {"address": "Shibuya-ku, Tokyo"}
[0709] Step 3:
[0710] The server analyzes the JSON data received from the device and generates a prompt to send to the generative AI model. Specifically, it analyzes the received data and constructs a prompt. For example, if the data received is {"address": "Shibuya-ku, Tokyo"}, it creates a prompt that reads, "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[0711] Input: JSON format data {"address": "Shibuya-ku, Tokyo"}
[0712] Output: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[0713] Step 4:
[0714] The generative AI model receives the prompt sent from the server and generates address candidates. The generative AI model references a map information database and generates the most suitable address candidate based on the prompt. For example, based on "Shibuya Ward, Tokyo," it generates candidates such as "Ato 1-chome, Shibuya Ward, Tokyo," "Jinnan 1-chome, Shibuya Ward, Tokyo," and "Ebisu 1-chome, Shibuya Ward, Tokyo."
[0715] Input: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[0716] Output: Candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0717] Step 5:
[0718] The emotion engine analyzes data such as the user's input speed and correction frequency to recognize the user's emotions. Based on these input parameters, the emotion engine infers the user's emotional state and identifies emotions such as "irritation," "confusion," and "normal."
[0719] Input: Data such as user typing speed and correction frequency
[0720] Output: User's emotional state (e.g., "irritated")
[0721] Step 6:
[0722] The server receives the candidate address data generated by the generative AI model, converts it to JSON format, and prepares to send it to the user's device. Specifically, the candidate address list is converted to JSON format using the JSON.stringify function. For example, the candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"] is converted to the JSON object {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}.
[0723] Input: Candidate Address List ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0724] Output: JSON format data {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[0725] Step 7:
[0726] The server adjusts the priority of candidate addresses based on the emotion data it receives. For example, if the emotion engine determines that the user is frustrated, it will prioritize the easiest and most reliable address candidates.
[0727] Input: Emotional state (e.g., "irritated"), candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0728] Output: Adjusted candidate address list ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[0729] Step 8:
[0730] The user device analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, candidate addresses are extracted from the received JSON data and an HTML pull-down menu is dynamically generated.
[0731] Input: JSON format data {"candidates": ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[0732] Output: HTML element of the drop-down menu
[0733] Step 9:
[0734] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the selected address is reflected in the input field.
[0735] Input: User selection event
[0736] Output: The selected address is reflected in the input field.
[0737] Step 10:
[0738] If necessary, the emotion engine will display a guide message based on the user's emotions. For example, if the user feels confused, the message "If you have any questions, please contact support" will be displayed.
[0739] Input: User's emotional state (e.g., "confused")
[0740] Output: Display guide message
[0741] Step 11:
[0742] When the user confirms the input and presses the send button, the device sends the selected address data back to the server in JSON format. The server then registers the received data and the address change procedure is complete.
[0743] Input: Selected address data, Submit button click event
[0744] Output: Final registration completion notification
[0745] (Application example 2)
[0746] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."
[0747] In recent years, the number of online address change procedures has increased, but the tendency for users to make input errors during the process has become a problem. Furthermore, systems that do not consider the user's emotional state during operation can result in a poor user experience, making it difficult to enter information accurately, especially in stressful situations. Therefore, there is a need for a system that can prevent input errors when changing addresses and provide a better user experience by considering the user's emotional state.
[0748] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[0749] In this invention, the server is equipped with an emotion engine that analyzes a user's input operations and patterns to recognize emotions, and includes a means for adjusting the priority of candidate addresses based on the user's emotional state, a means for transmitting the input address data to the server, and a means for a generative AI model to generate address candidates based on map information. This allows users to change their address with peace of mind while preventing input errors. It also reduces user stress and confusion, promoting a comfortable user experience.
[0750] An "input field" is an interface for a user to enter data.
[0751] "Real-time" is a technical term that means that data processing and communication occurs immediately.
[0752] "Means for monitoring input content" refers to means for sequentially checking data entered by the user.
[0753] "Means for sending input data" refers to a mechanism for sending information entered by a user to an external system such as a server.
[0754] A "generative AI model" is an algorithm or system that uses machine learning or deep learning to generate data.
[0755] "Map information" refers to data that includes location information and geographical information.
[0756] A "means for generating candidates" is a mechanism for generating multiple options based on user input.
[0757] An "emotion engine" is a system or software that analyzes and recognizes a user's emotional state.
[0758] "Emotional state" refers to the user's psychological and emotional state.
[0759] The "means for adjusting priority" is a method for changing the order in which candidates are displayed depending on conditions or circumstances.
[0760] "Secure Method" refers to the technology and means used to securely transmit and store information.
[0761] The "means of final registration" is the method for determining the selected data and storing it in a database or system.
[0762] The system for implementing this invention is composed of a user terminal, a server, a generative AI model, and an emotion engine. Each component and their interactions will be described below.
[0763] System configuration
[0764] 1. User Device:
[0765] Provides an interface for the user to enter an address.
[0766] Its role is to monitor the input content in real time and send the address data to the server.
[0767] The user device is a smartphone (iOS / Android).
[0768] 2. Server:
[0769] Data received from the user device is sent to the generative AI model and emotion engine.
[0770] The priority of the candidate addresses is adjusted based on the generated candidate addresses and the user's sentiment information.
[0771] The adjusted data is then sent back to the user's device, and finally the address information selected by the user is securely stored.
[0772] The servers use cloud infrastructure (e.g., AWS or Google Cloud).
[0773] 3. Generative AI Model:
[0774] Based on partial address data entered by the user, map information is used to generate candidate addresses.
[0775] Generative AI models used include, for example, GPT-4.
[0776] 4. Emotion Engine:
[0777] Analyzes input operations and patterns to recognize the user's emotional state.
[0778] The analysis results are sent to the server and used to adjust the priority of the candidate addresses.
[0779] The emotion engine uses Affectiva and Microsoft Azure Emotion API.
[0780] Specific operation of each element
[0781] For example, if the user enters an address:
[0782] 1. The user begins typing "Shibuya-ku, Tokyo."
[0783] 2. The user's device detects this input in real time and sends it to the server when the input data reaches a certain number of characters (for example, three or more characters).
[0784] 3. The server forwards the received data to the generative AI model and generates a prompt. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: 'Shibuya-ku, Tokyo'."
[0785] 4. The generative AI model generates candidate addresses and sends the results back to the server.
[0786] 5. In parallel, the emotion engine analyzes the user's input pattern and speed, and transmits the user's emotional state to the server.
[0787] 6. The server adjusts the priority based on the generated candidate addresses and the analysis results of the emotion engine.
[0788] 7. The adjusted candidate addresses are sent to the user's terminal and displayed in a pull-down menu format.
[0789] 8. The user selects the appropriate address, which is finally sent securely to the server to complete the registration.
[0790] In this way, the system can prevent input errors when users go through the change of address process and provide a better user experience that takes into account the user's emotional state.
[0791] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[0792] Step 1:
[0793] As users begin to type their address into the input field, the device monitors this input in real time, updating the data as each character is entered and retaining it until a certain number of characters is reached.
[0794] Step 2:
[0795] When the entered address data reaches a certain number of characters (for example, three or more characters), the terminal converts the data into JSON format and sends it to the server. The input data (for example, "Shibuya-ku, Tokyo") is processed into an appropriate format for transmission to the server.
[0796] Step 3:
[0797] The server receives the address data sent from the device and generates a prompt to send to the generative AI model. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: Shibuya-ku, Tokyo." This prompt is generated and sent to the generative AI model.
[0798] Step 4:
[0799] The generative AI model generates multiple candidate addresses based on the received prompt by referencing map information. Based on the input data, it generates a list of candidate addresses, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," and returns it to the server.
[0800] Step 5:
[0801] The server receives the candidate address list returned by the generative AI model and, in parallel, receives the user's input operation data analyzed by the emotion engine. The emotion engine analyzes the user's emotional state using data such as input speed and timing, and sends the results to the server.
[0802] Step 6:
[0803] The server adjusts the priority of candidate addresses based on the analysis results from the emotion engine. For example, if the user is feeling frustrated, it will prioritize more accurate and general candidates by placing them at the top of the list. The adjusted candidate address list is sent to the user's device in JSON format.
[0804] Step 7:
[0805] The terminal receives the adjusted candidate address list sent from the server and displays it in the user interface as a pull-down menu. The candidates are presented in list format to make selection easier for the user.
[0806] Step 8:
[0807] Once the user selects the correct address from the drop-down menu and confirms it, the device updates the input fields with the selected data. This final confirmation data is then reprocessed into JSON format and securely sent to the server.
[0808] Step 9:
[0809] The server receives the final address data sent by the user and stores it in the database. This completes the address change procedure, and a completion message is displayed to the user on the terminal.
[0810] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[0811] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[0812] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.
[0813] [Third embodiment]
[0814] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.
[0815] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.
[0816] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[0817] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.
[0818] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[0819] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[0820] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[0821] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[0822] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[0823] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[0824] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[0825] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."
[0826] This invention is a system that uses generative AI to present correct address candidates and prevent input errors when a user changes their address online. This system consists of a user terminal, a server, and a generative AI model. The program processing of this system is explained below in natural language.
[0827] Natural language processing explanation
[0828] 1. User input detection
[0829] When a user starts to enter characters into the address input field, the device monitors this entry in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check this entry as it goes along.
[0830] 2. Send input data to the server
[0831] When a user enters data of a certain number of characters or more (for example, three characters or more) into an input field, the device prepares a request to send this input data to the server. Specifically, it sends the input data to the server using Ajax or the Fetch API.
[0832] 3. Data transfer to generative AI
[0833] The server sends the input data received from the device to the generative AI model. For example, when the data "Shibuya-ku, Tokyo" arrives at the server, the server converts it into the required format and calls an API endpoint to send it to the generative AI model.
[0834] 4. Generate address candidates
[0835] The generative AI model generates candidate addresses by referencing map information based on the input data received from the server. Specifically, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0836] 5. Server return of candidate data
[0837] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate data to the device in JSON format.
[0838] 6. Displaying the drop-down menu
[0839] The user's device analyzes the candidate data received from the server and displays it as a pull-down menu. For example, the device displays candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" in a pull-down menu.
[0840] 7. User Choices and Registration
[0841] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field of the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration.
