System

Abstract

A system is provided.SOLUTION: A system including means for collecting public information including utterance data and behavior data, means for preprocessing the collected public information, means for training a generative artificial intelligence model using the preprocessed data, means for generating optimal advice using the generative artificial intelligence model for a question input from a user, means for providing the generated advice to the user, and means for receiving feedback from the user and adjusting a parameter of the generative artificial intelligence model.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] Corporate management decisions are extremely complex, and especially for startups, a single management decision can determine the success or failure of a company. When making management decisions, advice from external experts is often sought in addition to internal advice, but it is difficult to always obtain appropriate advice from experts. Furthermore, the cost and time required to access external experts can be a significant burden. Therefore, there is a need to provide a system that supports important corporate management decisions by utilizing generative AI that mimics the thinking and judgment of well-known business leaders. [Means for solving the problem]

[0005] The present invention solves these problems with a system that includes: means for collecting public information including speech data and behavioral data; means for preprocessing the collected public information; means for training a generative AI model using the preprocessed data; means for generating optimal advice using the generative AI model in response to a question entered by a user; means for providing the generated advice to the user; means for receiving feedback from the user and adjusting parameters of the generative AI model; and means for periodically collecting public information on the Internet and generating specific advice in real time based on user questions. This system enables companies to receive prompt and accurate advice when making important management decisions, thereby improving the quality of their decision-making.

[0006] "Speech Data" refers to communication information in the form of voice and text sent by an individual or organization.

[0007] "Behavioral data" refers to data that records the past actions and choices of individuals or organizations.

[0008] "Public information" refers to data or documents that are freely accessible on the Internet.

[0009] "Preprocessing" refers to the process of removing unnecessary information from collected data and converting it into a format suitable for analysis and learning.

[0010] A "generative artificial intelligence model" refers to an AI model that uses machine learning algorithms to generate specific patterns or predictions.

[0011] "User" refers to a company or individual who uses the system to seek advice.

[0012] A "question" refers to the consultation or problem that a user inputs to the system.

[0013] "Advice" refers to advice or suggestions for business decisions provided by the generated AI model.

[0014] "Feedback" refers to evaluation information that a user sends back to the system regarding the usefulness and satisfaction of the advice provided.

[0015] "Parameters" refer to variables and settings used to control the behavior of an AI model.

[0016] "Collection methods" refers to technologies and methods for automatically obtaining public information from the Internet.

[0017] "Real-time" refers to a time frame that provides an immediate response to user input. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention relates to a system that uses generative AI to support companies in making important business decisions. The following is a detailed description of the mode for carrying out the invention.

[0040] User Registration and Authentication

[0041] A user first accesses the system and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the device sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email sent to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the device sends that information to the server. The server performs authentication and allows the user to log in.

[0042] Data collection and learning

[0043] The server periodically collects publicly available information from the internet. This information includes speech and behavioral data of prominent business leaders. The collected data is preprocessed by the server, filtering out unnecessary information and converting it into an analyzable format. The server then uses the preprocessed data to train a generative artificial intelligence model. This AI model is trained to mimic business decisions and thought patterns.

[0044] Providing advice

[0045] The user uses the system to input a question related to business decisions. The question includes specific situational and background information. The terminal sends the input question to the server. The server analyzes the input information and generates optimal advice using a trained generative artificial intelligence model. The generated advice is sent to the terminal and provided to the user. The user makes business decisions based on the provided advice.

[0046] Feedback and Improvements

[0047] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then adjusts the parameters of the generative AI model based on this feedback. This improves the quality of advice provided in the future.

[0048] Specific examples

[0049] When CEO A (user) wants advice for an important meeting regarding the market launch of a new product, he logs into the system and enters a question including detailed market analysis data and competitive information. The device sends this information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch a new product?", the AI ​​model will refer to past success stories and market trends to provide advice recommending the most appropriate market segment.

[0050] In this way, by using this system, companies can easily obtain advice from outside experts, thereby improving the quality of important management decisions.

[0051] The processing flow will be explained below.

[0052] Step 1:

[0053] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[0054] Step 2:

[0055] The terminal transmits the input information to the server.

[0056] Step 3:

[0057] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[0058] Step 4:

[0059] The user activates their account by clicking the link in the confirmation email.

[0060] Step 5:

[0061] The server detects the link click and updates the account status to "active."

[0062] Step 6:

[0063] A user enters an email address and password to log in to the system.

[0064] Step 7:

[0065] The terminal sends the input information to the server.

[0066] Step 8:

[0067] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[0068] Step 9:

[0069] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[0070] Step 10:

[0071] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[0072] Step 11:

[0073] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[0074] Step 12:

[0075] The server saves the trained model and makes it available for the next time advice is generated.

[0076] Step 13:

[0077] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[0078] Step 14:

[0079] The terminal transmits the input question to the server.

[0080] Step 15:

[0081] Based on the information received by the server, optimal advice is generated using a generative AI model.

[0082] Step 16:

[0083] The server sends the generated advice to the terminal and displays it to the user.

[0084] Step 17:

[0085] Users make business decisions based on the advice provided.

[0086] Step 18:

[0087] The user inputs feedback about the usefulness of the advice and sends it to the system.

[0088] Step 19:

[0089] The device sends the feedback to the server.

[0090] Step 20:

[0091] The server receives the feedback and adjusts the parameters of the generative AI model.

[0092] Step 21:

[0093] The server stores the feedback information in a database and uses it to provide advice next time.

[0094] Example 1

[0095] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0096] In today's business environment, quick and accurate management decisions are essential for a company's success. However, many companies lack sufficient resources to identify important data from vast amounts of information and make appropriate decisions. Small and medium-sized enterprises, in particular, face the challenge of finding advice from outside experts. Therefore, there is a need for a system that allows companies to easily obtain high-quality management advice and make quick decisions.

