system

Abstract

We provide the system. [Solution] An information processing device that uses a generative model to improve the efficiency of business operations, A database means for collecting and storing information related to business operations, A learning method for training a generative model, A response means that generates a response via an international information and communication network and provides information to user equipment, A terminal device that accepts user input and presents answers through visual display, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional business processes, there are diverse and complex contract forms, and the handling of these often depends on the experience and knowledge of specific individuals, resulting in problems such as a decline in work efficiency and personalization. Furthermore, it is difficult for inexperienced personnel to handle, which has become a factor hindering the growth of the entire organization.

Means for Solving the Problems

[0005] This invention provides a system that streamlines tasks that were previously dependent on individual employees by utilizing a generative model and a database for collecting and storing business-related data. This enables quick and accurate responses to user inquiries by leveraging the response capabilities of the learned generative model. Furthermore, since the generative model is continuously optimized using data and feedback, the efficiency and accuracy of operations can be improved.

[0006] A "generative model" refers to an algorithm that creates new information or answers from given data, and specifically includes techniques for natural language generation.

[0007] An "information processing device" refers to a computer system used for collecting, storing, processing, and outputting data.

[0008] "Database means" refers to a configuration of software and hardware for systematically collecting and storing information, facilitating data management and access.

[0009] "Learning methods" refer to the processes and algorithms necessary to train a generative model based on collected data.

[0010] "Response mechanism" refers to a function that processes user inquiries and generates appropriate answers based on their content.

[0011] A "user interface" refers to the visual or manipulative methods of interaction that enable a user to effectively interact with a system.

[0012] "Optimization" refers to the process of adjusting a system or model to improve its performance based on feedback and new data. [Brief explanation of the drawing]

[0013] [Figure 1]This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and 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), or Bluetooth (registered trademark), and the like. [[ID=,20]]

[0020] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0024] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0025] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0026] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0027] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0028] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0031] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0032] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0033] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0034] This invention is an information processing system that streamlines business processes using a generative model. This system is realized through collaborative interaction between a server, a terminal, and a user.

[0035] Server operation

[0036] The server begins by collecting business-related data and storing it structured in a database. This data includes past interaction history, FAQs, and contract templates. Based on this data, the server trains a generative model to acquire knowledge capable of handling diverse business scenarios. During the training process, natural language processing techniques are used to optimize the model so that it can respond appropriately to inquiries.

[0037] Terminal operation

[0038] The terminal serves to provide an interface for user access. Through this interface, users can input specific questions regarding contractual matters. The terminal sends the entered questions to the server and uses an API to quickly retrieve the answers. The terminal receives the answers from the server and displays them clearly for the user.

[0039] User actions

[0040] Through this interface, users enter questions and uncertainties regarding their contracts. For example, if a user asks, "How do I renew my contract?", the terminal sends this information to the server. The server responds to the inquiry using a generative model and sends a specific answer, such as, "To renew your contract, you need to prepare certain documents and confirm their approval." Based on this answer, the user can quickly proceed with the necessary procedures.

[0041] In this way, servers, terminals, and users collaborate with each other, leveraging the power of generative models to improve operational efficiency. As a result, it becomes possible to significantly improve issues such as reliance on individual employees and operational efficiency, and the ability to respond to new inquiries is also enhanced.

[0042] The following describes the processing flow.

[0043] Step 1:

[0044] The server collects existing business-related data from internal systems and external databases, and organizes and structures it as digital data. This data includes past case studies, FAQs, and contract templates.

[0045] Step 2:

[0046] The server uses the collected data to build a database and trains a generative model. It employs natural language processing techniques to tokenize and normalize text data, learning knowledge related to contractual work.

[0047] Step 3:

[0048] The server has the ability to periodically update newly trained models. This includes retraining the model based on the latest data and adjusting its parameters.

[0049] Step 4:

[0050] The device provides a user-accessible interface. This interface is in a chatbot format and is designed to simplify user interaction.

[0051] Step 5:

[0052] The user enters questions about the contract and procedures through the terminal's interface. The entered questions are sent from the terminal to the server as string data.

[0053] Step 6:

[0054] The server analyzes the questions received from the user and inputs them into a generative model. The model then generates the optimal response based on this information, and the results are processed within the server.

[0055] Step 7:

[0056] The server sends the generated response back to the terminal and presents it to the user. This response contains specific instructions and related information.

[0057] Step 8:

[0058] Users refer to the responses provided to plan their business decisions and next actions. They can also ask additional questions as needed.

[0059] Through this series of processing steps, the system enables efficient task execution and helps users quickly obtain the information they need.

[0060] (Example 1)

[0061] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0062] Conventional information processing systems have struggled to respond smoothly and appropriately to inquiries related to business operations, often leading to reliance on individual expertise and decreased operational efficiency. Furthermore, while organizing vast amounts of business data and providing rapid responses are essential for improving the quality of responses to inquiries, there has been a lack of effective means to achieve these goals.

[0063] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0064] In this invention, the server includes data storage means for collecting and structuring business-related information, model generation means for machine learning information using a generative model, and response generation means for receiving user inquiries and generating responses using the generative model. This enables rapid and accurate responses to user inquiries, eliminates reliance on individual expertise in business operations, and realizes efficient business processes.

[0065] "Business-related information" refers to data such as history, documents, and templates that are necessary or useful for a specific business process.

[0066] "Data storage means" refers to a system or device for collecting, structuring, and storing information related to business operations.

[0067] A "generative model" refers to artificial intelligence technology that learns from given data and generates appropriate responses to inquiries.

[0068] "Model generation means" refers to a system or device that uses a generative model to learn information and improve its ability to respond to inquiries.

[0069] "Response generation means" refers to a system or device that generates a response using a generation model based on an inquiry received from a user.

[0070] A "user interface" refers to the software and hardware that provide the interaction a user can use to access, operate, and inquire about a system.

[0071] "Communication means" refers to a network or protocol used to send and receive information between a server and a user interface.

[0072] "Display control means" refers to software or hardware that displays the results generated by the response generation means in a way that is easy for the user to understand.

[0073] "Optimization means" refers to a mechanism that continuously improves the performance of a generative model using business-related data and user feedback.

[0074] To implement this invention, it is necessary to build a system in which a server, terminal, and user work in cooperation. The server collects business-related information and stores it in a database, thereby systematically organizing the information. Specifically, it uses a database management system such as MySQL® or PostgreSQL to store the information. This makes it possible to efficiently manage past interaction history, FAQs, contract templates, and so on.

[0075] Next, the server uses the collected information to leverage a generative model to generate responses to queries. The generative AI model uses a model trained with natural language processing frameworks such as TENSORFLOW® or PyTorch. This allows the model to acquire the knowledge to flexibly handle a variety of query scenarios.

[0076] The terminal provides a user-accessible interface and is implemented using front-end frameworks such as React or Angular. Through this interface, users can enter questions related to contract work. The entered questions are sent to the server via a RESTful API.

[0077] The user can enter a prompt such as, "How do I renew my contract?" The terminal sends this information to the server, which uses a generative model to generate an appropriate response. For example, a specific answer such as, "To renew your contract, you need to prepare certain documents and confirm their approval," is generated and displayed to the user via the terminal.

[0078] This system can improve the overall efficiency of business processes by preventing reliance on individual employees for specific tasks and improving the quality of responses to inquiries.

[0079] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0080] Step 1:

[0081] The server collects business-related information and stores it in a structured database. Specifically, it retrieves data from various business systems and external sources via APIs. Inputs include past support history, FAQs, and contract templates, which are stored in a database such as MySQL. The data is normalized, and indexes are created to enable efficient searching.

[0082] Step 2:

[0083] The server trains a generative AI model based on information stored in the database. The input is the structured data from step 1, and the output is an optimized model designed to provide highly accurate responses to queries. Data preprocessing and feature extraction are performed using tools such as TensorFlow, and the model is then trained.

[0084] Step 3:

[0085] The terminal provides an interface accessible to the user. Input consists of questions and prompts entered by the user into the interface. A user-friendly UI is created using frameworks such as React. The terminal receives user input and sends it to the server via a RESTful API.

[0086] Step 4:

[0087] The server generates a response using a generative AI model based on the user's inquiry. The input is the user's inquiry, and the output is a specific and appropriate answer. The server passes the inquiry to the generative model, which generates the requested response in text format.

[0088] Step 5:

[0089] The terminal displays the response received from the server to the user. The input is the response sent from the server, and the output is a display in a format that the user can understand. The terminal formats the received text using the UI and presents it to the user.

[0090] Step 6:

[0091] The user decides on their next action based on the displayed information. The input is the response displayed on the terminal, and the output is the user's decision regarding their next action. For example, the user receives information such as "To renew your contract, you need to prepare certain documents and confirm their approval," and then begins preparing the necessary documents.

[0092] (Application Example 1)

[0093] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0094] In digital services delivered via the internet, there is a need to respond to user inquiries quickly and efficiently. However, conventional systems often suffer from delayed or inaccurate responses, which detract from the user experience. This invention aims to solve these problems and provide higher quality user support by using a generative model.

[0095] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0096] In this invention, the server includes a database means for collecting and storing business-related information, a learning means for training a generative model, and a response means for generating responses via an international information and communication network and providing information to user devices. This makes it possible to respond quickly and accurately to user inquiries.

[0097] "Business process optimization" means optimizing specific business processes, reducing wasted time and resources, and improving productivity.

[0098] A "generative model" is an algorithm designed to generate new information based on past data, and is a technique particularly used in natural language processing and machine learning.

[0099] An "information processing device" is a device or system used to process, analyze, and output data.

[0100] A "database system" is a storage system for systematically accumulating and managing information.

[0101] "Learning methods" refer to algorithms and processes that enable a model to improve its predictive ability based on data.

[0102] A "response mechanism" is a function that generates and provides appropriate answers to user inquiries.

[0103] A "terminal device" is an interface device used by a user to input information and display the results.

[0104] "International information and communication network" refers to a globally connected communication network, such as the internet.

[0105] "User equipment" refers to electronic devices such as computers and mobile devices that are directly operated by the user.

[0106] "User" refers to an individual or legal entity that operates this system and obtains information from it.

[0107] In an embodiment of this invention, the server performs advanced information processing using a generative model for the purpose of improving operational efficiency. The server collects business-related data and stores it in a database system. This data includes transaction history, FAQs, contract templates, etc., and the generative model is trained based on this information.

[0108] Trained generative models can respond quickly and appropriately to a variety of user inquiries. By using natural language processing techniques, these models generate highly accurate answers to questions and instructions written in human language. This process includes, for example, open-source libraries used as machine learning platforms and third-party API services used for AI inference.

[0109] The terminal provides a user-friendly interface. The user inputs a question using the terminal, and this information is sent to the server via an API. The server performs analysis and generates an answer using a generative model, then sends the answer back to the terminal. The terminal then displays this answer, presenting it in a user-friendly format.

[0110] For example, if a user enters "I want to know about the point exchange process," the server will generate and display instructions such as "To exchange points, you need to press a specific button in the app, enter the required information, and confirm." This feature allows users to quickly resolve their questions without having to wait for support.