[0842] Specific examples
[0843] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps would be as follows:
[0844] 1. The user begins typing "Shibuya Ward, Tokyo."
[0845] 2. The device detects this in real time and sends the data to the server.
[0846] 3. The server transfers this data to the generative AI model.
[0847] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0848] 5. The server returns these candidates to the device.
[0849] 6. The terminal displays the candidate addresses as a pull-down menu.
[0850] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and finally registers.
[0851] This series of steps allows users to change their address easily and accurately.
[0852] The processing flow will be explained below.
[0853] Step 1:
[0854] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0855] Step 2:
[0856] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0857] Step 3:
[0858] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[0859] Step 4:
[0860] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0861] Step 5:
[0862] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[0863] Step 6:
[0864] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0865] Step 7:
[0866] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[0867] Step 8:
[0868] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[0869] Step 9:
[0870] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[0871] Step 10:
[0872] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data sent by the terminal and completes the address change procedure.
[0873] Example 1
[0874] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[0875] Conventional address change systems have a high risk of users making input errors. Input errors are particularly likely when complex notations such as kanji characters and place names are involved, making it difficult to accurately register an address. Furthermore, appropriate candidate addresses are not presented promptly, often resulting in a poor user experience. There is a need for a system that can solve these problems and allow users to change their address easily and accurately.
[0876] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[0877] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for the generative AI model to generate address candidates based on map information, means for the server to return the candidate addresses generated by the generative AI model to the server, means for the server to transmit the generated candidate addresses to a user terminal, and means for the user terminal to display the candidate addresses as a pull-down menu and finally register the address selected by the user from the pull-down menu. This makes it easier for the user to refer to the candidate addresses when inputting an address, preventing incorrect input and enabling accurate address changes.
[0878] A "user terminal" is a device that provides an interface for a user to input an address, monitors the input content in real time, and communicates with the server.
[0879] The "server" is a device that receives address data sent from the user device, transfers it to the generative AI model, and returns the results to the user device.
[0880] An "input field" is an interface element such as a text box or input area into which a user enters an address.
[0881] A "generative AI model" is an algorithm or machine learning model that references map information based on input address data and generates candidate addresses.
[0882] "Map information" is a dataset that includes geographic address data and area information, and is the reference data used by generative AI models to generate address candidates.
[0883] A "pull-down menu" is a drop-down menu that is displayed on a user's terminal and allows the user to select from among candidate addresses.
[0884] A "prompt sentence" is a text sentence that contains instructions for the generative AI model to generate address candidates.
[0885] This invention is a system that uses a generative AI model to present correct address candidates and prevent input errors when a user changes their address online. The system consists of a user terminal, a server, and a generative AI model.
[0886] Hardware and Software
[0887] The user device can be a computer, smartphone, tablet, or other input device. The server is a high-performance computer system with an appropriate database and network connection. The generative AI model is software that implements machine learning algorithms to generate address candidates based on map information.
[0888] The terminal provides an address input interface using JavaScript, HTML, and CSS. Specifically, it implements a text input field, real-time input detection, and JavaScript functions for submitting input. Data is submitted using Ajax and the Fetch API.
[0889] The server is implemented using a server-side programming language such as Python, Java, or Node.js. The server forwards input data received from the device to the generative AI model and then sends the results back to the device. A RESTful API is used to send and receive data to the server.
[0890] The generative AI model is implemented in Python or other machine learning frameworks (e.g., TensorFlow or PyTorch). The model generates candidate addresses based on a prompt and returns the results in JSON format.
[0891] Specific examples of processing
[0892] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps to follow are:
[0893] 1. The user begins typing "Shibuya Ward, Tokyo."
[0894] 2. The device detects the input content in real time and sends the data "Shibuya-ku, Tokyo" to the server.
[0895] 3. The server transfers this data to the generative AI model.
[0896] 4. The generative AI model generates candidate addresses using prompts like the following:
[0897] Generate address suggestions: List all addresses that match "Shibuya-ku, Tokyo."
[0898] 5. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" or "Jinnan 1-chome, Shibuya-ku, Tokyo" and sends them back to the server.
[0899] 6. The server returns these candidates to the device.
[0900] 7. The terminal displays the candidate addresses as a pull-down menu.
[0901] 8. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and presses the submit button to complete the final registration.
[0902] This system allows users to accurately register their address while checking candidate addresses, reducing input errors compared to conventional systems and enabling quick and accurate address changes.
[0903] The flow of the identification process in the first embodiment will be described with reference to FIG.
[0904] Step 1:
[0905] User starts typing
[0906] When the user starts typing characters into the address input field, the device monitors the input in real time. Specifically, using a JavaScript input event listener, the device captures the input as soon as the user starts typing "Tokyo". Input: "Tokyo". Output: "Tokyo"
[0907] Step 2:
[0908] Sending input data to the server
[0909] When the user enters a certain number of characters (e.g., 3 or more characters) in the input field, the device sends that data to the server. Specifically, it uses the JavaScript fetch API to send data to the server asynchronously. Input: "Tokyo". Output: Server send request (POST)
[0910] Step 3:
[0911] Receiving data on the server
[0912] The server receives the data sent from the device. It parses the received data into JSON format and prepares it for the next process. Input: "Tokyo" (JSON format). Output: "Tokyo" (structured data)
[0913] Step 4:
[0914] Data transfer to generative AI
[0915] The server sends the received data to the generative AI model. Specifically, it formats this data in a format that can be used by the generative AI model and forwards it as an API request. Input: "Tokyo" (structured data). Output: "Tokyo" (request to the generative AI model)
[0916] Step 5:
[0917] Generate address candidates
[0918] The generative AI model generates candidate addresses using prompts based on data sent from the server. For example, the prompt is "Generate address input candidates: List all addresses that match "Tokyo."" Input: "Tokyo" (request to the generative AI model). Output: "Chiyoda-ku, Tokyo," "Shibuya-ku, Tokyo" (candidate addresses)
[0919] Step 6:
[0920] Return candidate data to the server
[0921] The server receives address candidate data from the generative AI model and prepares to send the data to the user's device. The candidate data is converted to JSON format and sent back to the device via the server's API endpoint. Input: "Chiyoda-ku, Tokyo" and "Shibuya-ku, Tokyo" (candidate addresses). Output: Candidate address data (JSON format)
[0922] Step 7:
[0923] Displaying the drop-down menu
[0924] The terminal analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, it performs DOM manipulation using JavaScript to create a new <option>Create a tag and add it to the drop-down menu. Input: Candidate address data (JSON format). Output: Candidate addresses added to the drop-down menu
[0925] Step 8:
[0926] User Selection and Registration
[0927] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field on the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration. Input: Address selected by the user (e.g., "Shibuya-ku, Tokyo"). Output: Server transmission request (POST) for the selected address data
[0928] This series of steps allows users to change their address easily and accurately.
[0929] (Application example 1)
[0930] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[0931] In conventional address entry systems, users frequently made input errors when manually entering addresses, resulting in incorrect delivery of goods and delivery delays. Furthermore, the input burden on users was high, making it difficult to provide a comfortable user experience. There is a need for a system that can solve these problems and support accurate and fast address entry.
[0932] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[0933] In this invention, the server includes a means for monitoring the input content in real time when a user begins to enter an address into an input field, a means for transmitting the entered address data to the server, and a means for the server to transmit the input data to a generative AI model. This allows the generative AI model to generate address candidates based on map information and prompt text, and transmits the candidate addresses to the user's terminal to display them as a pull-down menu, enabling the user to quickly enter an accurate address. Furthermore, by providing a means for finally registering the address selected by the user from the pull-down menu and reflecting it on the online shopping site, delivery errors can be significantly reduced and user convenience can be improved.
[0934] A "user terminal" is a device used by a user to enter an address, and may include a smartphone, tablet, or personal computer.
[0935] "Address data" is the address information that a user enters into an input field.
[0936] The "server" is a computer system that processes address data received from a user device and sends it to the generative AI model.
[0937] A "generative AI model" is an artificial intelligence model that generates address candidates by referencing map information and prompt text based on input data sent from the server.
[0938] "Map information" is a geographic database that the generative AI model references when generating address candidates.
[0939] A "prompt sentence" is auxiliary text that a generative AI model uses when generating address candidates.
[0940] A "pull-down menu" is an interface element that allows a user terminal to display generated candidate addresses in a user-selectable format.
[0941] "Candidate addresses" are multiple address suggestions for the user to choose from that are generated by the generative AI model based on input data.
[0942] "Finally registering" refers to the act of the user finalizing the candidate address selected from the pull-down menu and saving it in the system.
[0943] "Mail Order Site" means an online shopping platform that a user accesses to complete the purchase process for a product.
[0944] This invention is a system that uses a generative AI model to present accurate address candidates in real time when a user enters an address on an online shopping site, preventing input errors.
[0945] 1. System Configuration
[0946] The system consists of the following hardware and software:
[0947] User devices: Smartphones, tablets, personal computers, etc.
[0948] Server: Backend system using Node.js and Express.
[0949] Generative AI model: OpenAI GPT-4.
[0950] Database: MongoDB.
[0951] 2. Natural language description of the process
[0952] When a user starts to enter characters into an address input field, the user's device monitors the input in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device checks the input as it goes along, and once a certain number of characters (e.g., three characters) have been entered, the input data is sent to the server.
[0953] The server sends the received input data to the generative AI model. Specifically, it calls OpenAI GPT-4 and sends a prompt saying, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates." Based on the input data and the prompt, the generative AI model references map information and generates candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo."
[0954] The server receives the candidate addresses returned by the generative AI model and sends them to the user's device. The user's device displays the received candidate addresses as a drop-down menu, allowing the user to select the correct address. The user selects the correct address from the drop-down menu, and the selected address is ultimately registered in the system. This series of steps minimizes delivery errors and increases user convenience.
[0955] 3. Specific Examples
[0956] Example of address input and candidate display
[0957] For example, if a user wants to register "Jinnan 1-chome, Shibuya-ku, Tokyo" on an online shopping site, the steps would be as follows:
[0958] 1. The user begins typing "Shibuya-ku, Tokyo" into the address input field.
[0959] 2. The user device detects this in real time and sends the data to the server.