[0097] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0098] In this invention, the server includes: means for user registration and authentication in which a user inputs information such as a name, email address, and password and sends it from the terminal to the server; means for the server to periodically collect public information on the Internet; means for the server to preprocess the collected public information to remove unnecessary information and convert it into an analyzable format; means for the server to train a generative artificial intelligence model using the preprocessed data; means for a user to input a question to the system and send it from the terminal to the server; means for the server to analyze the content of the user's question and generate optimal advice using the trained generative artificial intelligence model; means for the server to send the generated advice to the terminal and provide it to the user; means for the user to input feedback on the effectiveness or application results of the advice and send it from the terminal to the server; and means for the server to adjust parameters of the generative artificial intelligence model based on the feedback received. This enables companies to obtain quick, high-quality management advice and improve the quality of management decisions.

[0099] "User registration and authentication" refers to the process in which a user enters information such as name, email address, and password to access the system and sends it from their terminal to the server, including verification of user information and account activation.

[0100] "Public information collection" refers to the collection of data that is regularly accessible on the Internet by a server (e.g., speech data and behavioral data of prominent business executives).

[0101] "Data preprocessing" is a means to refer to the process by which the server filters the collected data, removes unnecessary information, and converts it into an analyzable format.

[0102] A "generative artificial intelligence model" is an artificial intelligence model trained by a machine learning framework using pre-processed data, and is a means used to mimic business decisions.

[0103] "Question input" refers to a process in which a user inputs a specific question about business decisions into the system and transmits it from the terminal to the server.

[0104] "Advice generation" is the process in which the server analyzes the question entered by the user and generates optimal advice using a trained artificial intelligence model.

[0105] "Providing advice" is a means to refer to the process in which the server sends the advice generated by the server to the terminal and displays it to the user.

[0106] "Feedback input" refers to a process in which a user inputs into the system an evaluation of the effectiveness of the advice provided and the results of its application, and transmits the input from the terminal to the server.

[0107] "Model parameter adjustment" refers to a process or means by which the server adjusts the parameters of the generative artificial intelligence model based on feedback received from the user to improve the accuracy of the model.

[0108] A "scraping tool" refers to a software tool used to automatically retrieve data from websites on the Internet.

[0109] "Real-time advice" refers to a process in which, upon receiving a question from a user, the server quickly generates specific advice using an artificial intelligence model and provides it immediately.

[0110] The present invention relates to a system that uses generative artificial intelligence (AI) models to help companies make important business decisions. The following describes in detail the embodiments of the invention.

[0111] User Registration and Authentication

[0112] A user first accesses the system and registers as a new user. The user enters the required information on the registration page, such as name, email address, and password. The terminal then sends this information to the server. The server verifies the received information, converts it into the required format, and saves the new user information in a database. The server also sends a confirmation email to the user, and the user clicks on a link to activate the account. After that, when the user logs into the system, they enter their email address and password, and the terminal sends the information to the server. The server authenticates and allows them to log in. The software used includes a database management system (e.g., MySQL) and an email sending system (e.g., SendGrid).

[0113] Data collection and learning

[0114] The server periodically collects publicly available information on the Internet using a scraping tool (e.g., Beautiful Soup). This public information includes speech data and behavioral data of prominent business leaders. The server receives the collected data, filters it to remove unnecessary information, and converts it into an analyzable format (e.g., text normalization, JSON format). The server then uses the preprocessed data to train a generative artificial intelligence model using a machine learning framework (e.g., TensorFlow). The trained AI model is saved to mimic business decisions and thought patterns.

[0115] Providing advice

[0116] The user inputs a question related to business decisions into the system. The question includes specific situational and background information. The device sends the input question to the server. The server analyzes the question and generates optimal advice using a trained generative AI model. The generated advice is sent to the device and provided to the user. The user makes business decisions based on the advice provided. The software used includes data analysis software (e.g., Python library).

[0117] As a concrete example, if CEO A (user) wants advice for an important meeting regarding the launch of a new product, he logs into the system and inputs a question including detailed market analysis data and competitive information. The terminal sends the information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch our new product?", the AI ​​model will provide advice recommending the optimal market segment by referring to past success stories and market trends. An example of a prompt for this process is, "Please tell me the optimal market segment for launching a new product. We will provide current market analysis data and competitive information."

[0118] Feedback and Improvements

[0119] Users input feedback into the system regarding the effectiveness of the advice provided and the results of its application. The feedback includes evaluation items related to the advice's specificity, usefulness, and feasibility. The device sends the feedback to the server, which then adjusts the parameters of the generative AI model based on the received feedback. This improves the quality of advice provided in the future. The system continuously learns and improves through this feedback loop, providing more accurate management advice.

[0120] In this way, by using this system, companies can easily obtain high-quality advice for making quick and accurate management decisions. Furthermore, the system can be further improved through user feedback, allowing for continuous improvement in the quality of corporate management decisions.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1: User Registration

[0123] 1.1 A user accesses the new user registration page and enters information such as name, email address, and password (input: name, email address, password).

[0124] 1.2 The terminal sends the entered information to the server (output: user information).

[0125] 1.3 The server validates the received information, converts it into a format, and saves it in the database (processing: input data format validation and conversion, output: database storage).

[0126] 1.4 The server sends a confirmation email to the user (Output:Confirmation email).

[0127] 1.5 User activates account by clicking link in confirmation email (Input: link in confirmation email, Output: account activated).

[0128] Step 2: Login authentication

[0129] 2.1 The user accesses the login page and enters their email address and password (input: email address, password).

[0130] 2.2 The terminal sends the entered information to the server (output: login information).

[0131] 2.3 The server compares the received information with the database and performs authentication (process: database comparison, output: authentication result).

[0132] 2.4 If authentication is successful, the server allows the user to log in (output: session ID).

[0133] Step 3: Data collection

[0134] 3.1 The server runs a job to periodically collect public information on the Internet (output: collection schedule).

[0135] 3.2 The server collects public information using a scraping tool (input: URL list, output: collected data).

[0136] 3.3 The server temporarily stores the collected data (output: raw data).