[0111] An example of a prompt statement is, "The user is asking about the point exchange process. Please explain the specific steps clearly." By using this prompt statement as input to the generative model, detailed steps are automatically generated.

[0112] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0113] Step 1:

[0114] The user enters the question through the terminal interface. The input data is in text format and is formatted as an API request. The entered data is sent directly to the API endpoint.

[0115] Step 2:

[0116] The device forwards user-submitted questions to the server via an API. The server analyzes the received text data and formats it into a format that the generative AI model can understand. This process involves text normalization and tokenization.

[0117] Step 3:

[0118] The server uses the formatted data to invoke a generative AI model, which generates answers tailored to the question. The generative model provides natural language answers based on a pre-trained database and prompt text. The output answers are packaged as text data in the specified format.

[0119] Step 4:

[0120] The server sends the generated response to the device. The device receives the response data and incorporates it into UI components for user-friendly display. This display takes into account font size, color, layout, etc., to present the information in a user-friendly manner.

[0121] Step 5:

[0122] The user reviews the answer displayed on the device. If necessary, they can repeat the process, such as entering another question. This cycle of answering and asking further questions allows the user to solve problems efficiently.

[0123] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0124] This invention combines an emotion engine with an information processing system that uses a generative model to improve business efficiency. This system has the function of appropriately recognizing the user's emotions through the server, terminal, and user, and generating and adjusting responses based on those emotions.

[0125] Server operation

[0126] The server first collects business-related data and stores the digitized information in a database. This data is used to train a generative model. The generative model acquires the ability to handle business-related scenarios using natural language processing techniques. Furthermore, the server has an emotion engine implemented, which is responsible for analyzing the user's emotions from the input data. This emotional information is taken into consideration when generating the generative model's response, enabling responses that are appropriate to the user's psychological state.

[0127] Terminal operation

[0128] The terminal provides a user interface and an environment where users can input questions. The terminal uses an API to send user input to the server in real time. The input text is analyzed by an emotion engine and used in the response generation process along with the emotional state.

[0129] User actions

[0130] The user enters questions about contract procedures through the terminal interface. For example, the question might include an emotion such as "I'm worried about renewing my contract." The server receives this input and uses an emotion engine to recognize the emotion of "anxiety." Then, a generative model considers this emotion data and generates a response to alleviate the anxiety, such as "Don't worry, renewing your contract is easy; just follow these steps."

[0131] This system enables more empathetic and personalized responses that respond to user emotions, improving the user experience in business processes. This leads to increased operational efficiency and improved user satisfaction.

[0132] The following describes the processing flow.

[0133] Step 1:

[0134] The server collects business-related data from internal and external sources and stores it in a database as digital data. This data includes contract templates, FAQs, and past inquiry history.

[0135] Step 2:

[0136] The server initiates a process of training a generative model based on the collected data. In this process, natural language processing techniques are used to analyze the text data and incorporate the knowledge needed to generate responses to queries into the model.

[0137] Step 3:

[0138] The device provides a user-accessible interface, allowing users to input questions through a chatbot on the device. The interface features a simple and user-friendly design.

[0139] Step 4:

[0140] Users enter questions about contracts and procedures through the terminal's interface. This input is sent to the server in text format.

[0141] Step 5:

[0142] The server passes the input text received from the user to the emotion engine, which analyzes the user's emotional state. For example, it identifies emotions such as "anxiety," "relief," and "anger."

[0143] Step 6:

[0144] The server incorporates the emotional state obtained from the emotion engine into a generative model to generate an appropriate response. This process is designed to emphasize content that takes the user's emotions into consideration.

[0145] Step 7:

[0146] The server sends the generated response back to the terminal and displays it to the user. The response may include specific steps or additional reassuring information.

[0147] Step 8:

[0148] The user refers to the response displayed on the device and decides on their next action. They can also enter further questions if necessary.

[0149] This series of processes provides real-time responses tailored to the user's emotional state, resulting in a better user experience.

[0150] (Example 2)

[0151] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0152] In recent years, many information processing systems have been utilizing generative models to improve operational efficiency. However, conventional systems have a problem in that they cannot take user emotions into consideration and therefore cannot adequately improve user satisfaction. In particular, there is a challenge in providing appropriate support and a sense of security to users in tasks that involve psychological burden, such as contract renewals.

[0153] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0154] In this invention, the server includes an information storage means for collecting business-related data and storing it as digital information, an information acquisition means for learning business scenarios using a generative model, an emotion analysis means for analyzing the user's emotions, and a response generation means for generating responses based on the analyzed emotions. This makes it possible to generate responses that take the user's emotions into consideration, thereby reducing psychological burden while simultaneously improving work efficiency and user satisfaction.

[0155] "Information storage means" refers to a device or method that has the function of collecting business-related data and storing it as digital information in a database.

[0156] "Information acquisition means" refers to a device or method that has the function of collecting and acquiring data and information necessary for training a generative model with business scenarios.

[0157] "Emotion analysis means" refers to a device or method that analyzes input data from a user and identifies the user's emotions from its content.

[0158] "Response generation means" refers to a device or method that has the function of generating a response to the user, taking into account the analyzed emotions.

[0159] A description of embodiments for carrying out this invention will be given.

[0160] Server Configuration

[0161] The server is equipped with an information storage device for collecting business-related data, digitizing it, and storing it in a database. This database management uses commonly used commercial database management system (DBMS) software. The server also has information acquisition capabilities for learning business scenarios, utilizing natural language processing technologies such as GPT-3® as a generative AI model. Furthermore, the server implements an emotion analysis engine to analyze user input and determine emotions. This analysis result is used by the generative AI model to generate responses appropriate to the user.

[0162] Device configuration

[0163] The terminal provides a user interface where users can input questions. This interface is accessible via a web browser and is designed to be easy and intuitive for users to use. The terminal has an API that uses an internet-based communication protocol (e.g., HTTPS) to send user input to the server in real time.

[0164] User actions

[0165] Users input specific questions, such as those related to contract procedures, into the interface. If the user's emotions are included (for example, "I'm worried about contract renewal"), these emotions are also processed by the server. The generative AI model then uses this information to generate a response tailored to the user and suggests specific steps to alleviate their anxiety.

[0166] Specific example

[0167] If a user enters "I'm worried about next month's budget" into their device, the server analyzes that emotion as "worry" and uses a generative model to prepare a response such as "Don't worry about the budget, we can help you with several ways to manage it."

[0168] Examples of prompts to input into a generative AI model

[0169] "When you receive a text message from a user expressing anxiety, please think of a response that will alleviate that anxiety. Specifically, please generate a response in the format of, 'Don't worry about what the user is concerned about. Instead, please try this.'"

[0170] This configuration allows the system to understand user emotions and provide optimal responses accordingly, thereby improving operational efficiency and enhancing the user experience.

[0171] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0172] Step 1:

[0173] The server collects business-related data and stores the digitized information in a database. This input data includes past contract history and user inquiry history. The server uses this data to build an information infrastructure to support the training of generative AI models. As a result, digital information related to business scenarios is aggregated in the database.

[0174] Step 2:

[0175] The terminal receives user questions in real time via the user interface. Users input specific questions and concerns regarding contracts and budgets. The entered text is sent to the server via an API. Data security is maintained through an established communication protocol.

[0176] Step 3:

[0177] The server inputs user input received from the terminal into an emotion analysis engine, which then analyzes the user's emotional state. This emotion analysis uses natural language processing techniques to identify emotions such as "anxiety" and "joy" from the text. The analyzed emotional information provides important clues to understanding the user's psychological state.

[0178] Step 4:

[0179] The server inputs the emotion analysis results and business-related information into a generating AI model and performs data calculations to generate an appropriate response based on the user's emotions. In this process, a customized response is constructed by considering the scenarios the model has learned and the user's emotions. The output response will be tailored to the user's emotional state.

[0180] Step 5:

[0181] The terminal displays the response sent back from the server to the user. This display process ensures that the response is in a concise and easy-to-understand format for the user. The terminal also presents the response in a visually user-friendly manner.

[0182] This process enables the system to provide quick and efficient responses that take user emotions into consideration.

[0183] (Application Example 2)

[0184] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0185] Conventional information processing systems have the problem of providing responses that are generated without considering the user's emotions, resulting in limited improvements to the user experience. Furthermore, because there are insufficient means to personalize emotion-based responses and quickly resolve the anxiety and dissatisfaction that users feel, it is difficult to achieve efficient business support and high user satisfaction.

[0186] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0187] In this invention, the server includes a storage means for collecting and storing business-related data, a learning means for training a generative model, a response means for analyzing emotions received from the user and generating a response based on that analysis, and a visualization means for displaying information aligned with the user's emotions. This makes it possible to analyze the user's emotions in real time and generate and display personalized responses.

[0188] A "generative model" is an artificial intelligence algorithm that generates new data or information based on input data.

[0189] An "information processing device" is a system of hardware and software for collecting, processing, and generating responses from data.

[0190] A "memory device" is a component that has the function of accumulating information related to business operations using a database or similar means.

[0191] "Learning methods" are means of training generative models to improve their predictions and responses.

[0192] A "response mechanism" is a component used to generate an appropriate response to a user inquiry using a generative model.

[0193] "Emotion analysis" is a technology that identifies emotions contained in user input, and it utilizes natural language processing and sensor data.

[0194] "Visualization means" are components for displaying generated information and responses on a user interface.

[0195] This invention provides a specific embodiment of an information processing system that combines generative models and emotion analysis technology. This system can improve work efficiency by adjusting responses based on the user's emotions.

[0196] The server collects business-related data and stores it in storage. A specific implementation includes a database management system for ingesting and storing digital data. This allows generative models to efficiently access and learn from the necessary information.

[0197] The server also employs an emotion engine that analyzes user input through natural language processing. For example, it identifies emotions from user text input via natural language processing APIs such as IBM Watson® and Microsoft® Azure®, and provides emotion-based data to a generative model to generate more appropriate responses.

[0198] The device accepts user input through a user interface. Specific examples include smart glasses and smartphones with dedicated applications installed, which can visually enhance the user experience.

[0199] User input is sent to a server via the device, and the server analyzes the emotions contained in that input in real time. At that time, a generative AI model generates a response based on the emotional information, and this response is displayed on a visualization device on the device. If the user feels anxious while tending to the garden, wondering "Will I ever finish this task?", an encouraging message such as "Let's take it little by little. Shall we have some tea in 10 minutes?" will be displayed to the user.

[0200] The following prompt statements are given as examples of input to the generative AI model.

[0201] "When a user says, 'I made another mistake,' and you sense they're feeling a little anxious, what kind of warm response can you give in this situation?"

[0202] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0203] Step 1:

[0204] Users input questions and statements through their devices. This input is in text format, and the devices send the input data to the server in real time. The text received as input is prepared for sentiment analysis.

[0205] Step 2:

[0206] The server passes the received input data to the emotion engine. The emotion engine uses natural language processing to analyze the emotions in the input data and identify emotions such as "anxiety" or "joy." This outputs the type of emotion, which is then used to generate subsequent responses.

[0207] Step 3:

[0208] The server uses a generative AI model to generate appropriate responses based on the analyzed emotional information. In this process, the input emotions are reflected in the response generation, creating emotionally sensitive wording. Using prompts, the AI ​​model outputs responses that match the user's psychological state.