[0960] 3. The server transfers this data to the generative AI model.
[0961] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[0962] 5. The server returns these candidate addresses to the terminal.
[0963] 6. The user device displays candidate addresses as a pull-down menu.
[0964] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" from the drop-down menu and finally registers the address.
[0965] In this way, by utilizing a generative AI model, users can input addresses accurately and quickly. An example of a prompt sentence is, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates."
[0966] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[0967] Step 1:
[0968] When a user starts typing characters into the address input field, the device monitors this input in real time. When three or more characters are entered into the input field, the device collects the input data. For example, if a user types "Shibu, Tokyo," the text data will be collected.
[0969] Step 2:
[0970] The device sends the collected input data to the server. Ajax or Fetch API is used to send the input data to the server as an HTTP POST request. Specifically, the data for "Shibu, Tokyo" is sent from the device to the server.
[0971] Step 3:
[0972] The server prepares to send the input data received from the device to the generative AI model. The server generates the input data as a prompt sentence and sends it to the generative AI. For example, a prompt sentence such as "The user has entered 'Shibu, Tokyo'. Please generate address candidates" is generated and sent to the generative AI model.
[0973] Step 4:
[0974] The generative AI model references a map information database based on the received prompt text and generates multiple address candidates. For example, candidates such as "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo" are generated. In this generation process, the input data is combined with map information to create a list of matching candidate addresses.
[0975] Step 5:
[0976] The server receives the candidate addresses generated by the generative AI model and processes them into JSON format. The server then sends the processed data to the user's device. For example, the generated address candidates are sent as {"addresses": ["Ebisu, Shibuya-ku, Tokyo", "Daikanyama, Shibuya-ku, Tokyo", "Shinsen, Shibuya-ku, Tokyo"]}.
[0977] Step 6:
[0978] The device analyzes the JSON format candidate address data received from the server and displays it as a pull-down menu. The user can select the appropriate address from the pull-down menu displayed at the bottom of the address input field. Specifically, the options are "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo."
[0979] Step 7:
[0980] The address selected by the user from the pull-down menu is automatically reflected in the input field and final registration is performed. The terminal then sends this selected address data back to the server and saves it in the database, allowing the user to register accurate address information.
[0981] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[0982] This invention is a system that, when a user changes their address online, presents correct address candidates based on generative AI and combines it with an emotion engine that recognizes the user's emotions, thereby preventing input errors and improving the user experience. The system is composed of a user terminal, a server, a generative AI model, and an emotion engine.
[0983] Natural language processing explanation
[0984] 1. User input detection
[0985] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[0986] 2. Send input data to the server
[0987] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[0988] 3. Data transfer to generative AI
[0989] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[0990] 4. Generate address candidates
[0991] The generative AI model generates candidate addresses from the input data based on map information. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[0992] 5. Emotion Recognition by Emotion Engine
[0993] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, for example, by determining their emotional state based on input speed, intervals, and frequency of input corrections.
[0994] 6. Server return of candidate data
[0995] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate addresses in JSON format to the device.
[0996] 7. Adjusting candidate priorities
[0997] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[0998] 8. Displaying the drop-down menu
[0999] The user's device analyzes the candidate address data received from the server and displays it as a pull-down menu. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are set and displayed in a pull-down menu.
[1000] 9. User Choices and Registration
[1001] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[1002] 10. Displaying Emotion-Based Guidance Messages
[1003] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if the emotion engine detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[1004] 11. Final Registration
[1005] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[1006] Specific examples
[1007] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," they would follow these steps:
[1008] 1. The user begins typing "Shibuya Ward, Tokyo."
[1009] 2. The device detects this input in real time and sends the data to the server.
[1010] 3. The server sends this data to a generative AI model to generate candidate addresses.
[1011] 4. The emotion engine analyzes the user's input patterns and recognizes their emotional state.
[1012] 5. The server sends the generated candidate addresses to the device and adjusts the priority based on the emotion.
[1013] 6. The terminal displays the candidate addresses as a pull-down menu.
[1014] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and the selection is reflected in the input field.
[1015] 8. The emotion engine displays guide messages according to the user's emotions.
[1016] 9. The user presses the submit button, the device sends the selected address to the server, and the address change is finally completed.
[1017] This series of steps allows users to change their address easily and accurately, and the system can provide a better user experience by taking user feelings into consideration.
[1018] The processing flow will be explained below.
[1019] Step 1:
[1020] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[1021] Step 2:
[1022] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[1023] Step 3:
[1024] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[1025] Step 4:
[1026] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[1027] Step 5:
[1028] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[1029] Step 6:
[1030] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[1031] Step 7:
[1032] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[1033] Step 8:
[1034] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[1035] Step 9:
[1036] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, determining their emotional state based on factors such as input speed, intervals, and frequency of input corrections.
[1037] Step 10:
[1038] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[1039] Step 11:
[1040] The device redisplays the adjusted candidate addresses as a drop-down menu, making it easier for the user to select from the displayed candidate addresses.
[1041] Step 12:
[1042] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal will update the input field with that information.
[1043] Step 13:
[1044] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if it detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[1045] Step 14:
[1046] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[1047] Example 2
[1048] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1049] In conventional address entry systems, users were prone to making mistakes when entering the correct address, and the entry process was cumbersome. This led to problems that reduced user satisfaction when changing their address. Furthermore, there was a lack of means to reduce the stress and frustration users felt when entering addresses.
[1050] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1051] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for an emotion engine to analyze and recognize the user's emotion, means for the generative AI model to generate address candidates based on map information, means for the server to transmit the generated candidate addresses to a user terminal, means for the server to adjust the priority of the candidate addresses based on the user's emotion, means for the user terminal to display the candidate addresses as a pull-down menu, means for the user terminal to finally register the address selected by the user from the pull-down menu, and means for the emotion engine to display a guide message as necessary. This allows the user to change their address quickly and accurately while preventing input errors, and further improves the user experience by providing guide messages that take the user's emotion into consideration.
[1052] "User" refers to an individual who uses the System to make a change of address.
[1053] An "input field" refers to a text box or form on a web page where a user can enter an address.
[1054] "Real-time" refers to a process that processes each user input immediately.
[1055] "Means for monitoring input content" refers to means for sequentially checking characters entered by a user into a text field and detecting changes in input.
[1056] "Entered Address Data" refers to address information entered by a user into an input field.
[1057] "Server" refers to the computer system responsible for receiving data sent from a user device and transmitting the data to the processing and generative AI model.
[1058] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze input data and generate appropriate address candidates.
[1059] "Map information" refers to information including geographical data and location information for generating address candidates.
[1060] "Emotion engine" refers to a software module for analyzing a user's input patterns and inferring the user's emotional state.
[1061] "Candidate addresses" refers to a list of candidate addresses generated by a generative AI model based on address data.
[1062] "Means for adjusting priority" refers to a function that changes the display order of candidate addresses generated based on the user's emotional data.
[1063] "Pull-down menu" refers to a drop-down menu that displays candidate addresses that a user can select from.
[1064] "Guide messages" refer to messages of assistance and advice provided by the system when the user is performing input tasks.
[1065] The present invention relates to a system that improves input accuracy and user experience when users change their address online, by integrating a generative AI model and an emotion engine. The system mainly consists of a user terminal, a server, a generative AI model, and an emotion engine.
[1066] 1. User Device
[1067] A user terminal is a device (such as a PC, smartphone, or tablet) that accesses the system through a web browser. When a user starts to enter text into an address input field on a web page, the terminal monitors the input in real time.
[1068] Specifically, when a user starts typing "Shibuya-ku, Tokyo," a JavaScript program on the device catches keyboard events and sequentially analyzes the input characters. The analysis results are prepared to be sent to the server as JSON-formatted data.
[1069] 2. Server
[1070] The server receives input data from the user device and sends it to the generative AI model. The server analyzes the received data and sends it to the generative AI model based on the appropriate prompt.
[1071] For example, the server might send the following prompt to the generative AI model:
[1072] "Generate suggestions based on the address entered by the user: Shibuya-ku, Tokyo."
[1073] 3. Generative AI Models
[1074] The generative AI model receives the prompt sent from the server and generates address candidates by referencing a map information database. The generative AI model uses a machine learning algorithm to analyze the input data and generate the optimal address candidates.
[1075] For example, candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," "Ebisu 1-chome, Shibuya-ku, Tokyo," etc. are generated. The generated results are sent back to the server.
[1076] 4. Emotion Engine
[1077] The emotion engine analyzes the user's input patterns (speed, frequency of corrections, etc.) and recognizes the user's emotional state in real time. If the emotion engine recognizes that the user is frustrated, the server adjusts the priority of candidate addresses.
[1078] For example, if the emotion engine detects irritation, it will instruct the server to display the simplest and most accurate candidate addresses at the top. It will also generate and send guide messages to the user's device as needed.
[1079] 5. Displaying the drop-down menu and final registration
[1080] The server sends the data received from the generative AI model and emotion engine to the user's device. The device analyzes the received candidate address data and displays it as a drop-down menu. If the user selects the correct address, that address is reflected in the input field. Finally, when the user presses the send button, the device sends the selected address data to the server, which then finally registers the data.
[1081] Specific examples
[1082] For example, if a user wants to register "Tokyo, Shibuya-ku, Jinnan 1-chome," the following steps are performed:
[1083] 1. The user begins typing "Shibuya-ku, Tokyo."
[1084] 2. The device detects the input content in real time and prepares to send the data to the server in JSON format.
[1085] 3. The server sends the received data to the generative AI model with the following prompt: "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[1086] 4. The generative AI model generates candidate addresses and sends them back to the server.
[1087] 5. The sentiment engine recognizes the user's sentiment and adjusts the priority of candidate addresses as needed.
[1088] 6. The server sends the generated candidate addresses to the user terminal.
[1089] 7. The device displays candidate addresses as a pull-down menu, and the user selects "Jinnan 1-chome, Shibuya-ku, Tokyo."
[1090] 8. If necessary, the emotion engine displays a guide message (e.g., "If you have any questions, please contact support").
[1091] 9. The user presses the send button, the terminal sends the selected address data to the server, and the server finally registers the address change.
[1092] Through the above process, users can quickly and accurately change their address, and the system can take users' feelings into consideration to provide a more comfortable user experience.