[0137] Step 4: Data Preprocessing

[0138] 4.1 The server receives the collected data (input: raw data).

[0139] 4.2 The server filters the data and removes unnecessary information (Process: Data Cleansing, Output: Cleansed Data).

[0140] 4.3 The server converts the data into a parseable format (Process: Data normalization, Output: Preprocessed data).

[0141] Step 5: Training the AI ​​model

[0142] 5.1 The server provides the preprocessed data to the machine learning framework (input: preprocessed data).

[0143] 5.2 The server uses the data to train the AI ​​model (processing: machine learning, output: trained AI model).

[0144] 5.3 The server saves the trained AI model (output: saved AI model).

[0145] Step 6: Enter your question

[0146] 6.1 The user inputs a question about business decisions into the system (input: question content).

[0147] 6.2 The device sends the question to the server (output: question data).

[0148] Step 7: Generating Advice

[0149] 7.1 The server receives the query (input: query data).

[0150] 7.2 The server analyzes the question content and inputs it into the trained AI model (processing: question analysis, input: trained AI model, output: analyzed question data).

[0151] 7.3 The server generates optimal advice using the AI ​​model (Process: Advice generation, Output: Generated advice).

[0152] 7.4 The server sends the generated advice to the terminal (Output: Advice sent).

[0153] Step 8: Providing advice

[0154] 8.1 The terminal receives the advice sent from the server (input: advice sent).

[0155] 8.2 The terminal displays the advice on the user interface (Process: Display UI, Output: Displayed advice).

[0156] Step 9: Provide feedback

[0157] 9.1 The user inputs feedback on the effectiveness and application results of the provided advice (input: feedback content).

[0158] 9.2 The device sends feedback to the server (output: feedback data).

[0159] Step 10: Adjust the model parameters

[0160] 10.1 The server receives and parses the feedback (input: feedback data).

[0161] 10.2 The server adjusts the parameters of the AI ​​model based on the feedback (processing: parameter adjustment, output: adjusted parameters).

[0162] 10.3 The server retrains the AI ​​model using the adjusted parameters (Process: Retrain, Output: Improved AI model).

[0163] In this way, by linking users, devices, and servers, this system realizes a series of processes from user registration to learning the AI ​​model, providing advice, and improving the model through feedback.

[0164] (Application example 1)

[0165] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0166] Inventory management and work efficiency are key issues for modern logistics centers. With conventional systems, real-time data collection and analysis takes time, making it difficult to make effective management decisions. Furthermore, there are insufficient methods for efficiently reflecting the quality of advice provided and feedback on application results. For this reason, there is a demand for a system that supports fast and accurate management decisions in the operation of logistics centers.

[0167] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0168] In this invention, the server includes: means for collecting public information including speech data and behavioral data; means for preprocessing the collected public information; means for training a generative AI model using the preprocessed data; means for generating optimal advice using the generative AI model in response to a question input by a user; means for providing the generated advice to the user; means for receiving feedback from the user and adjusting parameters of the generative AI model; means for collecting real-time data via sensors and cameras in the logistics center; means for preprocessing the collected real-time data and analyzing it as business-related data; means for inputting the analyzed business data into the generative AI model and generating optimal logistics management advice in response to the user's question; means for instantly providing the generated logistics management advice to the user; and means for collecting user feedback on the logistics management advice and improving the generative AI model. This enables quick and accurate management decisions in the operation of a logistics center.

[0169] "Speech data" refers to human speech expressed in audio or text format.

[0170] "Behavioral data" refers to information about the specific actions and activities of humans and machines.

[0171] "Public information" refers to information that is publicly available via the Internet or other media.

[0172] "Preprocessing" refers to the process of removing unnecessary parts from raw data and converting it into an analyzable format.

[0173] A "generative artificial intelligence model" refers to an artificial intelligence model that can learn specific patterns or rules from input data and generate corresponding outputs based on new data.

[0174] "Real-time data" refers to the latest dynamic information collected from a system or environment.

[0175] A "logistics center" refers to a facility that stores, manages, and delivers goods and materials.

[0176] A "sensor" refers to a device that detects the surrounding physical conditions and environment and outputs the data.

[0177] "Camera" refers to a device that captures still images and video.

[0178] "Business data" refers to information related to business operations, such as inventory within the logistics center, workers, and truck operation status.

[0179] "Feedback" refers to the user's evaluation and opinion on the system output, and is used to improve the system's performance based on this.

[0180] This invention relates to a system that uses generative AI to support management decisions, primarily in logistics centers. A specific embodiment of this system is described below.

[0181] User Registration and Authentication

[0182] First, a user accesses the system using a terminal and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the terminal sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server performs authentication and allows them to log in.

[0183] Data collection and learning

[0184] The server collects real-time data from sensors and cameras installed within the distribution center. Collected data includes inventory levels, worker numbers, truck arrival status, and more. The server preprocesses the collected data and filters out unnecessary information. The preprocessed data is then used to train a generative artificial intelligence model. The trained AI model is designed to support optimal decisions regarding the operation of the distribution center.

[0185] Providing advice

[0186] Users log in to the system using a terminal and input questions related to specific business decisions. The questions include detailed business data and background information. The terminal then sends the input questions to the server. The server analyzes the input information and generates optimal advice using a trained generative AI model. The generated advice is then sent to the terminal and provided to the user. The user can then refer to the provided advice and make appropriate business decisions immediately.

[0187] Feedback and Improvements

[0188] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then uses this feedback to adjust the parameters of the generative AI model. This improves the quality of advice provided in the future.

[0189] Specific examples

[0190] For example, if a logistics center manager wants advice on how to improve inventory management, he or she can log in to the system and enter a specific question. The question includes data such as current inventory levels, number of workers, and truck arrival status. The device sends this information to a server, which uses an AI model to suggest optimal inventory management methods based on the latest logistics trends and past success stories. The manager can then immediately improve inventory management based on the advice provided.

[0191] An example of a prompt is, "Please tell us how the current inventory management system could be improved. The data collected is inventory levels, number of workers, and number of arriving trucks."