[0209] Step 4:

[0210] The server sends the generated response to the terminal. The terminal displays the received response to the user via a visualization device. This allows the user to view the response on the screen and enjoy an interactive experience.

[0211] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0212] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0213] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0214] [Second Embodiment]

[0215] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0216] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0217] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0218] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0219] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0220] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0221] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0222] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0223] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0224] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0225] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0226] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0227] This invention is an information processing system that streamlines business processes using a generative model. This system is realized through collaborative interaction between a server, a terminal, and a user.

[0228] Server operation

[0229] The server begins by collecting business-related data and storing it structured in a database. This data includes past interaction history, FAQs, and contract templates. Based on this data, the server trains a generative model to acquire knowledge capable of handling diverse business scenarios. During the training process, natural language processing techniques are used to optimize the model so that it can respond appropriately to inquiries.

[0230] Terminal operation

[0231] The terminal serves to provide an interface for user access. Through this interface, users can input specific questions regarding contractual matters. The terminal sends the entered questions to the server and uses an API to quickly retrieve the answers. The terminal receives the answers from the server and displays them clearly for the user.

[0232] User actions

[0233] Through this interface, users enter questions and uncertainties regarding their contracts. For example, if a user asks, "How do I renew my contract?", the terminal sends this information to the server. The server responds to the inquiry using a generative model and sends a specific answer, such as, "To renew your contract, you need to prepare certain documents and confirm their approval." Based on this answer, the user can quickly proceed with the necessary procedures.

[0234] In this way, servers, terminals, and users collaborate with each other, leveraging the power of generative models to improve operational efficiency. As a result, it becomes possible to significantly improve issues such as reliance on individual employees and operational efficiency, and the ability to respond to new inquiries is also enhanced.

[0235] The following describes the processing flow.

[0236] Step 1:

[0237] The server collects existing business-related data from internal systems and external databases, and organizes and structures it as digital data. This data includes past case studies, FAQs, and contract templates.

[0238] Step 2:

[0239] The server uses the collected data to build a database and trains a generative model. It employs natural language processing techniques to tokenize and normalize text data, learning knowledge related to contractual work.

[0240] Step 3:

[0241] The server has the ability to periodically update newly trained models. This includes retraining the model based on the latest data and adjusting its parameters.

[0242] Step 4:

[0243] The device provides a user-accessible interface. This interface is in a chatbot format and is designed to simplify user interaction.

[0244] Step 5:

[0245] The user enters questions about the contract and procedures through the terminal's interface. The entered questions are sent from the terminal to the server as string data.

[0246] Step 6:

[0247] The server analyzes the questions received from the user and inputs them into a generative model. The model then generates the optimal response based on this information, and the results are processed within the server.

[0248] Step 7:

[0249] The server sends the generated response back to the terminal and presents it to the user. This response contains specific instructions and related information.

[0250] Step 8:

[0251] Users refer to the responses provided to plan their business decisions and next actions. They can also ask additional questions as needed.

[0252] Through this series of processing steps, the system enables efficient task execution and helps users quickly obtain the information they need.

[0253] (Example 1)

[0254] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0255] Conventional information processing systems have struggled to respond smoothly and appropriately to inquiries related to business operations, often leading to reliance on individual expertise and decreased operational efficiency. Furthermore, while organizing vast amounts of business data and providing rapid responses are essential for improving the quality of responses to inquiries, there has been a lack of effective means to achieve these goals.

[0256] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0257] In this invention, the server includes data storage means for collecting and structuring business-related information, model generation means for machine learning information using a generative model, and response generation means for receiving user inquiries and generating responses using the generative model. This enables rapid and accurate responses to user inquiries, eliminates reliance on individual expertise in business operations, and realizes efficient business processes.

[0258] "Business-related information" refers to data such as history, documents, and templates that are necessary or useful for a specific business process.

[0259] "Data storage means" refers to a system or device for collecting, structuring, and storing information related to business operations.

[0260] A "generative model" refers to artificial intelligence technology that learns from given data and generates appropriate responses to inquiries.

[0261] "Model generation means" refers to a system or device that uses a generative model to learn information and improve its ability to respond to inquiries.

[0262] "Response generation means" refers to a system or device that generates a response using a generation model based on an inquiry received from a user.

[0263] A "user interface" refers to the software and hardware that provide the interaction a user can use to access, operate, and inquire about a system.

[0264] "Communication means" refers to a network or protocol used to send and receive information between a server and a user interface.

[0265] "Display control means" refers to software or hardware that displays the results generated by the response generation means in a way that is easy for the user to understand.

[0266] "Optimization means" refers to a mechanism that continuously improves the performance of a generative model using business-related data and user feedback.

[0267] To implement this invention, it is necessary to build a system in which a server, terminal, and user work in cooperation. The server collects business-related information and stores it in a database, thereby systematically organizing the information. Specifically, it uses a database management system such as MySQL or PostgreSQL to store the information. This makes it possible to efficiently manage past interaction history, FAQs, contract templates, and so on.

[0268] Next, the server uses the collected information to leverage a generative model to generate responses to queries. The generative AI model utilizes a model trained using frameworks with natural language processing capabilities, such as TensorFlow or PyTorch. This allows the model to acquire the knowledge necessary to flexibly handle diverse query scenarios.

[0269] The terminal provides a user-accessible interface and is implemented using front-end frameworks such as React or Angular. Through this interface, users can enter questions related to contract work. The entered questions are sent to the server via a RESTful API.

[0270] The user can enter a prompt such as, "How do I renew my contract?" The terminal sends this information to the server, which uses a generative model to generate an appropriate response. For example, a specific answer such as, "To renew your contract, you need to prepare certain documents and confirm their approval," is generated and displayed to the user via the terminal.

[0271] This system can improve the overall efficiency of business processes by preventing reliance on individual employees for specific tasks and improving the quality of responses to inquiries.

[0272] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0273] Step 1:

[0274] The server collects business-related information and stores it in a structured database. Specifically, it retrieves data from various business systems and external sources via APIs. Inputs include past support history, FAQs, and contract templates, which are stored in a database such as MySQL. The data is normalized, and indexes are created to enable efficient searching.

[0275] Step 2:

[0276] The server trains a generative AI model based on information stored in the database. The input is the structured data from step 1, and the output is an optimized model designed to provide highly accurate responses to queries. Data preprocessing and feature extraction are performed using tools such as TensorFlow, and the model is then trained.

[0277] Step 3:

[0278] The terminal provides an interface accessible to the user. Input consists of questions and prompts entered by the user into the interface. A user-friendly UI is created using frameworks such as React. The terminal receives user input and sends it to the server via a RESTful API.

[0279] Step 4:

[0280] The server generates a response using a generative AI model based on the user's inquiry. The input is the user's inquiry, and the output is a specific and appropriate answer. The server passes the inquiry to the generative model, which generates the requested response in text format.

[0281] Step 5:

[0282] The terminal displays the response received from the server to the user. The input is the response sent from the server, and the output is the display in a format understandable by the user. The terminal formats the received text using the UI and presents it to the user.

[0283] Step 6:

[0284] The user determines the next action based on the displayed information. The input is the response displayed on the terminal, and the output is the determination regarding the user's next action. The user receives information such as "To renew the contract, specific documents need to be prepared and approval needs to be confirmed" and starts preparing the necessary documents.

[0285] (Application Example 1)

[0286] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0287] In digital services via the Internet, it is required to quickly and efficiently handle inquiries from users. However, in conventional systems, there may be delays and inaccuracies in responses, which have been a cause of deteriorating the user experience. The present invention aims to solve these problems and provide higher-quality user support by using a generative model.

[0288] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following respective means.

[0289] In this invention, the server includes database means for collecting and storing information related to business, learning means for training a generative model, and response means for generating a response through an international information communication network and providing information to user equipment. Thereby, it becomes possible to quickly and accurately respond to inquiries from users.

[0290] "Business process optimization" means optimizing specific business processes, reducing wasted time and resources, and improving productivity.

[0291] A "generative model" is an algorithm designed to generate new information based on past data, and is a technique particularly used in natural language processing and machine learning.

[0292] An "information processing device" is a device or system used to process, analyze, and output data.

[0293] A "database system" is a storage system for systematically accumulating and managing information.

[0294] "Learning methods" refer to algorithms and processes that enable a model to improve its predictive ability based on data.

[0295] A "response mechanism" is a function that generates and provides appropriate answers to user inquiries.

[0296] A "terminal device" is an interface device used by a user to input information and display the results.

[0297] "International information and communication network" refers to a globally connected communication network, such as the internet.

[0298] "User equipment" refers to electronic devices such as computers and mobile devices that are directly operated by the user.

[0299] "User" refers to an individual or legal entity that operates this system and obtains information from it.

[0300] In an embodiment of this invention, the server performs advanced information processing using a generative model for the purpose of improving operational efficiency. The server collects business-related data and stores it in a database system. This data includes transaction history, FAQs, contract templates, etc., and the generative model is trained based on this information.

[0301] Trained generative models can respond quickly and appropriately to a variety of user inquiries. By using natural language processing techniques, these models generate highly accurate answers to questions and instructions written in human language. This process includes, for example, open-source libraries used as machine learning platforms and third-party API services used for AI inference.

[0302] The terminal provides a user-friendly interface. The user inputs a question using the terminal, and this information is sent to the server via an API. The server performs analysis and generates an answer using a generative model, then sends the answer back to the terminal. The terminal then displays this answer, presenting it in a user-friendly format.

[0303] For example, if a user enters "I want to know about the point exchange process," the server will generate and display instructions such as "To exchange points, you need to press a specific button in the app, enter the required information, and confirm." This feature allows users to quickly resolve their questions without having to wait for support.

[0304] An example of a prompt statement is, "The user is asking about the point exchange process. Please explain the specific steps clearly." By using this prompt statement as input to the generative model, detailed steps are automatically generated.

[0305] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0306] Step 1:

[0307] The user inputs a question through the interface of the terminal. The input data is in text format and is formatted as an API request. The input data is directly sent to the API endpoint.

[0308] Step 2:

[0309] The terminal transfers the question sent by the user to the server via the API. The server analyzes the received text data and formats the data into a form that the generative AI model can understand. In this process, text normalization and tokenization are performed.

[0310] Step 3:

[0311] The server uses the formatted data to call the generative AI model and generates an answer according to the content of the question. The generative model gives an answer in natural language based on the pre-learned database and prompt text. The output answer is packaged into the specified format as text data.

[0312] Step 4:

[0313] The server sends the generated answer to the terminal. The terminal receives the received answer data and incorporates it into the UI components for easy display to the user. In this screen display, font size, color, layout, etc. are considered and presented in a user-friendly form.

[0314] Step 5:

[0315] The user checks the answer displayed on the terminal. If necessary, operations such as inputting another question can be repeated. Through this response-requestion cycle, the user can efficiently solve the problem.

[0316] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0317] This invention combines an emotion engine with an information processing system that uses a generative model to improve business efficiency. This system has the function of appropriately recognizing the user's emotions through the server, terminal, and user, and generating and adjusting responses based on those emotions.