[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1094] System program processing flow
[1095] Step 1:
[1096] When a user starts to enter text into an address input field, the terminal monitors the input in real time. Specifically, it catches keyboard press events and acquires the entered characters sequentially. The input data is in text format, and each character is added to a variable in the terminal as it is entered. For example, if a user starts to enter "Shibuya-ku, Tokyo," the terminal stores this string in a variable.
[1097] Input: Each character the user types
[1098] Output: The input string updated in real time
[1099] Step 2:
[1100] When the entered data is three characters or more, the device converts the data to JSON format and prepares to send it to the server. Specifically, it uses JavaScript's JSON.stringify function to convert the input string to JSON format. For example, if "Shibuya-ku, Tokyo" is entered, it is converted to a JSON object called {"address": "Shibuya-ku, Tokyo"}.
[1101] Input: Real-time updated input string
[1102] Output: JSON format data {"address": "Shibuya-ku, Tokyo"}
[1103] Step 3:
[1104] The server analyzes the JSON data received from the device and generates a prompt to send to the generative AI model. Specifically, it analyzes the received data and constructs a prompt. For example, if the data received is {"address": "Shibuya-ku, Tokyo"}, it creates a prompt that reads, "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[1105] Input: JSON format data {"address": "Shibuya-ku, Tokyo"}
[1106] Output: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[1107] Step 4:
[1108] The generative AI model receives the prompt sent from the server and generates address candidates. The generative AI model references a map information database and generates the most suitable address candidate based on the prompt. For example, based on "Shibuya Ward, Tokyo," it generates candidates such as "Ato 1-chome, Shibuya Ward, Tokyo," "Jinnan 1-chome, Shibuya Ward, Tokyo," and "Ebisu 1-chome, Shibuya Ward, Tokyo."
[1109] Input: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[1110] Output: Candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1111] Step 5:
[1112] The emotion engine analyzes data such as the user's input speed and correction frequency to recognize the user's emotions. Based on these input parameters, the emotion engine infers the user's emotional state and identifies emotions such as "irritation," "confusion," and "normal."
[1113] Input: Data such as user typing speed and correction frequency
[1114] Output: User's emotional state (e.g., "irritated")
[1115] Step 6:
[1116] The server receives the candidate address data generated by the generative AI model, converts it to JSON format, and prepares to send it to the user's device. Specifically, the candidate address list is converted to JSON format using the JSON.stringify function. For example, the candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"] is converted to the JSON object {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}.
[1117] Input: Candidate Address List ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1118] Output: JSON format data {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[1119] Step 7:
[1120] The server adjusts the priority of candidate addresses based on the emotion data it receives. For example, if the emotion engine determines that the user is frustrated, it will prioritize the easiest and most reliable address candidates.
[1121] Input: Emotional state (e.g., "irritated"), candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1122] Output: Adjusted candidate address list ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1123] Step 8:
[1124] The user device analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, candidate addresses are extracted from the received JSON data and an HTML pull-down menu is dynamically generated.
[1125] Input: JSON format data {"candidates": ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[1126] Output: HTML element of the drop-down menu
[1127] Step 9:
[1128] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the selected address is reflected in the input field.
[1129] Input: User selection event
[1130] Output: The selected address is reflected in the input field.
[1131] Step 10:
[1132] If necessary, the emotion engine will display a guide message based on the user's emotions. For example, if the user feels confused, the message "If you have any questions, please contact support" will be displayed.
[1133] Input: User's emotional state (e.g., "confused")
[1134] Output: Display guide message
[1135] Step 11:
[1136] When the user confirms the input and presses the send button, the device sends the selected address data back to the server in JSON format. The server then registers the received data and the address change procedure is complete.
[1137] Input: Selected address data, Submit button click event
[1138] Output: Final registration completion notification
[1139] (Application example 2)
[1140] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."
[1141] In recent years, the number of online address change procedures has increased, but the tendency for users to make input errors during the process has become a problem. Furthermore, systems that do not consider the user's emotional state during operation can result in a poor user experience, making it difficult to enter information accurately, especially in stressful situations. Therefore, there is a need for a system that can prevent input errors when changing addresses and provide a better user experience by considering the user's emotional state.
[1142] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[1143] In this invention, the server is equipped with an emotion engine that analyzes a user's input operations and patterns to recognize emotions, and includes a means for adjusting the priority of candidate addresses based on the user's emotional state, a means for transmitting the input address data to the server, and a means for a generative AI model to generate address candidates based on map information. This allows users to change their address with peace of mind while preventing input errors. It also reduces user stress and confusion, promoting a comfortable user experience.
[1144] An "input field" is an interface for a user to enter data.
[1145] "Real-time" is a technical term that means that data processing and communication occurs immediately.
[1146] "Means for monitoring input content" refers to means for sequentially checking data entered by the user.
[1147] "Means for sending input data" refers to a mechanism for sending information entered by a user to an external system such as a server.
[1148] A "generative AI model" is an algorithm or system that uses machine learning or deep learning to generate data.
[1149] "Map information" refers to data that includes location information and geographical information.
[1150] A "means for generating candidates" is a mechanism for generating multiple options based on user input.
[1151] An "emotion engine" is a system or software that analyzes and recognizes a user's emotional state.
[1152] "Emotional state" refers to the user's psychological and emotional state.
[1153] The "means for adjusting priority" is a method for changing the order in which candidates are displayed depending on conditions or circumstances.
[1154] "Secure Method" refers to the technology and means used to securely transmit and store information.
[1155] The "means of final registration" is the method for determining the selected data and storing it in a database or system.
[1156] The system for implementing this invention is composed of a user terminal, a server, a generative AI model, and an emotion engine. Each component and their interactions will be described below.
[1157] System configuration
[1158] 1. User Device:
[1159] Provides an interface for the user to enter an address.
[1160] Its role is to monitor the input content in real time and send the address data to the server.
[1161] The user device is a smartphone (iOS / Android).
[1162] 2. Server:
[1163] Data received from the user device is sent to the generative AI model and emotion engine.
[1164] The priority of the candidate addresses is adjusted based on the generated candidate addresses and the user's sentiment information.
[1165] The adjusted data is then sent back to the user's device, and finally the address information selected by the user is securely stored.
[1166] The servers use cloud infrastructure (e.g., AWS or Google Cloud).
[1167] 3. Generative AI Model:
[1168] Based on partial address data entered by the user, map information is used to generate candidate addresses.
[1169] Generative AI models used include, for example, GPT-4.
[1170] 4. Emotion Engine:
[1171] Analyzes input operations and patterns to recognize the user's emotional state.
[1172] The analysis results are sent to the server and used to adjust the priority of the candidate addresses.
[1173] The emotion engine uses Affectiva and Microsoft Azure Emotion API.
[1174] Specific operation of each element
[1175] For example, if the user enters an address:
[1176] 1. The user begins typing "Shibuya-ku, Tokyo."
[1177] 2. The user's device detects this input in real time and sends it to the server when the input data reaches a certain number of characters (for example, three or more characters).
[1178] 3. The server forwards the received data to the generative AI model and generates a prompt. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: 'Shibuya-ku, Tokyo'."
[1179] 4. The generative AI model generates candidate addresses and sends the results back to the server.
[1180] 5. In parallel, the emotion engine analyzes the user's input pattern and speed, and transmits the user's emotional state to the server.
[1181] 6. The server adjusts the priority based on the generated candidate addresses and the analysis results of the emotion engine.
[1182] 7. The adjusted candidate addresses are sent to the user's terminal and displayed in a pull-down menu format.
[1183] 8. The user selects the appropriate address, which is finally sent securely to the server to complete the registration.
[1184] In this way, the system can prevent input errors when users go through the change of address process and provide a better user experience that takes into account the user's emotional state.
[1185] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1186] Step 1:
[1187] As users begin to type their address into the input field, the device monitors this input in real time, updating the data as each character is entered and retaining it until a certain number of characters is reached.
[1188] Step 2:
[1189] When the entered address data reaches a certain number of characters (for example, three or more characters), the terminal converts the data into JSON format and sends it to the server. The input data (for example, "Shibuya-ku, Tokyo") is processed into an appropriate format for transmission to the server.
[1190] Step 3:
[1191] The server receives the address data sent from the device and generates a prompt to send to the generative AI model. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: Shibuya-ku, Tokyo." This prompt is generated and sent to the generative AI model.
[1192] Step 4:
[1193] The generative AI model generates multiple candidate addresses based on the received prompt by referencing map information. Based on the input data, it generates a list of candidate addresses, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," and returns it to the server.
[1194] Step 5:
[1195] The server receives the candidate address list returned by the generative AI model and, in parallel, receives the user's input operation data analyzed by the emotion engine. The emotion engine analyzes the user's emotional state using data such as input speed and timing, and sends the results to the server.
[1196] Step 6:
[1197] The server adjusts the priority of candidate addresses based on the analysis results from the emotion engine. For example, if the user is feeling frustrated, it will prioritize more accurate and general candidates by placing them at the top of the list. The adjusted candidate address list is sent to the user's device in JSON format.
[1198] Step 7:
[1199] The terminal receives the adjusted candidate address list sent from the server and displays it in the user interface as a pull-down menu. The candidates are presented in list format to make selection easier for the user.
[1200] Step 8:
[1201] Once the user selects the correct address from the drop-down menu and confirms it, the device updates the input fields with the selected data. This final confirmation data is then reprocessed into JSON format and securely sent to the server.
[1202] Step 9:
[1203] The server receives the final address data sent by the user and stores it in the database. This completes the address change procedure, and a completion message is displayed to the user on the terminal.
[1204] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.
[1205] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[1206] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.
[1207] [Fourth embodiment]
[1208] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.
[1209] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.
[1210] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).
[1211] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.
[1212] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.
[1213] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).
[1214] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.
[1215] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.
[1216] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.
[1217] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.
[1218] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.
[1219] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.
[1220] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1221] This invention is a system that uses generative AI to present correct address candidates and prevent input errors when a user changes their address online. This system consists of a user terminal, a server, and a generative AI model. The program processing of this system is explained below in natural language.
[1222] Natural language processing explanation
[1223] 1. User input detection
[1224] When a user starts to enter characters into the address input field, the device monitors this entry in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check this entry as it goes along.