[0192] The above is a specific embodiment for carrying out the present invention. By using this system, it is expected that management decisions at logistics centers will be made more quickly and with greater accuracy.

[0193] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0194] Step 1:

[0195] User Registration and Authentication

[0196] Specific operation: A user accesses the system using a terminal and registers as a new user. The user enters information such as their name, email address, and password. The entered information is sent from the terminal to the server. The server verifies the received information and registers the new user information in the database. A confirmation email is then sent to the user. The user clicks the link in the email to activate their account, completing the registration. When the user subsequently logs in to the system, they enter their email address and password, and the terminal sends this information to the server. The server performs authentication and allows the user to log in.

[0197] Input: User input information (name, email address, password)

[0198] Output: New user registration completed and account activated

[0199] Step 2:

[0200] Data collection

[0201] How it works: The server collects real-time data from sensors and cameras installed in the distribution center, continuously collecting data on inventory levels, number of workers, truck arrival status, and more.

[0202] Input: Real-time data from sensors and cameras

[0203] Output: raw data collected

[0204] Step 3:

[0205] Data Preprocessing

[0206] Specific operation: The server preprocesses the collected raw data, filters out unnecessary information, removes noise from the data, and converts it into an analyzable format.

[0207] Input: raw data

[0208] Output: Preprocessed data

[0209] Step 4:

[0210] Training generative AI models

[0211] How it works: The server uses the preprocessed data to train a generative AI model, teaching it patterns and rules to support decisions about inventory management and work efficiency.

[0212] Input: Preprocessed data

[0213] Output: A trained generative AI model

[0214] Step 5:

[0215] Enter a question and generate advice

[0216] How it works: The user uses a device to input a question into the system. The question includes detailed business data. The device then sends the question to the server. The server analyzes the input question and uses a generative AI model to generate optimal advice.

[0217] Input: User question data

[0218] Output: The generated advice

[0219] Step 6:

[0220] Providing advice

[0221] Specific operation: The generated advice is sent to the terminal and displayed to the user, who then uses the advice to make quick business decisions.

[0222] Input: Generated advice

[0223] Output: Advice given to the user

[0224] Step 7:

[0225] Gathering feedback and improving the model

[0226] How it works: The user inputs feedback about the advice provided to the system from their device. The server receives the feedback and adjusts the parameters of the generative AI model based on that feedback, improving the accuracy of future advice.

[0227] Input: User feedback

[0228] Output: An improved generative AI model

[0229] Specific examples

[0230] For example, if a manager asks how to improve inventory management, the prompt might look something like this:

[0231] "How can we improve our current inventory management system? The data collected is about inventory levels, number of workers, and number of arriving trucks."

[0232] The above are the specific processing steps for carrying out the invention. This system enables quick and accurate management decisions at a logistics center.

[0233] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0234] This invention combines a system that uses generative AI to support business decisions with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the invention.

[0235] User Registration and Authentication

[0236] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends the entered information to the server, which verifies the received information and then registers the new user information in the database. At the same time, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server compares the information with the database and allows them to log in.

[0237] Data collection and learning

[0238] The server periodically collects publicly available information from the internet. This public information includes speech data and behavioral data of prominent business leaders. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model is trained to mimic business decisions and thought patterns.

[0239] Use of emotion engine

[0240] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the way it is input. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. Based on this, the generative AI model generates advice that best suits the user's emotional state. For example, if the user is feeling impatient or anxious, the system can provide advice on an approach that will alleviate that feeling.

[0241] Providing advice

[0242] When a user inputs a specific question, the device sends that information to the server, which then uses a generative AI model to generate optimal advice. The generated advice is adjusted to match the user's emotional state by an emotion engine and sent to the device. The device displays the advice to the user, allowing the user to make business decisions based on useful advice.

[0243] Feedback and Improvements

[0244] Users provide feedback to the system regarding the usefulness of the advice and the results of its application. This feedback also passes through the emotion engine, and the analysis results are used to adjust the parameters of the generative AI model. The device then sends the feedback to the server, which analyzes it and uses it as data to improve the AI ​​model. This can improve the accuracy of future advice and user satisfaction.

[0245] Specific examples

[0246] When CEO A (user) seeks advice for an important meeting regarding the market launch of a new product, he logs into the system and enters his question along with detailed market analysis data. The device sends this information to the server, which uses an emotion engine to recognize CEO A's emotional state. For example, if it recognizes that CEO A is feeling anxious, the server uses a generative AI model to provide specific and actionable advice to alleviate his anxiety. For example, it provides specific information regarding risk and return in the form of, "Market segment A is high risk, but has the potential for large returns. Segment B is low risk and is expected to have stable growth."

[0247] In this way, this system, which combines an emotion engine, can provide appropriate advice according to the user's emotional state and support corporate management decisions.

[0248] The processing flow will be explained below.

[0249] Step 1:

[0250] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[0251] Step 2:

[0252] The terminal transmits the input information to the server.

[0253] Step 3:

[0254] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[0255] Step 4:

[0256] The user activates their account by clicking the link in the confirmation email.

[0257] Step 5:

[0258] The server detects the link click and updates the account status to "active."

[0259] Step 6:

[0260] A user enters an email address and password to log in to the system.

[0261] Step 7:

[0262] The terminal sends the input information to the server.

[0263] Step 8:

[0264] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[0265] Step 9:

[0266] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[0267] Step 10:

[0268] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[0269] Step 11:

[0270] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[0271] Step 12:

[0272] The server saves the trained model and makes it available for the next time advice is generated.

[0273] Step 13:

[0274] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[0275] Step 14:

[0276] The terminal transmits the input question to the server.

[0277] Step 15:

[0278] Based on the information received by the server, optimal advice is generated using a generative AI model.

[0279] Step 16:

[0280] The server sends the generated advice to the terminal and displays it to the user.

[0281] Step 17:

[0282] Users make business decisions based on the advice provided.