[0318] Server operation

[0319] The server first collects business-related data and stores the digitized information in a database. This data is used to train a generative model. The generative model acquires the ability to handle business-related scenarios using natural language processing techniques. Furthermore, the server has an emotion engine implemented, which is responsible for analyzing the user's emotions from the input data. This emotional information is taken into consideration when generating the generative model's response, enabling responses that are appropriate to the user's psychological state.

[0320] Terminal operation

[0321] The terminal provides a user interface and an environment where users can input questions. The terminal uses an API to send user input to the server in real time. The input text is analyzed by an emotion engine and used in the response generation process along with the emotional state.

[0322] User actions

[0323] The user enters questions about contract procedures through the terminal interface. For example, the question might include an emotion such as "I'm worried about renewing my contract." The server receives this input and uses an emotion engine to recognize the emotion of "anxiety." Then, a generative model considers this emotion data and generates a response to alleviate the anxiety, such as "Don't worry, renewing your contract is easy; just follow these steps."

[0324] This system enables more empathetic and personalized responses that respond to user emotions, improving the user experience in business processes. This leads to increased operational efficiency and improved user satisfaction.

[0325] The following describes the processing flow.

[0326] Step 1:

[0327] The server collects business-related data from internal and external sources and stores it in a database as digital data. This data includes contract templates, FAQs, and past inquiry history.

[0328] Step 2:

[0329] The server initiates a process of training a generative model based on the collected data. In this process, natural language processing techniques are used to analyze the text data and incorporate the knowledge needed to generate responses to queries into the model.

[0330] Step 3:

[0331] The device provides a user-accessible interface, allowing users to input questions through a chatbot on the device. The interface features a simple and user-friendly design.

[0332] Step 4:

[0333] Users enter questions about contracts and procedures through the terminal's interface. This input is sent to the server in text format.

[0334] Step 5:

[0335] The server passes the input text received from the user to the emotion engine, which analyzes the user's emotional state. For example, it identifies emotions such as "anxiety," "relief," and "anger."

[0336] Step 6:

[0337] The server incorporates the emotional state obtained from the emotion engine into a generative model to generate an appropriate response. This process is designed to emphasize content that takes the user's emotions into consideration.

[0338] Step 7:

[0339] The server sends the generated response back to the terminal and displays it to the user. The response may include specific steps or additional reassuring information.

[0340] Step 8:

[0341] The user refers to the response displayed on the device and decides on their next action. They can also enter further questions if necessary.

[0342] This series of processes provides real-time responses tailored to the user's emotional state, resulting in a better user experience.

[0343] (Example 2)

[0344] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0345] In recent years, many information processing systems have been utilizing generative models to improve operational efficiency. However, conventional systems have a problem in that they cannot take user emotions into consideration and therefore cannot adequately improve user satisfaction. In particular, there is a challenge in providing appropriate support and a sense of security to users in tasks that involve psychological burden, such as contract renewals.

[0346] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0347] In this invention, the server includes an information storage means for collecting business-related data and storing it as digital information, an information acquisition means for learning business scenarios using a generative model, an emotion analysis means for analyzing the user's emotions, and a response generation means for generating responses based on the analyzed emotions. This makes it possible to generate responses that take the user's emotions into consideration, thereby reducing psychological burden while simultaneously improving work efficiency and user satisfaction.

[0348] "Information storage means" refers to a device or method that has the function of collecting business-related data and storing it as digital information in a database.

[0349] "Information acquisition means" refers to a device or method that has the function of collecting and acquiring data and information necessary for training a generative model with business scenarios.

[0350] "Emotion analysis means" refers to a device or method that analyzes input data from a user and identifies the user's emotions from its content.

[0351] "Response generation means" refers to a device or method that has the function of generating a response to the user, taking into account the analyzed emotions.

[0352] A description of embodiments for carrying out this invention will be given.

[0353] Server Configuration

[0354] The server is equipped with an information storage device for collecting business-related data, digitizing it, and storing it in a database. This database management uses commonly used commercial database management system (DBMS) software. The server also has information acquisition capabilities for learning business scenarios, utilizing natural language processing technologies such as GPT-3 as a generative AI model. Furthermore, the server implements an emotion analysis engine to analyze user input and determine emotions. The results of this analysis are used by the generative AI model to generate responses appropriate to the user.

[0355] Device configuration

[0356] The terminal provides a user interface where users can input questions. This interface is accessible via a web browser and is designed to be easy and intuitive for users to use. The terminal has an API that uses an internet-based communication protocol (e.g., HTTPS) to send user input to the server in real time.

[0357] User actions

[0358] Users input specific questions, such as those related to contract procedures, into the interface. If the user's emotions are included (for example, "I'm worried about contract renewal"), these emotions are also processed by the server. The generative AI model then uses this information to generate a response tailored to the user and suggests specific steps to alleviate their anxiety.

[0359] Specific example

[0360] If a user enters "I'm worried about next month's budget" into their device, the server analyzes that emotion as "worry" and uses a generative model to prepare a response such as "Don't worry about the budget, we can help you with several ways to manage it."

[0361] Examples of prompts to input into a generative AI model

[0362] "When you receive a text message from a user expressing anxiety, please think of a response that will alleviate that anxiety. Specifically, please generate a response in the format of, 'Don't worry about what the user is concerned about. Instead, please try this.'"

[0363] This configuration allows the system to understand user emotions and provide optimal responses accordingly, thereby improving operational efficiency and enhancing the user experience.

[0364] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0365] Step 1:

[0366] The server collects business-related data and stores the digitized information in a database. This input data includes past contract history and user inquiry history. The server uses this data to build an information infrastructure to support the training of generative AI models. As a result, digital information related to business scenarios is aggregated in the database.

[0367] Step 2:

[0368] The terminal receives user questions in real time via the user interface. Users input specific questions and concerns regarding contracts and budgets. The entered text is sent to the server via an API. Data security is maintained through an established communication protocol.

[0369] Step 3:

[0370] The server inputs user input received from the terminal into an emotion analysis engine, which then analyzes the user's emotional state. This emotion analysis uses natural language processing techniques to identify emotions such as "anxiety" and "joy" from the text. The analyzed emotional information provides important clues to understanding the user's psychological state.

[0371] Step 4:

[0372] The server inputs the emotion analysis results and business-related information into a generating AI model and performs data calculations to generate an appropriate response based on the user's emotions. In this process, a customized response is constructed by considering the scenarios the model has learned and the user's emotions. The output response will be tailored to the user's emotional state.

[0373] Step 5:

[0374] The terminal displays the response sent back from the server to the user. This display process ensures that the response is in a concise and easy-to-understand format for the user. The terminal also presents the response in a visually user-friendly manner.

[0375] This process enables the system to provide quick and efficient responses that take user emotions into consideration.

[0376] (Application Example 2)

[0377] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0378] Conventional information processing systems have the problem of providing responses that are generated without considering the user's emotions, resulting in limited improvements to the user experience. Furthermore, because there are insufficient means to personalize emotion-based responses and quickly resolve the anxiety and dissatisfaction that users feel, it is difficult to achieve efficient business support and high user satisfaction.

[0379] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0380] In this invention, the server includes a storage means for collecting and storing business-related data, a learning means for training a generative model, a response means for analyzing emotions received from the user and generating a response based on that analysis, and a visualization means for displaying information aligned with the user's emotions. This makes it possible to analyze the user's emotions in real time and generate and display personalized responses.

[0381] A "generative model" is an artificial intelligence algorithm that generates new data or information based on input data.

[0382] An "information processing device" is a system of hardware and software for collecting, processing, and generating responses from data.

[0383] A "memory device" is a component that has the function of accumulating information related to business operations using a database or similar means.

[0384] "Learning methods" are means of training generative models to improve their predictions and responses.

[0385] A "response mechanism" is a component used to generate an appropriate response to a user inquiry using a generative model.

[0386] "Emotion analysis" is a technology that identifies emotions contained in user input, and it utilizes natural language processing and sensor data.

[0387] "Visualization means" are components for displaying generated information and responses on a user interface.

[0388] This invention provides a specific embodiment of an information processing system that combines generative models and emotion analysis technology. This system can improve work efficiency by adjusting responses based on the user's emotions.

[0389] The server collects business-related data and stores it in storage. A specific implementation includes a database management system for ingesting and storing digital data. This allows generative models to efficiently access and learn from the necessary information.

[0390] The server also employs an emotion engine that analyzes user input through natural language processing. For example, it identifies emotions from user text input via natural language processing APIs such as IBM Watson and Microsoft Azure, and provides emotion-based data to a generative model to generate more appropriate responses.

[0391] The device accepts user input through a user interface. Specific examples include smart glasses and smartphones with dedicated applications installed, which can visually enhance the user experience.

[0392] User input is sent to a server via the device, and the server analyzes the emotions contained in that input in real time. At that time, a generative AI model generates a response based on the emotional information, and this response is displayed on a visualization device on the device. If the user feels anxious while tending to the garden, wondering "Will I ever finish this task?", an encouraging message such as "Let's take it little by little. Shall we have some tea in 10 minutes?" will be displayed to the user.

[0393] The following prompt statements are given as examples of input to the generative AI model.

[0394] "When a user says, 'I made another mistake,' and you sense they're feeling a little anxious, what kind of warm response can you give in this situation?"

[0395] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0396] Step 1:

[0397] Users input questions and statements through their devices. This input is in text format, and the devices send the input data to the server in real time. The text received as input is prepared for sentiment analysis.

[0398] Step 2:

[0399] The server passes the received input data to the emotion engine. The emotion engine uses natural language processing to analyze the emotions in the input data and identify emotions such as "anxiety" or "joy." This outputs the type of emotion, which is then used to generate subsequent responses.

[0400] Step 3:

[0401] The server uses a generative AI model to generate appropriate responses based on the analyzed emotional information. In this process, the input emotions are reflected in the response generation, creating emotionally sensitive wording. Using prompts, the AI ​​model outputs responses that match the user's psychological state.

[0402] Step 4:

[0403] The server sends the generated response to the terminal. The terminal displays the received response to the user via a visualization device. This allows the user to view the response on the screen and enjoy an interactive experience.

[0404] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0405] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0406] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0407] [Third Embodiment]

[0408] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0409] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0410] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0411] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0412] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0413] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0414] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0415] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0416] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0417] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0418] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0419] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0420] This invention is an information processing system that streamlines business processes using a generative model. This system is realized through collaborative interaction between a server, a terminal, and a user.

[0421] Server operation

[0422] The server begins by collecting business-related data and storing it structured in a database. This data includes past interaction history, FAQs, and contract templates. Based on this data, the server trains a generative model to acquire knowledge capable of handling diverse business scenarios. During the training process, natural language processing techniques are used to optimize the model so that it can respond appropriately to inquiries.

[0423] Terminal operation

[0424] The terminal serves to provide an interface for user access. Through this interface, users can input specific questions regarding contractual matters. The terminal sends the entered questions to the server and uses an API to quickly retrieve the answers. The terminal receives the answers from the server and displays them clearly for the user.

[0425] User actions

[0426] Through this interface, users enter questions and uncertainties regarding their contracts. For example, if a user asks, "How do I renew my contract?", the terminal sends this information to the server. The server responds to the inquiry using a generative model and sends a specific answer, such as, "To renew your contract, you need to prepare certain documents and confirm their approval." Based on this answer, the user can quickly proceed with the necessary procedures.