[1225] 2. Send input data to the server
[1226] When a user enters data of a certain number of characters or more (for example, three characters or more) into an input field, the device prepares a request to send this input data to the server. Specifically, it sends the input data to the server using Ajax or the Fetch API.
[1227] 3. Data transfer to generative AI
[1228] The server sends the input data received from the device to the generative AI model. For example, when the data "Shibuya-ku, Tokyo" arrives at the server, the server converts it into the required format and calls an API endpoint to send it to the generative AI model.
[1229] 4. Generate address candidates
[1230] The generative AI model generates candidate addresses by referencing map information based on the input data received from the server. Specifically, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[1231] 5. Server return of candidate data
[1232] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate data to the device in JSON format.
[1233] 6. Displaying the drop-down menu
[1234] The user's device analyzes the candidate data received from the server and displays it as a pull-down menu. For example, the device displays candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" in a pull-down menu.
[1235] 7. User Choices and Registration
[1236] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field of the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration.
[1237] Specific examples
[1238] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps would be as follows:
[1239] 1. The user begins typing "Shibuya Ward, Tokyo."
[1240] 2. The device detects this in real time and sends the data to the server.
[1241] 3. The server transfers this data to the generative AI model.
[1242] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[1243] 5. The server returns these candidates to the device.
[1244] 6. The terminal displays the candidate addresses as a pull-down menu.
[1245] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and finally registers.
[1246] This series of steps allows users to change their address easily and accurately.
[1247] The processing flow will be explained below.
[1248] Step 1:
[1249] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[1250] Step 2:
[1251] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[1252] Step 3:
[1253] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[1254] Step 4:
[1255] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[1256] Step 5:
[1257] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[1258] Step 6:
[1259] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[1260] Step 7:
[1261] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[1262] Step 8:
[1263] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[1264] Step 9:
[1265] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[1266] Step 10:
[1267] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data sent by the terminal and completes the address change procedure.
[1268] Example 1
[1269] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1270] Conventional address change systems have a high risk of users making input errors. Input errors are particularly likely when complex notations such as kanji characters and place names are involved, making it difficult to accurately register an address. Furthermore, appropriate candidate addresses are not presented promptly, often resulting in a poor user experience. There is a need for a system that can solve these problems and allow users to change their address easily and accurately.
[1271] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.
[1272] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for the generative AI model to generate address candidates based on map information, means for the server to return the candidate addresses generated by the generative AI model to the server, means for the server to transmit the generated candidate addresses to a user terminal, and means for the user terminal to display the candidate addresses as a pull-down menu and finally register the address selected by the user from the pull-down menu. This makes it easier for the user to refer to the candidate addresses when inputting an address, preventing incorrect input and enabling accurate address changes.
[1273] A "user terminal" is a device that provides an interface for a user to input an address, monitors the input content in real time, and communicates with the server.
[1274] The "server" is a device that receives address data sent from the user device, transfers it to the generative AI model, and returns the results to the user device.
[1275] An "input field" is an interface element such as a text box or input area into which a user enters an address.
[1276] A "generative AI model" is an algorithm or machine learning model that references map information based on input address data and generates candidate addresses.
[1277] "Map information" is a dataset that includes geographic address data and area information, and is the reference data used by generative AI models to generate address candidates.
[1278] A "pull-down menu" is a drop-down menu that is displayed on a user's terminal and allows the user to select from among candidate addresses.
[1279] A "prompt sentence" is a text sentence that contains instructions for the generative AI model to generate address candidates.
[1280] This invention is a system that uses a generative AI model to present correct address candidates and prevent input errors when a user changes their address online. The system consists of a user terminal, a server, and a generative AI model.
[1281] Hardware and Software
[1282] The user device can be a computer, smartphone, tablet, or other input device. The server is a high-performance computer system with an appropriate database and network connection. The generative AI model is software that implements machine learning algorithms to generate address candidates based on map information.
[1283] The terminal provides an address input interface using JavaScript, HTML, and CSS. Specifically, it implements a text input field, real-time input detection, and JavaScript functions for submitting input. Data is submitted using Ajax and the Fetch API.
[1284] The server is implemented using a server-side programming language such as Python, Java, or Node.js. The server forwards input data received from the device to the generative AI model and then sends the results back to the device. A RESTful API is used to send and receive data to the server.
[1285] The generative AI model is implemented in Python or other machine learning frameworks (e.g., TensorFlow or PyTorch). The model generates candidate addresses based on a prompt and returns the results in JSON format.
[1286] Specific examples of processing
[1287] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," the steps to follow are:
[1288] 1. The user begins typing "Shibuya Ward, Tokyo."
[1289] 2. The device detects the input content in real time and sends the data "Shibuya-ku, Tokyo" to the server.
[1290] 3. The server transfers this data to the generative AI model.
[1291] 4. The generative AI model generates candidate addresses using prompts like the following:
[1292] Generate address suggestions: List all addresses that match "Shibuya-ku, Tokyo."
[1293] 5. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" or "Jinnan 1-chome, Shibuya-ku, Tokyo" and sends them back to the server.
[1294] 6. The server returns these candidates to the device.
[1295] 7. The terminal displays the candidate addresses as a pull-down menu.
[1296] 8. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and presses the submit button to complete the final registration.
[1297] This system allows users to accurately register their address while checking candidate addresses, reducing input errors compared to conventional systems and enabling quick and accurate address changes.
[1298] The flow of the identification process in the first embodiment will be described with reference to FIG.
[1299] Step 1:
[1300] User starts typing
[1301] When the user starts typing characters into the address input field, the device monitors the input in real time. Specifically, using a JavaScript input event listener, the device captures the input as soon as the user starts typing "Tokyo". Input: "Tokyo". Output: "Tokyo"
[1302] Step 2:
[1303] Sending input data to the server
[1304] When the user enters a certain number of characters (e.g., 3 or more characters) in the input field, the device sends that data to the server. Specifically, it uses the JavaScript fetch API to send data to the server asynchronously. Input: "Tokyo". Output: Server send request (POST)
[1305] Step 3:
[1306] Receiving data on the server
[1307] The server receives the data sent from the device. It parses the received data into JSON format and prepares it for the next process. Input: "Tokyo" (JSON format). Output: "Tokyo" (structured data)
[1308] Step 4:
[1309] Data transfer to generative AI
[1310] The server sends the received data to the generative AI model. Specifically, it formats this data in a format that can be used by the generative AI model and forwards it as an API request. Input: "Tokyo" (structured data). Output: "Tokyo" (request to the generative AI model)
[1311] Step 5:
[1312] Generate address candidates
[1313] The generative AI model generates candidate addresses using prompts based on data sent from the server. For example, the prompt is "Generate address input candidates: List all addresses that match "Tokyo."" Input: "Tokyo" (request to the generative AI model). Output: "Chiyoda-ku, Tokyo," "Shibuya-ku, Tokyo" (candidate addresses)
[1314] Step 6:
[1315] Return candidate data to the server
[1316] The server receives address candidate data from the generative AI model and prepares to send the data to the user's device. The candidate data is converted to JSON format and sent back to the device via the server's API endpoint. Input: "Chiyoda-ku, Tokyo" and "Shibuya-ku, Tokyo" (candidate addresses). Output: Candidate address data (JSON format)
[1317] Step 7:
[1318] Displaying the drop-down menu
[1319] The terminal analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, it performs DOM manipulation using JavaScript to create a new <option>Create a tag and add it to the drop-down menu. Input: Candidate address data (JSON format). Output: Candidate addresses added to the drop-down menu
[1320] Step 8:
[1321] User Selection and Registration
[1322] The user selects the correct address from the pull-down menu. The selected address is reflected in the input field on the terminal. When the user finally presses the send button, the terminal sends the selected address data to the server and performs final registration. Input: Address selected by the user (e.g., "Shibuya-ku, Tokyo"). Output: Server transmission request (POST) for the selected address data
[1323] This series of steps allows users to change their address easily and accurately.
[1324] (Application example 1)
[1325] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1326] In conventional address entry systems, users frequently made input errors when manually entering addresses, resulting in incorrect delivery of goods and delivery delays. Furthermore, the input burden on users was high, making it difficult to provide a comfortable user experience. There is a need for a system that can solve these problems and support accurate and fast address entry.
[1327] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.
[1328] In this invention, the server includes a means for monitoring the input content in real time when a user begins to enter an address into an input field, a means for transmitting the entered address data to the server, and a means for the server to transmit the input data to a generative AI model. This allows the generative AI model to generate address candidates based on map information and prompt text, and transmits the candidate addresses to the user's terminal to display them as a pull-down menu, enabling the user to quickly enter an accurate address. Furthermore, by providing a means for finally registering the address selected by the user from the pull-down menu and reflecting it on the online shopping site, delivery errors can be significantly reduced and user convenience can be improved.
[1329] A "user terminal" is a device used by a user to enter an address, and may include a smartphone, tablet, or personal computer.
[1330] "Address data" is the address information that a user enters into an input field.
[1331] The "server" is a computer system that processes address data received from a user device and sends it to the generative AI model.
[1332] A "generative AI model" is an artificial intelligence model that generates address candidates by referencing map information and prompt text based on input data sent from the server.
[1333] "Map information" is a geographic database that the generative AI model references when generating address candidates.
[1334] A "prompt sentence" is auxiliary text that a generative AI model uses when generating address candidates.
[1335] A "pull-down menu" is an interface element that allows a user terminal to display generated candidate addresses in a user-selectable format.
[1336] "Candidate addresses" are multiple address suggestions for the user to choose from that are generated by the generative AI model based on input data.
[1337] "Finally registering" refers to the act of the user finalizing the candidate address selected from the pull-down menu and saving it in the system.
[1338] "Mail Order Site" means an online shopping platform that a user accesses to complete the purchase process for a product.
[1339] This invention is a system that uses a generative AI model to present accurate address candidates in real time when a user enters an address on an online shopping site, preventing input errors.
[1340] 1. System Configuration
[1341] The system consists of the following hardware and software:
[1342] User devices: Smartphones, tablets, personal computers, etc.
[1343] Server: Backend system using Node.js and Express.
[1344] Generative AI model: OpenAI GPT-4.
[1345] Database: MongoDB.