[0283] Step 18:

[0284] The user inputs feedback about the usefulness of the advice and sends it to the system.

[0285] Step 19:

[0286] The device sends the feedback to the server.

[0287] Step 20:

[0288] The server receives the feedback and adjusts the parameters of the generative AI model.

[0289] Step 21:

[0290] The server stores the feedback information in a database and uses it to provide advice next time.

[0291] Step 22:

[0292] The emotion engine analyzes the user's emotional state from their input and feedback.

[0293] Step 23:

[0294] The server uses the analysis results of the emotion engine to generate advice suited to the user's emotional state.

[0295] Step 24:

[0296] The server uses the emotion engine's analysis results for the next advice and feedback analysis to improve the model.

[0297] Example 2

[0298] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0299] Today's business environment is complex and diverse, requiring managers to make quick and appropriate decisions based on a variety of data and information. However, systems that support business decisions do not take into account the user's emotional state, making it difficult to alleviate the anxiety and stress felt by the user and provide optimal advice. Furthermore, continuous learning and model improvement are necessary to improve the usefulness of generated advice. The purpose of this invention is to solve these problems.

[0300] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0301] In this invention, the server includes means for collecting public information, means for preprocessing the collected public information, means for training a generative AI model using the preprocessed data, means for recognizing a user's emotional state, means for adjusting the generated advice based on the recognized emotional state, and means for receiving feedback from the user and adjusting parameters of the generative AI model. This makes it possible to provide appropriate advice tailored to the user's emotional state and effectively support business decisions.

[0302] "Public information" refers to data or information that is publicly accessible on the Internet, including, for example, news articles, blogs, social media posts, research papers, statements and behavioral data of management, etc.

[0303] "Preprocessing" refers to the process of applying data cleansing, text normalization, filtering, and other processes to collected data to prepare it in a format suitable for analysis.

[0304] A "generative artificial intelligence model" is an AI model trained using machine learning and deep learning techniques that performs inference and generation based on user input.

[0305] "Emotional state" refers to the psychological state or emotion that the user is feeling, and involves analyzing emotions such as anxiety, impatience, and joy.

[0306] "Adjusting advice" means appropriately modifying the generated advice in accordance with the user's emotional state and providing it to the user in an optimal form.

[0307] "Feedback" refers to the user inputting into the system evaluations and opinions about the usefulness of the advice provided and the results of its application.

[0308] "Parameter tuning" refers to readjusting the internal settings and weights of an AI model based on feedback from users to improve the model's performance and accuracy.

[0309] This invention combines a system that uses a generative AI model to support business decisions with an emotion engine that recognizes user emotions. Below, we will explain in detail the embodiments of the invention.

[0310] Overall structure

[0311] The system mainly consists of a server, a terminal, and a user interface. The server is responsible for data collection, preprocessing, AI model training, emotion recognition, and advice generation, while the terminal is responsible for inputting questions from users and sending and receiving feedback. Users access the system using various devices.

[0312] User Registration and Authentication

[0313] A user accesses the system and enters the required information, such as name, email address, and password, into the new user registration page. The terminal sends the entered information to the server, which verifies the information and then registers the new user information in the database. Once registration is complete, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. Thereafter, the user enters their email address and password to log in to the system. The terminal sends the information to the server, which verifies it against the information in the database and allows the user to log in.

[0314] Data collection and learning

[0315] The server periodically collects publicly available information on the Internet, particularly executive speech and behavioral data. This process utilizes web scraping and API access. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This training is carried out using deep learning frameworks such as TensorFlow and PyTorch.

[0316] Use of emotion engine

[0317] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the input method. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. The recognized emotional state is used as an important factor in the generative AI model to generate optimal advice.

[0318] Providing advice

[0319] When a user inputs a specific question into the system, the device sends that information to the server. The server uses a generative AI model to generate optimal advice. The generated advice is then adjusted to the user's emotional state by an emotion engine. The adjusted advice is then provided to the user via the device. For example, if the user is feeling anxious, specific advice to alleviate that anxiety is provided.

[0320] Feedback and Improvements

[0321] The user enters feedback about the usefulness of the advice provided and the results of its application. This feedback information is sent from the device to the server, which analyzes it. The results of analyzing the feedback data are used to retrain the generative AI model next time, improving the model's performance and accuracy.

[0322] Specific examples

[0323] For example, if a manager seeks advice on launching a new product, he or she logs into the system and enters, "Please give me some advice on launching a new product. I'm currently feeling anxious about the intensifying competition in the online market." The device sends this information to the server, which uses an emotion engine to recognize the manager's emotional state. If anxiety is recognized, the server generates specific advice to alleviate the anxiety, such as, "Market segment A is high risk, but you can expect a big return. Segment B is low risk and is expected to grow steadily." Based on this advice, the manager can make business decisions with confidence.

[0324] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0325] Step 1:

[0326] A user accesses the system and enters required information such as name, email address, and password into the new user registration page.

[0327] Input: Username, Email Address, Password

[0328] Output: Complete set of input data

[0329] Specific operation: The user enters information into a form on a web browser and presses the submit button.

[0330] Step 2:

[0331] The terminal transmits the input information to the server.

[0332] Input: All input data (user name, email address, password)

[0333] Output: HTTP request to the server

[0334] Specific behavior: The form data is sent to the server as an HTTP POST request.

[0335] Step 3:

[0336] The server verifies the received information and registers the new user information in the database.

[0337] Input: Submitted user registration information

[0338] Output: Registration results in the database

[0339] Specific operation: The server checks the format of the input data and the strength of the password, and if there are no problems, it saves the information in the database.

[0340] Step 4:

[0341] The server sends a confirmation email to the user's email address.

[0342] Input: User's email address and confirmation email content

[0343] Output:Confirmation email

[0344] What happens: The server will send a confirmation email via the SMTP server, which will contain a link to activate your account.

[0345] Step 5:

[0346] The user activates their account by clicking the link in the confirmation email.