[0427] In this way, servers, terminals, and users collaborate with each other, leveraging the power of generative models to improve operational efficiency. As a result, it becomes possible to significantly improve issues such as reliance on individual employees and operational efficiency, and the ability to respond to new inquiries is also enhanced.

[0428] The following describes the processing flow.

[0429] Step 1:

[0430] The server collects existing business-related data from internal systems and external databases, and organizes and structures it as digital data. This data includes past case studies, FAQs, and contract templates.

[0431] Step 2:

[0432] The server uses the collected data to build a database and trains a generative model. It employs natural language processing techniques to tokenize and normalize text data, learning knowledge related to contractual work.

[0433] Step 3:

[0434] The server has the ability to periodically update newly trained models. This includes retraining the model based on the latest data and adjusting its parameters.

[0435] Step 4:

[0436] The device provides a user-accessible interface. This interface is in a chatbot format and is designed to simplify user interaction.

[0437] Step 5:

[0438] The user enters questions about the contract and procedures through the terminal's interface. The entered questions are sent from the terminal to the server as string data.

[0439] Step 6:

[0440] The server analyzes the questions received from the user and inputs them into a generative model. The model then generates the optimal response based on this information, and the results are processed within the server.

[0441] Step 7:

[0442] The server sends the generated response back to the terminal and presents it to the user. This response contains specific instructions and related information.

[0443] Step 8:

[0444] Users refer to the responses provided to plan their business decisions and next actions. They can also ask additional questions as needed.

[0445] Through this series of processing steps, the system enables efficient task execution and helps users quickly obtain the information they need.

[0446] (Example 1)

[0447] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0448] Conventional information processing systems have struggled to respond smoothly and appropriately to inquiries related to business operations, often leading to reliance on individual expertise and decreased operational efficiency. Furthermore, while organizing vast amounts of business data and providing rapid responses are essential for improving the quality of responses to inquiries, there has been a lack of effective means to achieve these goals.

[0449] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0450] In this invention, the server includes data storage means for collecting and structuring business-related information, model generation means for machine learning information using a generative model, and response generation means for receiving user inquiries and generating responses using the generative model. This enables rapid and accurate responses to user inquiries, eliminates reliance on individual expertise in business operations, and realizes efficient business processes.

[0451] "Business-related information" refers to data such as history, documents, and templates that are necessary or useful for a specific business process.

[0452] "Data storage means" refers to a system or device for collecting, structuring, and storing information related to business operations.

[0453] A "generative model" refers to artificial intelligence technology that learns from given data and generates appropriate responses to inquiries.

[0454] "Model generation means" refers to a system or device that uses a generative model to learn information and improve its ability to respond to inquiries.

[0455] "Response generation means" refers to a system or device that generates a response using a generation model based on an inquiry received from a user.

[0456] A "user interface" refers to the software and hardware that provide the interaction a user can use to access, operate, and inquire about a system.

[0457] "Communication means" refers to a network or protocol used to send and receive information between a server and a user interface.

[0458] "Display control means" refers to software or hardware that displays the results generated by the response generation means in a way that is easy for the user to understand.

[0459] "Optimization means" refers to a mechanism that continuously improves the performance of a generative model using business-related data and user feedback.

[0460] To implement this invention, it is necessary to build a system in which a server, terminal, and user work in cooperation. The server collects business-related information and stores it in a database, thereby systematically organizing the information. Specifically, it uses a database management system such as MySQL or PostgreSQL to store the information. This makes it possible to efficiently manage past interaction history, FAQs, contract templates, and so on.

[0461] Next, the server uses the collected information to leverage a generative model to generate responses to queries. The generative AI model utilizes a model trained using frameworks with natural language processing capabilities, such as TensorFlow or PyTorch. This allows the model to acquire the knowledge necessary to flexibly handle diverse query scenarios.

[0462] The terminal provides a user-accessible interface and is implemented using front-end frameworks such as React or Angular. Through this interface, users can enter questions related to contract work. The entered questions are sent to the server via a RESTful API.

[0463] The user can enter a prompt such as, "How do I renew my contract?" The terminal sends this information to the server, which uses a generative model to generate an appropriate response. For example, a specific answer such as, "To renew your contract, you need to prepare certain documents and confirm their approval," is generated and displayed to the user via the terminal.

[0464] This system can improve the overall efficiency of business processes by preventing reliance on individual employees for specific tasks and improving the quality of responses to inquiries.

[0465] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0466] Step 1:

[0467] The server collects business-related information and stores it in a structured database. Specifically, it retrieves data from various business systems and external sources via APIs. Inputs include past support history, FAQs, and contract templates, which are stored in a database such as MySQL. The data is normalized, and indexes are created to enable efficient searching.

[0468] Step 2:

[0469] The server trains a generative AI model based on information stored in the database. The input is the structured data from step 1, and the output is an optimized model designed to provide highly accurate responses to queries. Data preprocessing and feature extraction are performed using tools such as TensorFlow, and the model is then trained.

[0470] Step 3:

[0471] The terminal provides an interface accessible to the user. Input consists of questions and prompts entered by the user into the interface. A user-friendly UI is created using frameworks such as React. The terminal receives user input and sends it to the server via a RESTful API.

[0472] Step 4:

[0473] The server generates a response using a generative AI model based on the user's inquiry. The input is the user's inquiry, and the output is a specific and appropriate answer. The server passes the inquiry to the generative model, which generates the requested response in text format.

[0474] Step 5:

[0475] The terminal displays the response received from the server to the user. The input is the response sent from the server, and the output is a display in a format that the user can understand. The terminal formats the received text using the UI and presents it to the user.

[0476] Step 6:

[0477] The user decides on their next action based on the displayed information. The input is the response displayed on the terminal, and the output is the user's decision regarding their next action. For example, the user receives information such as "To renew your contract, you need to prepare certain documents and confirm their approval," and then begins preparing the necessary documents.

[0478] (Application Example 1)

[0479] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0480] In digital services delivered via the internet, there is a need to respond to user inquiries quickly and efficiently. However, conventional systems often suffer from delayed or inaccurate responses, which detract from the user experience. This invention aims to solve these problems and provide higher quality user support by using a generative model.

[0481] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0482] In this invention, the server includes a database means for collecting and storing business-related information, a learning means for training a generative model, and a response means for generating responses via an international information and communication network and providing information to user devices. This makes it possible to respond quickly and accurately to user inquiries.

[0483] "Business process optimization" means optimizing specific business processes, reducing wasted time and resources, and improving productivity.

[0484] A "generative model" is an algorithm designed to generate new information based on past data, and is a technique particularly used in natural language processing and machine learning.

[0485] An "information processing device" is a device or system used to process, analyze, and output data.

[0486] A "database system" is a storage system for systematically accumulating and managing information.

[0487] "Learning methods" refer to algorithms and processes that enable a model to improve its predictive ability based on data.

[0488] A "response mechanism" is a function that generates and provides appropriate answers to user inquiries.

[0489] A "terminal device" is an interface device used by a user to input information and display the results.

[0490] "International information and communication network" refers to a globally connected communication network, such as the internet.

[0491] "User equipment" refers to electronic devices such as computers and mobile devices that are directly operated by the user.

[0492] "User" refers to an individual or legal entity that operates this system and obtains information from it.

[0493] In an embodiment of this invention, the server performs advanced information processing using a generative model for the purpose of improving operational efficiency. The server collects business-related data and stores it in a database system. This data includes transaction history, FAQs, contract templates, etc., and the generative model is trained based on this information.

[0494] Trained generative models can respond quickly and appropriately to a variety of user inquiries. By using natural language processing techniques, these models generate highly accurate answers to questions and instructions written in human language. This process includes, for example, open-source libraries used as machine learning platforms and third-party API services used for AI inference.

[0495] The terminal provides a user-friendly interface. The user inputs a question using the terminal, and this information is sent to the server via an API. The server performs analysis and generates an answer using a generative model, then sends the answer back to the terminal. The terminal then displays this answer, presenting it in a user-friendly format.

[0496] For example, if a user enters "I want to know about the point exchange process," the server will generate and display instructions such as "To exchange points, you need to press a specific button in the app, enter the required information, and confirm." This feature allows users to quickly resolve their questions without having to wait for support.

[0497] An example of a prompt statement is, "The user is asking about the point exchange process. Please explain the specific steps clearly." By using this prompt statement as input to the generative model, detailed steps are automatically generated.

[0498] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0499] Step 1:

[0500] The user enters the question through the terminal interface. The input data is in text format and is formatted as an API request. The entered data is sent directly to the API endpoint.

[0501] Step 2:

[0502] The device forwards user-submitted questions to the server via an API. The server analyzes the received text data and formats it into a format that the generative AI model can understand. This process involves text normalization and tokenization.

[0503] Step 3:

[0504] The server uses the formatted data to invoke a generative AI model, which generates answers tailored to the question. The generative model provides natural language answers based on a pre-trained database and prompt text. The output answers are packaged as text data in the specified format.

[0505] Step 4:

[0506] The server sends the generated response to the device. The device receives the response data and incorporates it into UI components for user-friendly display. This display takes into account font size, color, layout, etc., to present the information in a user-friendly manner.

[0507] Step 5:

[0508] The user reviews the answer displayed on the device. If necessary, they can repeat the process, such as entering another question. This cycle of answering and asking further questions allows the user to solve problems efficiently.

[0509] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0510] This invention combines an emotion engine with an information processing system that uses a generative model to improve business efficiency. This system has the function of appropriately recognizing the user's emotions through the server, terminal, and user, and generating and adjusting responses based on those emotions.

[0511] Server operation

[0512] The server first collects business-related data and stores the digitized information in a database. This data is used to train a generative model. The generative model acquires the ability to handle business-related scenarios using natural language processing techniques. Furthermore, the server has an emotion engine implemented, which is responsible for analyzing the user's emotions from the input data. This emotional information is taken into consideration when generating the generative model's response, enabling responses that are appropriate to the user's psychological state.

[0513] Terminal operation

[0514] The terminal provides a user interface and an environment where users can input questions. The terminal uses an API to send user input to the server in real time. The input text is analyzed by an emotion engine and used in the response generation process along with the emotional state.

[0515] User actions

[0516] The user enters questions about contract procedures through the terminal interface. For example, the question might include an emotion such as "I'm worried about renewing my contract." The server receives this input and uses an emotion engine to recognize the emotion of "anxiety." Then, a generative model considers this emotion data and generates a response to alleviate the anxiety, such as "Don't worry, renewing your contract is easy; just follow these steps."

[0517] This system enables more empathetic and personalized responses that respond to user emotions, improving the user experience in business processes. This leads to increased operational efficiency and improved user satisfaction.

[0518] The following describes the processing flow.

[0519] Step 1:

[0520] The server collects business-related data from internal and external sources and stores it in a database as digital data. This data includes contract templates, FAQs, and past inquiry history.

[0521] Step 2:

[0522] The server initiates a process of training a generative model based on the collected data. In this process, natural language processing techniques are used to analyze the text data and incorporate the knowledge needed to generate responses to queries into the model.