[1346] 2. Natural language description of the process
[1347] When a user starts to enter characters into an address input field, the user's device monitors the input in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device checks the input as it goes along, and once a certain number of characters (e.g., three characters) have been entered, the input data is sent to the server.
[1348] The server sends the received input data to the generative AI model. Specifically, it calls OpenAI GPT-4 and sends a prompt saying, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates." Based on the input data and the prompt, the generative AI model references map information and generates candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo."
[1349] The server receives the candidate addresses returned by the generative AI model and sends them to the user's device. The user's device displays the received candidate addresses as a drop-down menu, allowing the user to select the correct address. The user selects the correct address from the drop-down menu, and the selected address is ultimately registered in the system. This series of steps minimizes delivery errors and increases user convenience.
[1350] 3. Specific Examples
[1351] Example of address input and candidate display
[1352] For example, if a user wants to register "Jinnan 1-chome, Shibuya-ku, Tokyo" on an online shopping site, the steps would be as follows:
[1353] 1. The user begins typing "Shibuya-ku, Tokyo" into the address input field.
[1354] 2. The user device detects this in real time and sends the data to the server.
[1355] 3. The server transfers this data to the generative AI model.
[1356] 4. The generative AI model generates candidates such as "Ato 1-chome, Shibuya-ku, Tokyo" and "Jinnan 1-chome, Shibuya-ku, Tokyo."
[1357] 5. The server returns these candidate addresses to the terminal.
[1358] 6. The user device displays candidate addresses as a pull-down menu.
[1359] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" from the drop-down menu and finally registers the address.
[1360] In this way, by utilizing a generative AI model, users can input addresses accurately and quickly. An example of a prompt sentence is, "The user entered 'Shibuya-ku, Tokyo'. Please generate address candidates."
[1361] The flow of the specific processing in the application example 1 will be described with reference to FIG.
[1362] Step 1:
[1363] When a user starts typing characters into the address input field, the device monitors this input in real time. When three or more characters are entered into the input field, the device collects the input data. For example, if a user types "Shibu, Tokyo," the text data will be collected.
[1364] Step 2:
[1365] The device sends the collected input data to the server. Ajax or Fetch API is used to send the input data to the server as an HTTP POST request. Specifically, the data for "Shibu, Tokyo" is sent from the device to the server.
[1366] Step 3:
[1367] The server prepares to send the input data received from the device to the generative AI model. The server generates the input data as a prompt sentence and sends it to the generative AI. For example, a prompt sentence such as "The user has entered 'Shibu, Tokyo'. Please generate address candidates" is generated and sent to the generative AI model.
[1368] Step 4:
[1369] The generative AI model references a map information database based on the received prompt text and generates multiple address candidates. For example, candidates such as "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo" are generated. In this generation process, the input data is combined with map information to create a list of matching candidate addresses.
[1370] Step 5:
[1371] The server receives the candidate addresses generated by the generative AI model and processes them into JSON format. The server then sends the processed data to the user's device. For example, the generated address candidates are sent as {"addresses": ["Ebisu, Shibuya-ku, Tokyo", "Daikanyama, Shibuya-ku, Tokyo", "Shinsen, Shibuya-ku, Tokyo"]}.
[1372] Step 6:
[1373] The device analyzes the JSON format candidate address data received from the server and displays it as a pull-down menu. The user can select the appropriate address from the pull-down menu displayed at the bottom of the address input field. Specifically, the options are "Ebisu, Shibuya-ku, Tokyo," "Daikanyama, Shibuya-ku, Tokyo," and "Shinsen, Shibuya-ku, Tokyo."
[1374] Step 7:
[1375] The address selected by the user from the pull-down menu is automatically reflected in the input field and final registration is performed. The terminal then sends this selected address data back to the server and saves it in the database, allowing the user to register accurate address information.
[1376] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.
[1377] This invention is a system that, when a user changes their address online, presents correct address candidates based on generative AI and combines it with an emotion engine that recognizes the user's emotions, thereby preventing input errors and improving the user experience. The system is composed of a user terminal, a server, a generative AI model, and an emotion engine.
[1378] Natural language processing explanation
[1379] 1. User input detection
[1380] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[1381] 2. Send input data to the server
[1382] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[1383] 3. Data transfer to generative AI
[1384] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[1385] 4. Generate address candidates
[1386] The generative AI model generates candidate addresses from the input data based on map information. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[1387] 5. Emotion Recognition by Emotion Engine
[1388] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, for example, by determining their emotional state based on input speed, intervals, and frequency of input corrections.
[1389] 6. Server return of candidate data
[1390] The generative AI model returns the generated candidate address data to the server, which receives this data and prepares it for transmission to the user's device. The server then sends the candidate addresses in JSON format to the device.
[1391] 7. Adjusting candidate priorities
[1392] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[1393] 8. Displaying the drop-down menu
[1394] The user's device analyzes the candidate address data received from the server and displays it as a pull-down menu. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are set and displayed in a pull-down menu.
[1395] 9. User Choices and Registration
[1396] The user selects the correct address from the pull-down menu. If the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal updates the input field with that information.
[1397] 10. Displaying Emotion-Based Guidance Messages
[1398] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if the emotion engine detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[1399] 11. Final Registration
[1400] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[1401] Specific examples
[1402] For example, if a user wants to change their address to "Jinnan 1-chome, Shibuya-ku, Tokyo," they would follow these steps:
[1403] 1. The user begins typing "Shibuya Ward, Tokyo."
[1404] 2. The device detects this input in real time and sends the data to the server.
[1405] 3. The server sends this data to a generative AI model to generate candidate addresses.
[1406] 4. The emotion engine analyzes the user's input patterns and recognizes their emotional state.
[1407] 5. The server sends the generated candidate addresses to the device and adjusts the priority based on the emotion.
[1408] 6. The terminal displays the candidate addresses as a pull-down menu.
[1409] 7. The user selects "Jinnan 1-chome, Shibuya-ku, Tokyo" and the selection is reflected in the input field.
[1410] 8. The emotion engine displays guide messages according to the user's emotions.
[1411] 9. The user presses the submit button, the device sends the selected address to the server, and the address change is finally completed.
[1412] This series of steps allows users to change their address easily and accurately, and the system can provide a better user experience by taking user feelings into consideration.
[1413] The processing flow will be explained below.
[1414] Step 1:
[1415] When a user starts to enter characters into an address field, the device monitors this change in real time. For example, if a user starts to enter "Shibuya-ku, Tokyo," the device will check the input content as it progresses.
[1416] Step 2:
[1417] When the entered data reaches a specified number of characters (for example, three or more characters), the device begins preparing to send the data to the server. Specifically, it formats the data appropriately.
[1418] Step 3:
[1419] The data prepared by the device is sent to the server using Ajax or Fetch API. The data sent is, for example, the string "Shibuya-ku, Tokyo."
[1420] Step 4:
[1421] The server receives the data from the device and prepares it for transmission to the generative AI model. Specifically, it converts the data into an appropriate format and sends it to the generative AI model.
[1422] Step 5:
[1423] The server sends the converted data to the generative AI model, which generates candidate addresses from the input data based on map information.
[1424] Step 6:
[1425] The generative AI model generates candidate addresses and sends the results back to the server. For example, candidates such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo" are generated.
[1426] Step 7:
[1427] The server analyzes the candidate addresses received from the generation AI model and prepares them for transmission to the user's device. The server sends the candidate addresses to the device in JSON format or similar.
[1428] Step 8:
[1429] The device analyzes the candidate address data received from the server and displays it as a pull-down menu to the user. Specifically, the device sets the addresses received, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," in the pull-down menu.
[1430] Step 9:
[1431] The emotion engine analyzes the user's input actions and patterns to recognize the user's emotions in real time, determining their emotional state based on factors such as input speed, intervals, and frequency of input corrections.
[1432] Step 10:
[1433] The server receives information from the emotion engine and adjusts the priority of the suggested addresses based on the user's emotions. For example, if data indicating frustration is detected, simpler and more accurate suggestions will be ranked higher.
[1434] Step 11:
[1435] The device redisplays the adjusted candidate addresses as a drop-down menu, making it easier for the user to select from the displayed candidate addresses.
[1436] Step 12:
[1437] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the terminal will update the input field with that information.
[1438] Step 13:
[1439] If necessary, the emotion engine will determine the user's state of mind and display a guide message. For example, if it detects that the user is confused, it will display a message such as "If you have any questions, please contact support."
[1440] Step 14:
[1441] When the user confirms the input and presses the send button, the terminal sends the selected address data to the server, which then registers the data and completes the address change procedure.
[1442] Example 2
[1443] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1444] In conventional address entry systems, users were prone to making mistakes when entering the correct address, and the entry process was cumbersome. This led to problems that reduced user satisfaction when changing their address. Furthermore, there was a lack of means to reduce the stress and frustration users felt when entering addresses.
[1445] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.
[1446] In this invention, the server includes means for monitoring the input content in real time when a user starts to input an address into an input field, means for transmitting the input address data to the server, means for the server to transmit the input data to a generative AI model, means for an emotion engine to analyze and recognize the user's emotion, means for the generative AI model to generate address candidates based on map information, means for the server to transmit the generated candidate addresses to a user terminal, means for the server to adjust the priority of the candidate addresses based on the user's emotion, means for the user terminal to display the candidate addresses as a pull-down menu, means for the user terminal to finally register the address selected by the user from the pull-down menu, and means for the emotion engine to display a guide message as necessary. This allows the user to change their address quickly and accurately while preventing input errors, and further improves the user experience by providing guide messages that take the user's emotion into consideration.
[1447] "User" refers to an individual who uses the System to make a change of address.
[1448] An "input field" refers to a text box or form on a web page where a user can enter an address.
[1449] "Real-time" refers to a process that processes each user input immediately.
[1450] "Means for monitoring input content" refers to means for sequentially checking characters entered by a user into a text field and detecting changes in input.
[1451] "Entered Address Data" refers to address information entered by a user into an input field.
[1452] "Server" refers to the computer system responsible for receiving data sent from a user device and transmitting the data to the processing and generative AI model.
[1453] "Generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to analyze input data and generate appropriate address candidates.
[1454] "Map information" refers to information including geographical data and location information for generating address candidates.
[1455] "Emotion engine" refers to a software module for analyzing a user's input patterns and inferring the user's emotional state.