[0347] Input: Link in confirmation email

[0348] Output: Account enabled

[0349] What happens: When a user clicks on the link, the server receives the request and updates the user status in the database to active.

[0350] Step 6:

[0351] The user enters their email address and password, and the device sends that information to the server, which checks it against a database and allows them to log in.

[0352] Input: Email address, password

[0353] Output: Session information for successful login

[0354] Specific operation: The entered information is sent to the server and compared with the user information in the database. If authentication is successful, a session is created.

[0355] Step 7:

[0356] The server periodically collects public information on the Internet.

[0357] Input: Public data sources on the internet

[0358] Output: Collected dataset

[0359] Specific operations: The server periodically performs scraping and API access to collect data on managerial statements and behavior.

[0360] Step 8:

[0361] The server preprocesses the collected data, normalizing the text and filtering out unnecessary information.

[0362] Input: Collected public data

[0363] Output: Preprocessed dataset

[0364] Specific operation: Data is cleansed using an NLP library (e.g., spaCy) and formatted for analysis.

[0365] Step 9:

[0366] The server uses the preprocessed data to train the generative AI model.

[0367] Input: Preprocessed dataset

[0368] Output: The trained AI model

[0369] Specific operation: Train generative AI models using TensorFlow and PyTorch. Use high-performance GPUs to streamline learning.

[0370] Step 10:

[0371] A user uses the system to enter a question and the terminal sends the information to the server.

[0372] Input: Question data from the user

[0373] Output: Submitted question data

[0374] What happens: A user uses a web interface to enter a question and presses the submit button, which sends the data to the server as an HTTP POST request.

[0375] Step 11:

[0376] The server uses an emotion engine to recognize the user's emotional state.

[0377] Input: Submitted question data

[0378] Output: Perceived emotional state

[0379] Specific operation: The server calls an emotion analysis API (e.g., IBM Watson Natural Language Understanding) to perform emotion recognition.

[0380] Step 12:

[0381] The server uses a generative AI model to generate optimal advice, which is then adjusted by an emotion engine.

[0382] Input: User question data, perceived emotional state

[0383] Output: Adjusted advice

[0384] Specific operation: The prompt sentence "Please give me some advice on launching a new product to market" is passed as input to the generative AI model, and the generated text is adjusted using the emotion engine.

[0385] Step 13:

[0386] The terminal displays the received advice to the user.

[0387] Input: Tailored Advice

[0388] Output: Advice displayed to the user

[0389] Specific operation: The received advice content is displayed on the web browser.

[0390] Step 14:

[0391] The user inputs feedback into the system regarding the usefulness of the advice and the results of its application.

[0392] Input: Feedback data

[0393] Output: Input feedback data

[0394] Specific operation: The user uses the web interface to enter ratings and comments and presses the submit button.

[0395] Step 15:

[0396] The terminal sends feedback information to the server.

[0397] Input: Feedback data

[0398] Output: HTTP request to the server

[0399] Specific behavior: The form data is sent to the server as an HTTP POST request.

[0400] Step 16:

[0401] The server analyzes the feedback and uses it as data to improve the generative AI model.

[0402] Input: Submitted feedback data

[0403] Output: AI model calibration data

[0404] What it does: Analyzes the feedback data and uses it to retrain the generative AI model, improving its performance and accuracy.

[0405] (Application example 2)

[0406] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0407] Conventional systems using generative AI provide management decisions and advice without considering the user's emotional state, resulting in a lack of advice that is optimal for the user's psychological state. Furthermore, when dealing with customers in brick-and-mortar stores, there is a lack of means to recognize emotions in real time and provide advice that is in line with the user's needs, making it difficult to improve customer satisfaction.

[0408] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting public information including utterance data and behavioral data, means for preprocessing the collected public information, means for training a generative artificial intelligence model using the preprocessed data, emotion analysis means for recognizing the user's emotional state, means for generating advice optimal for the user's question based on the generative artificial intelligence model, means for providing the generated advice to the user, means for displaying or outputting advice by voice in real time according to the usage environment, and means for receiving feedback from the user and adjusting parameters of the generative artificial intelligence model. This makes it possible to provide optimal advice based on the user's emotional state in real time and improve customer satisfaction.

[0409] "Speech data" refers to information converted from speech into text format.

[0410] "Behavioral data" refers to information that records a user's actions, location, operation history, etc.

[0411] "Public Information" means publicly accessible information that is published on the Internet.

[0412] "Preprocessing" refers to the process of formatting collected data into a form that is easy to analyze.

[0413] A "generative artificial intelligence model" is an AI model that is trained using large amounts of data.

[0414] "Emotion analysis means" refers to technology or equipment for recognizing a user's emotional state from text or voice data.

[0415] "Advice generation means" refers to AI technologies and algorithms that provide optimal advice based on user input and status.

[0416] The "advice providing means" refers to devices such as a display and a speaker for presenting the generated advice to the user.

[0417] "Real-time display means" refers to technology or equipment for displaying advice on the user's condition without delay.

[0418] "Real-time voice output means" refers to technology or equipment for instantly providing generated advice in voice form.

[0419] "Feedback receiving means" refers to the technology and equipment used to collect opinions and reactions from users.

[0420] "Parameter adjustment means" refers to techniques or equipment for improving the performance of an artificial intelligence model based on collected feedback information.

[0421] The present invention provides a system for recognizing a user's emotional state and providing appropriate management decisions and advice based on the recognition. The system is configured using various hardware and software.

[0422] User Registration and Authentication

[0423] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends this information to the server, which then registers the new user information in the database based on the received information. At the same time, a confirmation email is sent to the user's email address. When the user clicks on the link contained in the confirmation email, their account is activated and they can then log in to the system.

[0424] Data collection and learning

[0425] The server periodically collects public information from the Internet (such as speech data and behavioral data). This is done using Python scraping technology and public APIs. The collected data is preprocessed to normalize the text and filter out unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model uses Hugging Face's Transformers library and TensorFlow.