[0523] Step 3:

[0524] The device provides a user-accessible interface, allowing users to input questions through a chatbot on the device. The interface features a simple and user-friendly design.

[0525] Step 4:

[0526] Users enter questions about contracts and procedures through the terminal's interface. This input is sent to the server in text format.

[0527] Step 5:

[0528] The server passes the input text received from the user to the emotion engine, which analyzes the user's emotional state. For example, it identifies emotions such as "anxiety," "relief," and "anger."

[0529] Step 6:

[0530] The server incorporates the emotional state obtained from the emotion engine into a generative model to generate an appropriate response. This process is designed to emphasize content that takes the user's emotions into consideration.

[0531] Step 7:

[0532] The server sends the generated response back to the terminal and displays it to the user. The response may include specific steps or additional reassuring information.

[0533] Step 8:

[0534] The user refers to the response displayed on the device and decides on their next action. They can also enter further questions if necessary.

[0535] This series of processes provides real-time responses tailored to the user's emotional state, resulting in a better user experience.

[0536] (Example 2)

[0537] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0538] In recent years, many information processing systems have been utilizing generative models to improve operational efficiency. However, conventional systems have a problem in that they cannot take user emotions into consideration and therefore cannot adequately improve user satisfaction. In particular, there is a challenge in providing appropriate support and a sense of security to users in tasks that involve psychological burden, such as contract renewals.

[0539] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0540] In this invention, the server includes an information storage means for collecting business-related data and storing it as digital information, an information acquisition means for learning business scenarios using a generative model, an emotion analysis means for analyzing the user's emotions, and a response generation means for generating responses based on the analyzed emotions. This makes it possible to generate responses that take the user's emotions into consideration, thereby reducing psychological burden while simultaneously improving work efficiency and user satisfaction.

[0541] "Information storage means" refers to a device or method that has the function of collecting business-related data and storing it as digital information in a database.

[0542] "Information acquisition means" refers to a device or method that has the function of collecting and acquiring data and information necessary for training a generative model with business scenarios.

[0543] "Emotion analysis means" refers to a device or method that analyzes input data from a user and identifies the user's emotions from its content.

[0544] "Response generation means" refers to a device or method that has the function of generating a response to the user, taking into account the analyzed emotions.

[0545] A description of embodiments for carrying out this invention will be given.

[0546] Server Configuration

[0547] The server is equipped with an information storage device for collecting business-related data, digitizing it, and storing it in a database. This database management uses commonly used commercial database management system (DBMS) software. The server also has information acquisition capabilities for learning business scenarios, utilizing natural language processing technologies such as GPT-3 as a generative AI model. Furthermore, the server implements an emotion analysis engine to analyze user input and determine emotions. The results of this analysis are used by the generative AI model to generate responses appropriate to the user.

[0548] Device configuration

[0549] The terminal provides a user interface where users can input questions. This interface is accessible via a web browser and is designed to be easy and intuitive for users to use. The terminal has an API that uses an internet-based communication protocol (e.g., HTTPS) to send user input to the server in real time.

[0550] User actions

[0551] Users input specific questions, such as those related to contract procedures, into the interface. If the user's emotions are included (for example, "I'm worried about contract renewal"), these emotions are also processed by the server. The generative AI model then uses this information to generate a response tailored to the user and suggests specific steps to alleviate their anxiety.

[0552] Specific example

[0553] If a user enters "I'm worried about next month's budget" into their device, the server analyzes that emotion as "worry" and uses a generative model to prepare a response such as "Don't worry about the budget, we can help you with several ways to manage it."

[0554] Examples of prompts to input into a generative AI model

[0555] "When you receive a text message from a user expressing anxiety, please think of a response that will alleviate that anxiety. Specifically, please generate a response in the format of, 'Don't worry about what the user is concerned about. Instead, please try this.'"

[0556] This configuration allows the system to understand user emotions and provide optimal responses accordingly, thereby improving operational efficiency and enhancing the user experience.

[0557] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0558] Step 1:

[0559] The server collects business-related data and stores the digitized information in a database. This input data includes past contract history and user inquiry history. The server uses this data to build an information infrastructure to support the training of generative AI models. As a result, digital information related to business scenarios is aggregated in the database.

[0560] Step 2:

[0561] The terminal receives user questions in real time via the user interface. Users input specific questions and concerns regarding contracts and budgets. The entered text is sent to the server via an API. Data security is maintained through an established communication protocol.

[0562] Step 3:

[0563] The server inputs user input received from the terminal into an emotion analysis engine, which then analyzes the user's emotional state. This emotion analysis uses natural language processing techniques to identify emotions such as "anxiety" and "joy" from the text. The analyzed emotional information provides important clues to understanding the user's psychological state.

[0564] Step 4:

[0565] The server inputs the emotion analysis results and business-related information into a generating AI model and performs data calculations to generate an appropriate response based on the user's emotions. In this process, a customized response is constructed by considering the scenarios the model has learned and the user's emotions. The output response will be tailored to the user's emotional state.

[0566] Step 5:

[0567] The terminal displays the response sent back from the server to the user. This display process ensures that the response is in a concise and easy-to-understand format for the user. The terminal also presents the response in a visually user-friendly manner.

[0568] This process enables the system to provide quick and efficient responses that take user emotions into consideration.

[0569] (Application Example 2)

[0570] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0571] Conventional information processing systems have the problem of providing responses that are generated without considering the user's emotions, resulting in limited improvements to the user experience. Furthermore, because there are insufficient means to personalize emotion-based responses and quickly resolve the anxiety and dissatisfaction that users feel, it is difficult to achieve efficient business support and high user satisfaction.

[0572] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0573] In this invention, the server includes a storage means for collecting and storing business-related data, a learning means for training a generative model, a response means for analyzing emotions received from the user and generating a response based on that analysis, and a visualization means for displaying information aligned with the user's emotions. This makes it possible to analyze the user's emotions in real time and generate and display personalized responses.

[0574] A "generative model" is an artificial intelligence algorithm that generates new data or information based on input data.

[0575] An "information processing device" is a system of hardware and software for collecting, processing, and generating responses from data.

[0576] A "memory device" is a component that has the function of accumulating information related to business operations using a database or similar means.

[0577] "Learning methods" are means of training generative models to improve their predictions and responses.

[0578] A "response mechanism" is a component used to generate an appropriate response to a user inquiry using a generative model.

[0579] "Emotion analysis" is a technology that identifies emotions contained in user input, and it utilizes natural language processing and sensor data.

[0580] "Visualization means" are components for displaying generated information and responses on a user interface.

[0581] This invention provides a specific embodiment of an information processing system that combines generative models and emotion analysis technology. This system can improve work efficiency by adjusting responses based on the user's emotions.

[0582] The server collects business-related data and stores it in storage. A specific implementation includes a database management system for ingesting and storing digital data. This allows generative models to efficiently access and learn from the necessary information.

[0583] The server also employs an emotion engine that analyzes user input through natural language processing. For example, it identifies emotions from user text input via natural language processing APIs such as IBM Watson and Microsoft Azure, and provides emotion-based data to a generative model to generate more appropriate responses.

[0584] The device accepts user input through a user interface. Specific examples include smart glasses and smartphones with dedicated applications installed, which can visually enhance the user experience.

[0585] User input is sent to a server via the device, and the server analyzes the emotions contained in that input in real time. At that time, a generative AI model generates a response based on the emotional information, and this response is displayed on a visualization device on the device. If the user feels anxious while tending to the garden, wondering "Will I ever finish this task?", an encouraging message such as "Let's take it little by little. Shall we have some tea in 10 minutes?" will be displayed to the user.

[0586] The following prompt statements are given as examples of input to the generative AI model.

[0587] "When a user says, 'I made another mistake,' and you sense they're feeling a little anxious, what kind of warm response can you give in this situation?"

[0588] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0589] Step 1:

[0590] Users input questions and statements through their devices. This input is in text format, and the devices send the input data to the server in real time. The text received as input is prepared for sentiment analysis.

[0591] Step 2:

[0592] The server passes the received input data to the emotion engine. The emotion engine uses natural language processing to analyze the emotions in the input data and identify emotions such as "anxiety" or "joy." This outputs the type of emotion, which is then used to generate subsequent responses.

[0593] Step 3:

[0594] The server uses a generative AI model to generate appropriate responses based on the analyzed emotional information. In this process, the input emotions are reflected in the response generation, creating emotionally sensitive wording. Using prompts, the AI ​​model outputs responses that match the user's psychological state.

[0595] Step 4:

[0596] The server sends the generated response to the terminal. The terminal displays the received response to the user via a visualization device. This allows the user to view the response on the screen and enjoy an interactive experience.

[0597] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0598] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0599] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0600] [Fourth Embodiment]

[0601] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0602] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0603] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0604] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0605] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0606] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0607] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0608] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0609] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0610] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0611] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0612] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0613] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] This invention is an information processing system that streamlines business processes using a generative model. This system is realized through collaborative interaction between a server, a terminal, and a user.

[0615] Server operation

[0616] The server begins by collecting business-related data and storing it structured in a database. This data includes past interaction history, FAQs, and contract templates. Based on this data, the server trains a generative model to acquire knowledge capable of handling diverse business scenarios. During the training process, natural language processing techniques are used to optimize the model so that it can respond appropriately to inquiries.

[0617] Terminal operation

[0618] The terminal serves to provide an interface for user access. Through this interface, users can input specific questions regarding contractual matters. The terminal sends the entered questions to the server and uses an API to quickly retrieve the answers. The terminal receives the answers from the server and displays them clearly for the user.

[0619] User actions

[0620] Through this interface, users enter questions and uncertainties regarding their contracts. For example, if a user asks, "How do I renew my contract?", the terminal sends this information to the server. The server responds to the inquiry using a generative model and sends a specific answer, such as, "To renew your contract, you need to prepare certain documents and confirm their approval." Based on this answer, the user can quickly proceed with the necessary procedures.

[0621] In this way, servers, terminals, and users collaborate with each other, leveraging the power of generative models to improve operational efficiency. As a result, it becomes possible to significantly improve issues such as reliance on individual employees and operational efficiency, and the ability to respond to new inquiries is also enhanced.

[0622] The following describes the processing flow.

[0623] Step 1:

[0624] The server collects existing business-related data from internal systems and external databases, and organizes and structures it as digital data. This data includes past case studies, FAQs, and contract templates.

[0625] Step 2:

[0626] The server uses the collected data to build a database and trains a generative model. It employs natural language processing techniques to tokenize and normalize text data, learning knowledge related to contractual work.

[0627] Step 3:

[0628] The server has the ability to periodically update newly trained models. This includes retraining the model based on the latest data and adjusting its parameters.

[0629] Step 4:

[0630] The device provides a user-accessible interface. This interface is in a chatbot format and is designed to simplify user interaction.

[0631] Step 5:

[0632] The user enters questions about the contract and procedures through the terminal's interface. The entered questions are sent from the terminal to the server as string data.

[0633] Step 6:

[0634] The server analyzes the questions received from the user and inputs them into a generative model. The model then generates the optimal response based on this information, and the results are processed within the server.

[0635] Step 7:

[0636] The server sends the generated response back to the terminal and presents it to the user. This response contains specific instructions and related information.