[1456] "Candidate addresses" refers to a list of candidate addresses generated by a generative AI model based on address data.
[1457] "Means for adjusting priority" refers to a function that changes the display order of candidate addresses generated based on the user's emotional data.
[1458] "Pull-down menu" refers to a drop-down menu that displays candidate addresses that a user can select from.
[1459] "Guide messages" refer to messages of assistance and advice provided by the system when the user is performing input tasks.
[1460] The present invention relates to a system that improves input accuracy and user experience when users change their address online, by integrating a generative AI model and an emotion engine. The system mainly consists of a user terminal, a server, a generative AI model, and an emotion engine.
[1461] 1. User Device
[1462] A user terminal is a device (such as a PC, smartphone, or tablet) that accesses the system through a web browser. When a user starts to enter text into an address input field on a web page, the terminal monitors the input in real time.
[1463] Specifically, when a user starts typing "Shibuya-ku, Tokyo," a JavaScript program on the device catches keyboard events and sequentially analyzes the input characters. The analysis results are prepared to be sent to the server as JSON-formatted data.
[1464] 2. Server
[1465] The server receives input data from the user device and sends it to the generative AI model. The server analyzes the received data and sends it to the generative AI model based on the appropriate prompt.
[1466] For example, the server might send the following prompt to the generative AI model:
[1467] "Generate suggestions based on the address entered by the user: Shibuya-ku, Tokyo."
[1468] 3. Generative AI Models
[1469] The generative AI model receives the prompt sent from the server and generates address candidates by referencing a map information database. The generative AI model uses a machine learning algorithm to analyze the input data and generate the optimal address candidates.
[1470] For example, candidate addresses such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," "Ebisu 1-chome, Shibuya-ku, Tokyo," etc. are generated. The generated results are sent back to the server.
[1471] 4. Emotion Engine
[1472] The emotion engine analyzes the user's input patterns (speed, frequency of corrections, etc.) and recognizes the user's emotional state in real time. If the emotion engine recognizes that the user is frustrated, the server adjusts the priority of candidate addresses.
[1473] For example, if the emotion engine detects irritation, it will instruct the server to display the simplest and most accurate candidate addresses at the top. It will also generate and send guide messages to the user's device as needed.
[1474] 5. Displaying the drop-down menu and final registration
[1475] The server sends the data received from the generative AI model and emotion engine to the user's device. The device analyzes the received candidate address data and displays it as a drop-down menu. If the user selects the correct address, that address is reflected in the input field. Finally, when the user presses the send button, the device sends the selected address data to the server, which then finally registers the data.
[1476] Specific examples
[1477] For example, if a user wants to register "Tokyo, Shibuya-ku, Jinnan 1-chome," the following steps are performed:
[1478] 1. The user begins typing "Shibuya-ku, Tokyo."
[1479] 2. The device detects the input content in real time and prepares to send the data to the server in JSON format.
[1480] 3. The server sends the received data to the generative AI model with the following prompt: "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[1481] 4. The generative AI model generates candidate addresses and sends them back to the server.
[1482] 5. The sentiment engine recognizes the user's sentiment and adjusts the priority of candidate addresses as needed.
[1483] 6. The server sends the generated candidate addresses to the user terminal.
[1484] 7. The device displays candidate addresses as a pull-down menu, and the user selects "Jinnan 1-chome, Shibuya-ku, Tokyo."
[1485] 8. If necessary, the emotion engine displays a guide message (e.g., "If you have any questions, please contact support").
[1486] 9. The user presses the send button, the terminal sends the selected address data to the server, and the server finally registers the address change.
[1487] Through the above process, users can quickly and accurately change their address, and the system can take users' feelings into consideration to provide a more comfortable user experience.
[1488] The flow of the identification process in the second embodiment will be described with reference to FIG.
[1489] System program processing flow
[1490] Step 1:
[1491] When a user starts to enter text into an address input field, the terminal monitors the input in real time. Specifically, it catches keyboard press events and acquires the entered characters sequentially. The input data is in text format, and each character is added to a variable in the terminal as it is entered. For example, if a user starts to enter "Shibuya-ku, Tokyo," the terminal stores this string in a variable.
[1492] Input: Each character the user types
[1493] Output: The input string updated in real time
[1494] Step 2:
[1495] When the entered data is three characters or more, the device converts the data to JSON format and prepares to send it to the server. Specifically, it uses JavaScript's JSON.stringify function to convert the input string to JSON format. For example, if "Shibuya-ku, Tokyo" is entered, it is converted to a JSON object called {"address": "Shibuya-ku, Tokyo"}.
[1496] Input: Real-time updated input string
[1497] Output: JSON format data {"address": "Shibuya-ku, Tokyo"}
[1498] Step 3:
[1499] The server analyzes the JSON data received from the device and generates a prompt to send to the generative AI model. Specifically, it analyzes the received data and constructs a prompt. For example, if the data received is {"address": "Shibuya-ku, Tokyo"}, it creates a prompt that reads, "Generate candidates based on the address 'Shibuya-ku, Tokyo' entered by the user."
[1500] Input: JSON format data {"address": "Shibuya-ku, Tokyo"}
[1501] Output: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[1502] Step 4:
[1503] The generative AI model receives the prompt sent from the server and generates address candidates. The generative AI model references a map information database and generates the most suitable address candidate based on the prompt. For example, based on "Shibuya Ward, Tokyo," it generates candidates such as "Ato 1-chome, Shibuya Ward, Tokyo," "Jinnan 1-chome, Shibuya Ward, Tokyo," and "Ebisu 1-chome, Shibuya Ward, Tokyo."
[1504] Input: Prompt text "Generate candidates based on the address entered by the user: Shibuya-ku, Tokyo"
[1505] Output: Candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1506] Step 5:
[1507] The emotion engine analyzes data such as the user's input speed and correction frequency to recognize the user's emotions. Based on these input parameters, the emotion engine infers the user's emotional state and identifies emotions such as "irritation," "confusion," and "normal."
[1508] Input: Data such as user typing speed and correction frequency
[1509] Output: User's emotional state (e.g., "irritated")
[1510] Step 6:
[1511] The server receives the candidate address data generated by the generative AI model, converts it to JSON format, and prepares to send it to the user's device. Specifically, the candidate address list is converted to JSON format using the JSON.stringify function. For example, the candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"] is converted to the JSON object {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}.
[1512] Input: Candidate Address List ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1513] Output: JSON format data {"candidates": ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[1514] Step 7:
[1515] The server adjusts the priority of candidate addresses based on the emotion data it receives. For example, if the emotion engine determines that the user is frustrated, it will prioritize the easiest and most reliable address candidates.
[1516] Input: Emotional state (e.g., "irritated"), candidate address list ["Ato 1-chome, Shibuya-ku, Tokyo", "Jinnan 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1517] Output: Adjusted candidate address list ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]
[1518] Step 8:
[1519] The user device analyzes the candidate address data received from the server and displays it as a pull-down menu. Specifically, candidate addresses are extracted from the received JSON data and an HTML pull-down menu is dynamically generated.
[1520] Input: JSON format data {"candidates": ["Jinnan 1-chome, Shibuya-ku, Tokyo", "Ato 1-chome, Shibuya-ku, Tokyo", "Ebisu 1-chome, Shibuya-ku, Tokyo"]}
[1521] Output: HTML element of the drop-down menu
[1522] Step 9:
[1523] The user selects the correct address from the pull-down menu. For example, if the user selects "Tokyo, Shibuya-ku, Jinnan 1-chome," the selected address is reflected in the input field.
[1524] Input: User selection event
[1525] Output: The selected address is reflected in the input field.
[1526] Step 10:
[1527] If necessary, the emotion engine will display a guide message based on the user's emotions. For example, if the user feels confused, the message "If you have any questions, please contact support" will be displayed.
[1528] Input: User's emotional state (e.g., "confused")
[1529] Output: Display guide message
[1530] Step 11:
[1531] When the user confirms the input and presses the send button, the device sends the selected address data back to the server in JSON format. The server then registers the received data and the address change procedure is complete.
[1532] Input: Selected address data, Submit button click event
[1533] Output: Final registration completion notification
[1534] (Application example 2)
[1535] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."
[1536] In recent years, the number of online address change procedures has increased, but the tendency for users to make input errors during the process has become a problem. Furthermore, systems that do not consider the user's emotional state during operation can result in a poor user experience, making it difficult to enter information accurately, especially in stressful situations. Therefore, there is a need for a system that can prevent input errors when changing addresses and provide a better user experience by considering the user's emotional state.
[1537] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.
[1538] In this invention, the server is equipped with an emotion engine that analyzes a user's input operations and patterns to recognize emotions, and includes a means for adjusting the priority of candidate addresses based on the user's emotional state, a means for transmitting the input address data to the server, and a means for a generative AI model to generate address candidates based on map information. This allows users to change their address with peace of mind while preventing input errors. It also reduces user stress and confusion, promoting a comfortable user experience.
[1539] An "input field" is an interface for a user to enter data.
[1540] "Real-time" is a technical term that means that data processing and communication occurs immediately.
[1541] "Means for monitoring input content" refers to means for sequentially checking data entered by the user.
[1542] "Means for sending input data" refers to a mechanism for sending information entered by a user to an external system such as a server.
[1543] A "generative AI model" is an algorithm or system that uses machine learning or deep learning to generate data.
[1544] "Map information" refers to data that includes location information and geographical information.
[1545] A "means for generating candidates" is a mechanism for generating multiple options based on user input.
[1546] An "emotion engine" is a system or software that analyzes and recognizes a user's emotional state.
[1547] "Emotional state" refers to the user's psychological and emotional state.
[1548] The "means for adjusting priority" is a method for changing the order in which candidates are displayed depending on conditions or circumstances.
[1549] "Secure Method" refers to the technology and means used to securely transmit and store information.
[1550] The "means of final registration" is the method for determining the selected data and storing it in a database or system.
[1551] The system for implementing this invention is composed of a user terminal, a server, a generative AI model, and an emotion engine. Each component and their interactions will be described below.
[1552] System configuration
[1553] 1. User Device:
[1554] Provides an interface for the user to enter an address.
[1555] Its role is to monitor the input content in real time and send the address data to the server.
[1556] The user device is a smartphone (iOS / Android).