[0426] Use of emotion engine

[0427] When a user uses the system to input a question, the device sends that information to the server. The server's emotion analysis means analyzes the user's emotional state from their text and voice data. Based on the analysis results, the generative AI model generates optimal advice based on the user's emotional state.

[0428] Providing advice

[0429] The generated advice is provided to the user via the device. The display of the smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The advice is displayed or output as audio in real time, allowing the user to respond immediately.

[0430] Feedback and Improvements

[0431] User feedback is sent to the server via the device, which then adjusts the parameters of the generative AI model to improve its accuracy. This process uses a specific algorithm (e.g., backpropagation).

[0432] Specific examples

[0433] For example, if a store staff member receives feedback from a customer saying, "I'd like to learn more about this product, but I have some concerns.":

[0434] Provided prompt: The user is feeling anxious. Please give some advice to ease their anxiety.

[0435] The server uses a generative AI model to generate advice such as, "This product is of high quality and has satisfied many customers in the past. Don't worry."

[0436] In this way, the system can provide optimal advice according to the user's emotional state, increasing customer satisfaction.

[0437] To implement this invention, we use a smartphone or tablet as hardware and Python, TensorFlow, the Hugging Face Transformers library, etc. as software. This system enables real-time emotion analysis and advice provision.

[0438] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0439] Step 1: User Registration and Authentication

[0440] A user accesses the new user registration page and enters the required information, such as name, email address, and password. The terminal sends this information to the server, which registers the received information in a database. At the same time, a confirmation email is sent to the user's email address. The user clicks the link in the confirmation email to activate their account. When the user then logs in with their email address and password, the terminal sends that information to the server, which collates it with the database information and allows them to log in. The input is the user's registration information, and the output is the sending of a confirmation email and account activation information.

[0441] Step 2: Data collection and preprocessing

[0442] The server periodically collects public information (speech data, behavioral data) from the Internet. Collection methods include scraping technology using Python and public APIs. The server preprocesses the collected data, such as normalizing the text and filtering out unnecessary information, and stores it in a database. The input is public information from the Internet, and the output is the preprocessed data.

[0443] Step 3: Training the generative AI model

[0444] Using the preprocessed data, the server trains a generative AI model using TensorFlow or Hugging Face's Transformers library. This is to optimize the model parameters based on large amounts of data and apply them to business decisions and advice generation. The input is the preprocessed data, and the output is a trained generative AI model.

[0445] Step 4: Sentiment Analysis

[0446] When a user uses the system to input a question, the device sends that information to the server. The server uses an emotion analysis means (emotion engine) to analyze the user's emotional state from text and voice data and provides the results to the generative AI model. The input is the user's question data, and the output is the user's emotional state.

[0447] Step 5: Advice Generation

[0448] The server uses a generative AI model to generate optimal advice based on the emotional state. A prompt such as "The user is feeling anxious. Please give us some advice to alleviate their anxiety" is input into the generative AI model, which then outputs specific advice. The inputs are the emotion analysis results and the prompt, and the output is the generated advice.

[0449] Step 6: Providing advice

[0450] The generated advice is sent from the server to the terminal, which then presents it to the user. The display of a smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The input is the generated advice, and the output is the advice display or audio provided to the user.

[0451] Step 7: Feedback and model adjustment

[0452] The user inputs feedback into the system about the usefulness of the advice that was implemented. The device sends the feedback to the server, which analyzes it and adjusts the parameters of the generative AI model. The input is the user's feedback, and the output is the adjusted generative AI model.

[0453] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0454] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0455] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0456] [Second embodiment]

[0457] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0458] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0459] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0460] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0461] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0462] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0463] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0464] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0465] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0466] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0467] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0468] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0469] This invention relates to a system that uses generative AI to support companies in making important business decisions. The following is a detailed description of the mode for carrying out the invention.

[0470] User Registration and Authentication

[0471] A user first accesses the system and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the device sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email sent to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the device sends that information to the server. The server performs authentication and allows the user to log in.

[0472] Data collection and learning

[0473] The server periodically collects publicly available information from the internet. This information includes speech and behavioral data of prominent business leaders. The collected data is preprocessed by the server, filtering out unnecessary information and converting it into an analyzable format. The server then uses the preprocessed data to train a generative artificial intelligence model. This AI model is trained to mimic business decisions and thought patterns.

[0474] Providing advice

[0475] The user uses the system to input a question related to business decisions. The question includes specific situational and background information. The terminal sends the input question to the server. The server analyzes the input information and generates optimal advice using a trained generative artificial intelligence model. The generated advice is sent to the terminal and provided to the user. The user makes business decisions based on the provided advice.

[0476] Feedback and Improvements

[0477] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then adjusts the parameters of the generative AI model based on this feedback. This improves the quality of advice provided in the future.

[0478] Specific examples

[0479] When CEO A (user) wants advice for an important meeting regarding the market launch of a new product, he logs into the system and enters a question including detailed market analysis data and competitive information. The device sends this information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch a new product?", the AI ​​model will refer to past success stories and market trends to provide advice recommending the most appropriate market segment.

[0480] In this way, by using this system, companies can easily obtain advice from outside experts, thereby improving the quality of important management decisions.

[0481] The processing flow will be explained below.

[0482] Step 1:

[0483] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[0484] Step 2:

[0485] The terminal transmits the input information to the server.

[0486] Step 3:

[0487] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[0488] Step 4:

[0489] The user activates their account by clicking the link in the confirmation email.

[0490] Step 5:

[0491] The server detects the link click and updates the account status to "active."

[0492] Step 6:

[0493] A user enters an email address and password to log in to the system.

[0494] Step 7:

[0495] The terminal sends the input information to the server.

[0496] Step 8:

[0497] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[0498] Step 9:

[0499] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[0500] Step 10:

[0501] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[0502] Step 11:

[0503] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[0504] Step 12:

[0505] The server saves the trained model and makes it available for the next time advice is generated.

[0506] Step 13:

[0507] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[0508] Step 14:

[0509] The terminal transmits the input question to the server.