[0637] Step 8:

[0638] Users refer to the responses provided to plan their business decisions and next actions. They can also ask additional questions as needed.

[0639] Through this series of processing steps, the system enables efficient task execution and helps users quickly obtain the information they need.

[0640] (Example 1)

[0641] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0642] Conventional information processing systems have struggled to respond smoothly and appropriately to inquiries related to business operations, often leading to reliance on individual expertise and decreased operational efficiency. Furthermore, while organizing vast amounts of business data and providing rapid responses are essential for improving the quality of responses to inquiries, there has been a lack of effective means to achieve these goals.

[0643] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0644] In this invention, the server includes data storage means for collecting and structuring business-related information, model generation means for machine learning information using a generative model, and response generation means for receiving user inquiries and generating responses using the generative model. This enables rapid and accurate responses to user inquiries, eliminates reliance on individual expertise in business operations, and realizes efficient business processes.

[0645] "Business-related information" refers to data such as history, documents, and templates that are necessary or useful for a specific business process.

[0646] "Data storage means" refers to a system or device for collecting, structuring, and storing information related to business operations.

[0647] A "generative model" refers to artificial intelligence technology that learns from given data and generates appropriate responses to inquiries.

[0648] "Model generation means" refers to a system or device that uses a generative model to learn information and improve its ability to respond to inquiries.

[0649] "Response generation means" refers to a system or device that generates a response using a generation model based on an inquiry received from a user.

[0650] A "user interface" refers to the software and hardware that provide the interaction a user can use to access, operate, and inquire about a system.

[0651] "Communication means" refers to a network or protocol used to send and receive information between a server and a user interface.

[0652] "Display control means" refers to software or hardware that displays the results generated by the response generation means in a way that is easy for the user to understand.

[0653] "Optimization means" refers to a mechanism that continuously improves the performance of a generative model using business-related data and user feedback.

[0654] To implement this invention, it is necessary to build a system in which a server, terminal, and user work in cooperation. The server collects business-related information and stores it in a database, thereby systematically organizing the information. Specifically, it uses a database management system such as MySQL or PostgreSQL to store the information. This makes it possible to efficiently manage past interaction history, FAQs, contract templates, and so on.

[0655] Next, the server uses the collected information to leverage a generative model to generate responses to queries. The generative AI model utilizes a model trained using frameworks with natural language processing capabilities, such as TensorFlow or PyTorch. This allows the model to acquire the knowledge necessary to flexibly handle diverse query scenarios.

[0656] The terminal provides a user-accessible interface and is implemented using front-end frameworks such as React or Angular. Through this interface, users can enter questions related to contract work. The entered questions are sent to the server via a RESTful API.

[0657] The user can enter a prompt such as, "How do I renew my contract?" The terminal sends this information to the server, which uses a generative model to generate an appropriate response. For example, a specific answer such as, "To renew your contract, you need to prepare certain documents and confirm their approval," is generated and displayed to the user via the terminal.

[0658] This system can improve the overall efficiency of business processes by preventing reliance on individual employees for specific tasks and improving the quality of responses to inquiries.

[0659] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0660] Step 1:

[0661] The server collects business-related information and stores it in a structured database. Specifically, it retrieves data from various business systems and external sources via APIs. Inputs include past support history, FAQs, and contract templates, which are stored in a database such as MySQL. The data is normalized, and indexes are created to enable efficient searching.

[0662] Step 2:

[0663] The server trains a generative AI model based on information stored in the database. The input is the structured data from step 1, and the output is an optimized model designed to provide highly accurate responses to queries. Data preprocessing and feature extraction are performed using tools such as TensorFlow, and the model is then trained.

[0664] Step 3:

[0665] The terminal provides an interface accessible to the user. Input consists of questions and prompts entered by the user into the interface. A user-friendly UI is created using frameworks such as React. The terminal receives user input and sends it to the server via a RESTful API.

[0666] Step 4:

[0667] The server generates a response using a generative AI model based on the user's inquiry. The input is the user's inquiry, and the output is a specific and appropriate answer. The server passes the inquiry to the generative model, which generates the requested response in text format.

[0668] Step 5:

[0669] The terminal displays the response received from the server to the user. The input is the response sent from the server, and the output is a display in a format that the user can understand. The terminal formats the received text using the UI and presents it to the user.

[0670] Step 6:

[0671] The user decides on their next action based on the displayed information. The input is the response displayed on the terminal, and the output is the user's decision regarding their next action. For example, the user receives information such as "To renew your contract, you need to prepare certain documents and confirm their approval," and then begins preparing the necessary documents.

[0672] (Application Example 1)

[0673] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0674] In digital services delivered via the internet, there is a need to respond to user inquiries quickly and efficiently. However, conventional systems often suffer from delayed or inaccurate responses, which detract from the user experience. This invention aims to solve these problems and provide higher quality user support by using a generative model.

[0675] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0676] In this invention, the server includes a database means for collecting and storing business-related information, a learning means for training a generative model, and a response means for generating responses via an international information and communication network and providing information to user devices. This makes it possible to respond quickly and accurately to user inquiries.

[0677] "Business process optimization" means optimizing specific business processes, reducing wasted time and resources, and improving productivity.

[0678] A "generative model" is an algorithm designed to generate new information based on past data, and is a technique particularly used in natural language processing and machine learning.

[0679] An "information processing device" is a device or system used to process, analyze, and output data.

[0680] A "database system" is a storage system for systematically accumulating and managing information.

[0681] "Learning methods" refer to algorithms and processes that enable a model to improve its predictive ability based on data.

[0682] A "response mechanism" is a function that generates and provides appropriate answers to user inquiries.

[0683] A "terminal device" is an interface device used by a user to input information and display the results.

[0684] "International information and communication network" refers to a globally connected communication network, such as the internet.

[0685] "User equipment" refers to electronic devices such as computers and mobile devices that are directly operated by the user.

[0686] "User" refers to an individual or legal entity that operates this system and obtains information from it.

[0687] In an embodiment of this invention, the server performs advanced information processing using a generative model for the purpose of improving operational efficiency. The server collects business-related data and stores it in a database system. This data includes transaction history, FAQs, contract templates, etc., and the generative model is trained based on this information.

[0688] Trained generative models can respond quickly and appropriately to a variety of user inquiries. By using natural language processing techniques, these models generate highly accurate answers to questions and instructions written in human language. This process includes, for example, open-source libraries used as machine learning platforms and third-party API services used for AI inference.

[0689] The terminal provides a user-friendly interface. The user inputs a question using the terminal, and this information is sent to the server via an API. The server performs analysis and generates an answer using a generative model, then sends the answer back to the terminal. The terminal then displays this answer, presenting it in a user-friendly format.

[0690] For example, if a user enters "I want to know about the point exchange process," the server will generate and display instructions such as "To exchange points, you need to press a specific button in the app, enter the required information, and confirm." This feature allows users to quickly resolve their questions without having to wait for support.

[0691] An example of a prompt statement is, "The user is asking about the point exchange process. Please explain the specific steps clearly." By using this prompt statement as input to the generative model, detailed steps are automatically generated.

[0692] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0693] Step 1:

[0694] The user enters the question through the terminal interface. The input data is in text format and is formatted as an API request. The entered data is sent directly to the API endpoint.

[0695] Step 2:

[0696] The device forwards user-submitted questions to the server via an API. The server analyzes the received text data and formats it into a format that the generative AI model can understand. This process involves text normalization and tokenization.

[0697] Step 3:

[0698] The server uses the formatted data to invoke a generative AI model, which generates answers tailored to the question. The generative model provides natural language answers based on a pre-trained database and prompt text. The output answers are packaged as text data in the specified format.

[0699] Step 4:

[0700] The server sends the generated response to the device. The device receives the response data and incorporates it into UI components for user-friendly display. This display takes into account font size, color, layout, etc., to present the information in a user-friendly manner.

[0701] Step 5:

[0702] The user reviews the answer displayed on the device. If necessary, they can repeat the process, such as entering another question. This cycle of answering and asking further questions allows the user to solve problems efficiently.

[0703] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0704] This invention combines an emotion engine with an information processing system that uses a generative model to improve business efficiency. This system has the function of appropriately recognizing the user's emotions through the server, terminal, and user, and generating and adjusting responses based on those emotions.

[0705] Server operation

[0706] The server first collects business-related data and stores the digitized information in a database. This data is used to train a generative model. The generative model acquires the ability to handle business-related scenarios using natural language processing techniques. Furthermore, the server has an emotion engine implemented, which is responsible for analyzing the user's emotions from the input data. This emotional information is taken into consideration when generating the generative model's response, enabling responses that are appropriate to the user's psychological state.

[0707] Terminal operation

[0708] The terminal provides a user interface and an environment where users can input questions. The terminal uses an API to send user input to the server in real time. The input text is analyzed by an emotion engine and used in the response generation process along with the emotional state.

[0709] User actions

[0710] The user enters questions about contract procedures through the terminal interface. For example, the question might include an emotion such as "I'm worried about renewing my contract." The server receives this input and uses an emotion engine to recognize the emotion of "anxiety." Then, a generative model considers this emotion data and generates a response to alleviate the anxiety, such as "Don't worry, renewing your contract is easy; just follow these steps."

[0711] This system enables more empathetic and personalized responses that respond to user emotions, improving the user experience in business processes. This leads to increased operational efficiency and improved user satisfaction.

[0712] The following describes the processing flow.

[0713] Step 1:

[0714] The server collects business-related data from internal and external sources and stores it in a database as digital data. This data includes contract templates, FAQs, and past inquiry history.

[0715] Step 2:

[0716] The server initiates a process of training a generative model based on the collected data. In this process, natural language processing techniques are used to analyze the text data and incorporate the knowledge needed to generate responses to queries into the model.

[0717] Step 3:

[0718] The device provides a user-accessible interface, allowing users to input questions through a chatbot on the device. The interface features a simple and user-friendly design.

[0719] Step 4:

[0720] Users enter questions about contracts and procedures through the terminal's interface. This input is sent to the server in text format.

[0721] Step 5:

[0722] The server passes the input text received from the user to the emotion engine, which analyzes the user's emotional state. For example, it identifies emotions such as "anxiety," "relief," and "anger."

[0723] Step 6:

[0724] The server incorporates the emotional state obtained from the emotion engine into a generative model to generate an appropriate response. This process is designed to emphasize content that takes the user's emotions into consideration.

[0725] Step 7:

[0726] The server sends the generated response back to the terminal and displays it to the user. The response may include specific steps or additional reassuring information.

[0727] Step 8:

[0728] The user refers to the response displayed on the device and decides on their next action. They can also enter further questions if necessary.

[0729] This series of processes provides real-time responses tailored to the user's emotional state, resulting in a better user experience.

[0730] (Example 2)

[0731] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0732] In recent years, many information processing systems have been utilizing generative models to improve operational efficiency. However, conventional systems have a problem in that they cannot take user emotions into consideration and therefore cannot adequately improve user satisfaction. In particular, there is a challenge in providing appropriate support and a sense of security to users in tasks that involve psychological burden, such as contract renewals.