[1557] 2. Server:
[1558] Data received from the user device is sent to the generative AI model and emotion engine.
[1559] The priority of the candidate addresses is adjusted based on the generated candidate addresses and the user's sentiment information.
[1560] The adjusted data is then sent back to the user's device, and finally the address information selected by the user is securely stored.
[1561] The servers use cloud infrastructure (e.g., AWS or Google Cloud).
[1562] 3. Generative AI Model:
[1563] Based on partial address data entered by the user, map information is used to generate candidate addresses.
[1564] Generative AI models used include, for example, GPT-4.
[1565] 4. Emotion Engine:
[1566] Analyzes input operations and patterns to recognize the user's emotional state.
[1567] The analysis results are sent to the server and used to adjust the priority of the candidate addresses.
[1568] The emotion engine uses Affectiva and Microsoft Azure Emotion API.
[1569] Specific operation of each element
[1570] For example, if the user enters an address:
[1571] 1. The user begins typing "Shibuya-ku, Tokyo."
[1572] 2. The user's device detects this input in real time and sends it to the server when the input data reaches a certain number of characters (for example, three or more characters).
[1573] 3. The server forwards the received data to the generative AI model and generates a prompt. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: 'Shibuya-ku, Tokyo'."
[1574] 4. The generative AI model generates candidate addresses and sends the results back to the server.
[1575] 5. In parallel, the emotion engine analyzes the user's input pattern and speed, and transmits the user's emotional state to the server.
[1576] 6. The server adjusts the priority based on the generated candidate addresses and the analysis results of the emotion engine.
[1577] 7. The adjusted candidate addresses are sent to the user's terminal and displayed in a pull-down menu format.
[1578] 8. The user selects the appropriate address, which is finally sent securely to the server to complete the registration.
[1579] In this way, the system can prevent input errors when users go through the change of address process and provide a better user experience that takes into account the user's emotional state.
[1580] The flow of the specific processing in the application example 2 will be described with reference to FIG.
[1581] Step 1:
[1582] As users begin to type their address into the input field, the device monitors this input in real time, updating the data as each character is entered and retaining it until a certain number of characters is reached.
[1583] Step 2:
[1584] When the entered address data reaches a certain number of characters (for example, three or more characters), the terminal converts the data into JSON format and sends it to the server. The input data (for example, "Shibuya-ku, Tokyo") is processed into an appropriate format for transmission to the server.
[1585] Step 3:
[1586] The server receives the address data sent from the device and generates a prompt to send to the generative AI model. For example, the prompt might be, "The user is trying to change their address. Please predict the address that may follow the following string: Shibuya-ku, Tokyo." This prompt is generated and sent to the generative AI model.
[1587] Step 4:
[1588] The generative AI model generates multiple candidate addresses based on the received prompt by referencing map information. Based on the input data, it generates a list of candidate addresses, such as "Ato 1-chome, Shibuya-ku, Tokyo," "Jinnan 1-chome, Shibuya-ku, Tokyo," and "Ebisu 1-chome, Shibuya-ku, Tokyo," and returns it to the server.
[1589] Step 5:
[1590] The server receives the candidate address list returned by the generative AI model and, in parallel, receives the user's input operation data analyzed by the emotion engine. The emotion engine analyzes the user's emotional state using data such as input speed and timing, and sends the results to the server.
[1591] Step 6:
[1592] The server adjusts the priority of candidate addresses based on the analysis results from the emotion engine. For example, if the user is feeling frustrated, it will prioritize more accurate and general candidates by placing them at the top of the list. The adjusted candidate address list is sent to the user's device in JSON format.
[1593] Step 7:
[1594] The terminal receives the adjusted candidate address list sent from the server and displays it in the user interface as a pull-down menu. The candidates are presented in list format to make selection easier for the user.
[1595] Step 8:
[1596] Once the user selects the correct address from the drop-down menu and confirms it, the device updates the input fields with the selected data. This final confirmation data is then reprocessed into JSON format and securely sent to the server.
[1597] Step 9:
[1598] The server receives the final address data sent by the user and stores it in the database. This completes the address change procedure, and a completion message is displayed to the user on the terminal.
[1599] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.
[1600] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.
[1601] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.
[1602] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.
[1603] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.
[1604] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.
[1605] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).
[1606] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.
[1607] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."
[1608] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.
[1609] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).
[1610] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.
[1611] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.
[1612] 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.
[1613] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.
[1614] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.
[1615] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.
[1616] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.
[1617] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.
[1618] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.
[1619] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.
[1620] The following is further disclosed regarding the above embodiment.
[1621] (Claim 1)
[1622] A means of monitoring the input in real time as the user begins to enter an address into the input field; and
[1623] means for transmitting the input address data to a server;
[1624] a means for the server to send input data to the generative AI model;
[1625] A means for the generative AI model to generate address candidates based on map information;
[1626] A means for the server to transmit the generated candidate addresses to the user terminal;
[1627] A means for the user terminal to display candidate addresses as a pull-down menu;
[1628] A means for the user to finally register the address selected from the drop-down menu;
[1629] A system including:
[1630] (Claim 2)
[1631] 2. The system according to claim 1, further comprising means for satisfying a condition for sending address data to a server when the address data entered by a user in an input field reaches a specific number of characters.
[1632] (Claim 3)
[1633] The system according to claim 1, wherein the generation AI model comprises means for generating candidate addresses by referring to Yahoo! map information.
[1634] "Example 1"
[1635] (Claim 1)
[1636] A means of monitoring the input in real time as the user begins to enter an address into the input field; and
[1637] means for transmitting the input address data to a server;
[1638] a means for the server to send input data to the generative AI model;
[1639] A means for the generative AI model to generate address candidates based on map information;
[1640] A means for returning the candidate addresses generated by the generative AI model to the server;
[1641] A means for the server to transmit the generated candidate addresses to a user terminal;
[1642] A means for a user terminal to display candidate addresses as a pull-down menu and for a user to finally register an address selected from the pull-down menu;
[1643] A system including:
[1644] (Claim 2)
[1645] 2. The system according to claim 1, further comprising means for satisfying a condition for sending address data to a server when the address data entered by a user in an input field reaches a specific number of characters.
[1646] (Claim 3)
[1647] 10. The system of claim 1, wherein the generative AI model comprises means for using prompt sentences to generate candidate addresses by referencing map information.
[1648] "Application Example 1"
[1649] (Claim 1)
[1650] A means of monitoring the input in real time as the user begins to enter an address into the input field; and
[1651] means for transmitting the input address data to a server;
[1652] a means for the server to send input data to the generative AI model;
[1653] A means for the generative AI model to generate address candidates based on map information and prompt text;
[1654] A means for the server to transmit the generated candidate addresses to the user terminal;
[1655] A means for the user terminal to display candidate addresses as a pull-down menu;
[1656] A way for users to finally register the address they selected from the drop-down menu and reflect it on the online shopping site,
[1657] A system including:
[1658] (Claim 2)
[1659] 2. The system according to claim 1, further comprising means for satisfying a condition for sending address data to a server when the address data entered by a user in an input field reaches a specific number of characters.
[1660] (Claim 3)
[1661] 2. The system of claim 1, wherein the generative AI model comprises means for generating candidate addresses by referencing a general-purpose map database.
[1662] "Example 2: Combining Emotion Engines"
[1663] (Claim 1)
[1664] A means of monitoring the input in real time as the user begins to enter an address into the input field; and
[1665] means for transmitting the input address data to a server;
[1666] a means for the server to send input data to the generative AI model;
[1667] A means for the generative AI model to generate address candidates based on map information;
[1668] A means for the emotion engine to analyze and recognize the user's emotions;
[1669] A means for the server to transmit the generated candidate addresses to the user terminal;
[1670] A means for the server to adjust the priority of candidate addresses based on user sentiment;
[1671] A means for the user terminal to display candidate addresses as a pull-down menu;
[1672] A means for the user to finally register the address selected from the drop-down menu;
[1673] A means for the emotion engine to display guide messages as needed;
[1674] A system including:
[1675] (Claim 2)
[1676] 2. The system according to claim 1, further comprising means for satisfying a condition for sending address data to a server when the address data entered by a user in an input field reaches a specific number of characters.
[1677] (Claim 3)
[1678] The system of claim 1, further comprising means for generating candidate addresses by referencing a map information database.
[1679] "Application example 2 when combining emotion engines"
[1680] (Claim 1)
[1681] a means for monitoring the address entry in real time as the user begins to enter the address in the input field;
[1682] means for transmitting the input address data to a server;
[1683] a means for the server to send input data to the generative AI model;
[1684] A means for the generative AI model to generate address candidates based on map information;
[1685] A means for the server to transmit the generated candidate addresses to the user terminal;
[1686] A means for the user terminal to display candidate addresses as a pull-down menu;
[1687] A means for the user to finally register the address selected from the drop-down menu;
[1688] an emotion engine that analyzes user input operations and patterns to recognize emotions, and a means for adjusting the priority of candidate addresses based on the user's emotional state;
[1689] means for ensuring that the selected address is ultimately transmitted to a server in a secure manner;
[1690] A system including:
[1691] (Claim 2)
[1692] 2. The system according to claim 1, further comprising means for satisfying a condition for sending address data to a server when the address data entered by a user in an input field reaches a specific number of characters.
[1693] (Claim 3)
[1694] The system according to claim 1, further comprising a means for generating candidate addresses by referring to map information. [Explanation of symbols]
[1695] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / option> < / url:> < / option> < / url:> < / option> < / url:> < / option>
Claims
1. A means of monitoring the input in real time as the user begins to enter an address into the input field; and means for transmitting the input address data to a server; a means for the server to send input data to the generative AI model; A means for the generative AI model to generate address candidates based on map information; A means for the server to transmit the generated candidate addresses to the user terminal; A means for the user terminal to display candidate addresses as a pull-down menu; A means for the user to finally register the address selected from the drop-down menu; A system including:
2. 2. The system according to claim 1, further comprising means for satisfying a condition for sending address data to a server when the address data entered by a user in the input field reaches a specific number of characters.
3. The system according to claim 1, further comprising a means for generating candidate addresses by referring to Yahoo! Map Information.
Citation Information
Patent Citations
Persona chatbot control method and system
JP2022180282A