[0733] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0734] In this invention, the server includes an information storage means for collecting business-related data and storing it as digital information, an information acquisition means for learning business scenarios using a generative model, an emotion analysis means for analyzing the user's emotions, and a response generation means for generating responses based on the analyzed emotions. This makes it possible to generate responses that take the user's emotions into consideration, thereby reducing psychological burden while simultaneously improving work efficiency and user satisfaction.

[0735] "Information storage means" refers to a device or method that has the function of collecting business-related data and storing it as digital information in a database.

[0736] "Information acquisition means" refers to a device or method that has the function of collecting and acquiring data and information necessary for training a generative model with business scenarios.

[0737] "Emotion analysis means" refers to a device or method that analyzes input data from a user and identifies the user's emotions from its content.

[0738] "Response generation means" refers to a device or method that has the function of generating a response to the user, taking into account the analyzed emotions.

[0739] A description of embodiments for carrying out this invention will be given.

[0740] Server Configuration

[0741] The server is equipped with an information storage device for collecting business-related data, digitizing it, and storing it in a database. This database management uses commonly used commercial database management system (DBMS) software. The server also has information acquisition capabilities for learning business scenarios, utilizing natural language processing technologies such as GPT-3 as a generative AI model. Furthermore, the server implements an emotion analysis engine to analyze user input and determine emotions. The results of this analysis are used by the generative AI model to generate responses appropriate to the user.

[0742] Device configuration

[0743] The terminal provides a user interface where users can input questions. This interface is accessible via a web browser and is designed to be easy and intuitive for users to use. The terminal has an API that uses an internet-based communication protocol (e.g., HTTPS) to send user input to the server in real time.

[0744] User actions

[0745] Users input specific questions, such as those related to contract procedures, into the interface. If the user's emotions are included (for example, "I'm worried about contract renewal"), these emotions are also processed by the server. The generative AI model then uses this information to generate a response tailored to the user and suggests specific steps to alleviate their anxiety.

[0746] Specific example

[0747] If a user enters "I'm worried about next month's budget" into their device, the server analyzes that emotion as "worry" and uses a generative model to prepare a response such as "Don't worry about the budget, we can help you with several ways to manage it."

[0748] Examples of prompts to input into a generative AI model

[0749] "When you receive a text message from a user expressing anxiety, please think of a response that will alleviate that anxiety. Specifically, please generate a response in the format of, 'Don't worry about what the user is concerned about. Instead, please try this.'"

[0750] This configuration allows the system to understand user emotions and provide optimal responses accordingly, thereby improving operational efficiency and enhancing the user experience.

[0751] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0752] Step 1:

[0753] The server collects business-related data and stores the digitized information in a database. This input data includes past contract history and user inquiry history. The server uses this data to build an information infrastructure to support the training of generative AI models. As a result, digital information related to business scenarios is aggregated in the database.

[0754] Step 2:

[0755] The terminal receives user questions in real time via the user interface. Users input specific questions and concerns regarding contracts and budgets. The entered text is sent to the server via an API. Data security is maintained through an established communication protocol.

[0756] Step 3:

[0757] The server inputs user input received from the terminal into an emotion analysis engine, which then analyzes the user's emotional state. This emotion analysis uses natural language processing techniques to identify emotions such as "anxiety" and "joy" from the text. The analyzed emotional information provides important clues to understanding the user's psychological state.

[0758] Step 4:

[0759] The server inputs the emotion analysis results and business-related information into a generating AI model and performs data calculations to generate an appropriate response based on the user's emotions. In this process, a customized response is constructed by considering the scenarios the model has learned and the user's emotions. The output response will be tailored to the user's emotional state.

[0760] Step 5:

[0761] The terminal displays the response sent back from the server to the user. This display process ensures that the response is in a concise and easy-to-understand format for the user. The terminal also presents the response in a visually user-friendly manner.

[0762] This process enables the system to provide quick and efficient responses that take user emotions into consideration.

[0763] (Application Example 2)

[0764] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0765] Conventional information processing systems have the problem of providing responses that are generated without considering the user's emotions, resulting in limited improvements to the user experience. Furthermore, because there are insufficient means to personalize emotion-based responses and quickly resolve the anxiety and dissatisfaction that users feel, it is difficult to achieve efficient business support and high user satisfaction.

[0766] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0767] In this invention, the server includes a storage means for collecting and storing business-related data, a learning means for training a generative model, a response means for analyzing emotions received from the user and generating a response based on that analysis, and a visualization means for displaying information aligned with the user's emotions. This makes it possible to analyze the user's emotions in real time and generate and display personalized responses.

[0768] A "generative model" is an artificial intelligence algorithm that generates new data or information based on input data.

[0769] An "information processing device" is a system of hardware and software for collecting, processing, and generating responses from data.

[0770] A "memory device" is a component that has the function of accumulating information related to business operations using a database or similar means.

[0771] "Learning methods" are means of training generative models to improve their predictions and responses.

[0772] A "response mechanism" is a component used to generate an appropriate response to a user inquiry using a generative model.

[0773] "Emotion analysis" is a technology that identifies emotions contained in user input, and it utilizes natural language processing and sensor data.

[0774] "Visualization means" are components for displaying generated information and responses on a user interface.

[0775] This invention provides a specific embodiment of an information processing system that combines generative models and emotion analysis technology. This system can improve work efficiency by adjusting responses based on the user's emotions.

[0776] The server collects business-related data and stores it in storage. A specific implementation includes a database management system for ingesting and storing digital data. This allows generative models to efficiently access and learn from the necessary information.

[0777] The server also employs an emotion engine that analyzes user input through natural language processing. For example, it identifies emotions from user text input via natural language processing APIs such as IBM Watson and Microsoft Azure, and provides emotion-based data to a generative model to generate more appropriate responses.

[0778] The device accepts user input through a user interface. Specific examples include smart glasses and smartphones with dedicated applications installed, which can visually enhance the user experience.

[0779] User input is sent to a server via the device, and the server analyzes the emotions contained in that input in real time. At that time, a generative AI model generates a response based on the emotional information, and this response is displayed on a visualization device on the device. If the user feels anxious while tending to the garden, wondering "Will I ever finish this task?", an encouraging message such as "Let's take it little by little. Shall we have some tea in 10 minutes?" will be displayed to the user.

[0780] The following prompt statements are given as examples of input to the generative AI model.

[0781] "When a user says, 'I made another mistake,' and you sense they're feeling a little anxious, what kind of warm response can you give in this situation?"

[0782] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0783] Step 1:

[0784] Users input questions and statements through their devices. This input is in text format, and the devices send the input data to the server in real time. The text received as input is prepared for sentiment analysis.

[0785] Step 2:

[0786] The server passes the received input data to the emotion engine. The emotion engine uses natural language processing to analyze the emotions in the input data and identify emotions such as "anxiety" or "joy." This outputs the type of emotion, which is then used to generate subsequent responses.

[0787] Step 3:

[0788] The server uses a generative AI model to generate appropriate responses based on the analyzed emotional information. In this process, the input emotions are reflected in the response generation, creating emotionally sensitive wording. Using prompts, the AI ​​model outputs responses that match the user's psychological state.

[0789] Step 4:

[0790] The server sends the generated response to the terminal. The terminal displays the received response to the user via a visualization device. This allows the user to view the response on the screen and enjoy an interactive experience.

[0791] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0792] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0793] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0794] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0795] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0796] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0797] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0798] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0799] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0800] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0801] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0802] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0803] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0804] 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.

[0805] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0806] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0807] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0808] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0809] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0810] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0811] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0812] The following is further disclosed regarding the embodiments described above.

[0813] (Claim 1)

[0814] An information processing device that uses a generative model to improve the efficiency of business operations, comprising: a database means for collecting and storing business-related data; a learning means for training a generative model; and a response means for processing inquiries received from a user and generating answers.

[0815] (Claim 2)

[0816] The system according to claim 1, which provides a user interface and autonomously displays answers using a generative model.

[0817] (Claim 3)

[0818] The system according to claim 1, which continuously optimizes a generative model using business-related data and user feedback.

[0819] "Example 1"

[0820] (Claim 1)

[0821] A data storage method for collecting and structuring business-related information,

[0822] A model generation method that uses a generative model to machine-learn information,

[0823] A response generation means that receives inquiries from users and generates responses using a generation model,

[0824] An input receiving means that provides a user interface and receives user input,

[0825] A means of communication for sending and receiving information between the server and the user interface,

[0826] A system that includes this.

[0827] (Claim 2)

[0828] The system according to claim 1, comprising a display control means for displaying the results generated by the response generation means in a manner that is easily understandable to the user, based on information provided through a user interface.

[0829] (Claim 3)

[0830] The system according to claim 1, comprising optimization means for integrating business-related data and user feedback to continuously optimize the generative model.

[0831] "Application Example 1"

[0832] (Claim 1)

[0833] An information processing device that uses a generative model to improve the efficiency of business operations,

[0834] A database means for collecting and storing information related to business operations,

[0835] A learning method for training a generative model,

[0836] A response means that generates a response via an international information and communication network and provides information to user equipment,

[0837] A terminal device that accepts user input and presents answers through visual display,

[0838] A system that includes this.

[0839] (Claim 2)

[0840] The system according to claim 1, wherein a user operates a user interface via a remotely controllable device, and a generative model autonomously displays a response quickly and accurately.

[0841] (Claim 3)

[0842] The system according to claim 1, which continuously optimizes the generative model using business-related information and user evaluation information.

[0843] "Example 2 of combining an emotion engine"

[0844] (Claim 1)

[0845] An information storage means for collecting business-related data and storing it as digital information,

[0846] A means of acquiring information to enable the acquisition of business scenarios using a generative model,

[0847] A means of analyzing user emotions,

[0848] A response generation means that generates a response based on analyzed emotions,

[0849] A system that includes this.

[0850] (Claim 2)

[0851] The system according to claim 1, comprising a communication means for receiving user input in real time and transmitting it to a server, and displaying a response that takes the user's emotions into consideration using a generative model.

[0852] (Claim 3)

[0853] The system according to claim 1, which uses business data and feedback data including user sentiment information to continuously optimize the quality of responses of a generative model.

[0854] "Application example 2 when combining with an emotional engine"

[0855] (Claim 1)

[0856] An information processing device that improves the efficiency of business operations using a generative model, comprising: a storage means for collecting and storing business-related data; a learning means for training a generative model; a response means for analyzing emotions received from a user and generating a response based thereon; and a visualization means for displaying information in line with the user's emotions.

[0857] (Claim 2)

[0858] The system according to claim 1, which provides a user interface and displays a response autonomously analyzed for sentiment by a generative model.

[0859] (Claim 3)

[0860] The system according to claim 1, which continuously optimizes a generative model using business-related data and user feedback to improve the accuracy of sentiment analysis. [Explanation of symbols]

[0861] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. An information processing device that uses a generative model to improve the efficiency of business operations, A database means for collecting and storing information related to business operations, A learning method for training a generative model, A response means that generates a response via an international information and communication network and provides information to user equipment, A terminal device that accepts user input and presents answers through visual display, A system that includes this.

2. The system according to claim 1, wherein a user operates a user interface via a remotely controllable device, and a generative model autonomously displays a response quickly and accurately.

3. The system according to claim 1, which continuously optimizes the generative model using business-related information and user evaluation information.

Images