[0510] Step 15:

[0511] Based on the information received by the server, optimal advice is generated using a generative AI model.

[0512] Step 16:

[0513] The server sends the generated advice to the terminal and displays it to the user.

[0514] Step 17:

[0515] Users make business decisions based on the advice provided.

[0516] Step 18:

[0517] The user inputs feedback about the usefulness of the advice and sends it to the system.

[0518] Step 19:

[0519] The device sends the feedback to the server.

[0520] Step 20:

[0521] The server receives the feedback and adjusts the parameters of the generative AI model.

[0522] Step 21:

[0523] The server stores the feedback information in a database and uses it to provide advice next time.

[0524] Example 1

[0525] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0526] In today's business environment, quick and accurate management decisions are essential for a company's success. However, many companies lack sufficient resources to identify important data from vast amounts of information and make appropriate decisions. Small and medium-sized enterprises, in particular, face the challenge of finding advice from outside experts. Therefore, there is a need for a system that allows companies to easily obtain high-quality management advice and make quick decisions.

[0527] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0528] In this invention, the server includes: means for user registration and authentication in which a user inputs information such as a name, email address, and password and sends it from the terminal to the server; means for the server to periodically collect public information on the Internet; means for the server to preprocess the collected public information to remove unnecessary information and convert it into an analyzable format; means for the server to train a generative artificial intelligence model using the preprocessed data; means for a user to input a question to the system and send it from the terminal to the server; means for the server to analyze the content of the user's question and generate optimal advice using the trained generative artificial intelligence model; means for the server to send the generated advice to the terminal and provide it to the user; means for the user to input feedback on the effectiveness or application results of the advice and send it from the terminal to the server; and means for the server to adjust parameters of the generative artificial intelligence model based on the feedback received. This enables companies to obtain quick, high-quality management advice and improve the quality of management decisions.

[0529] "User registration and authentication" refers to the process in which a user enters information such as name, email address, and password to access the system and sends it from their terminal to the server, including verification of user information and account activation.

[0530] "Public information collection" refers to the collection of data that is regularly accessible on the Internet by a server (e.g., speech data and behavioral data of prominent business executives).

[0531] "Data preprocessing" is a means to refer to the process by which the server filters the collected data, removes unnecessary information, and converts it into an analyzable format.

[0532] A "generative artificial intelligence model" is an artificial intelligence model trained by a machine learning framework using pre-processed data, and is a means used to mimic business decisions.

[0533] "Question input" refers to a process in which a user inputs a specific question about business decisions into the system and transmits it from the terminal to the server.

[0534] "Advice generation" is the process in which the server analyzes the question entered by the user and generates optimal advice using a trained artificial intelligence model.

[0535] "Providing advice" is a means to refer to the process in which the server sends the advice generated by the server to the terminal and displays it to the user.

[0536] "Feedback input" refers to a process in which a user inputs into the system an evaluation of the effectiveness of the advice provided and the results of its application, and transmits the input from the terminal to the server.

[0537] "Model parameter adjustment" refers to a process or means by which the server adjusts the parameters of the generative artificial intelligence model based on feedback received from the user to improve the accuracy of the model.

[0538] A "scraping tool" refers to a software tool used to automatically retrieve data from websites on the Internet.

[0539] "Real-time advice" refers to a process in which, upon receiving a question from a user, the server quickly generates specific advice using an artificial intelligence model and provides it immediately.

[0540] The present invention relates to a system that uses generative artificial intelligence (AI) models to help companies make important business decisions. The following describes in detail the embodiments of the invention.

[0541] User Registration and Authentication

[0542] A user first accesses the system and registers as a new user. The user enters the required information on the registration page, such as name, email address, and password. The terminal then sends this information to the server. The server verifies the received information, converts it into the required format, and saves the new user information in a database. The server also sends a confirmation email to the user, and the user clicks on a link to activate the account. After that, when the user logs into the system, they enter their email address and password, and the terminal sends the information to the server. The server authenticates and allows them to log in. The software used includes a database management system (e.g., MySQL) and an email sending system (e.g., SendGrid).

[0543] Data collection and learning

[0544] The server periodically collects publicly available information on the Internet using a scraping tool (e.g., Beautiful Soup). This public information includes speech data and behavioral data of prominent business leaders. The server receives the collected data, filters it to remove unnecessary information, and converts it into an analyzable format (e.g., text normalization, JSON format). The server then uses the preprocessed data to train a generative artificial intelligence model using a machine learning framework (e.g., TensorFlow). The trained AI model is saved to mimic business decisions and thought patterns.

[0545] Providing advice

[0546] The user inputs a question related to business decisions into the system. The question includes specific situational and background information. The device sends the input question to the server. The server analyzes the question and generates optimal advice using a trained generative AI model. The generated advice is sent to the device and provided to the user. The user makes business decisions based on the advice provided. The software used includes data analysis software (e.g., Python library).

[0547] As a concrete example, if CEO A (user) wants advice for an important meeting regarding the launch of a new product, he logs into the system and inputs a question including detailed market analysis data and competitive information. The terminal sends the information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch our new product?", the AI ​​model will provide advice recommending the optimal market segment by referring to past success stories and market trends. An example of a prompt for this process is, "Please tell me the optimal market segment for launching a new product. We will provide current market analysis data and competitive information."

[0548] Feedback and Improvements

[0549] Users input feedback into the system regarding the effectiveness of the advice provided and the results of its application. The feedback includes evaluation items related to the advice's specificity, usefulness, and feasibility. The device sends the feedback to the server, which then adjusts the parameters of the generative AI model based on the received feedback. This improves the quality of advice provided in the future. The system continuously learns and improves through this feedback loop, providing more accurate management advice.

[0550] In this way, by using this system, companies can easily obtain high-quality advice for making quick and accurate management decisions. Furthermore, the system can be further improved through user feedback, allowing for continuous improvement in the quality of corporate management decisions.

[0551] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0552] Step 1: User Registration

[0553] 1.1 A user accesses the new user registration page and enters information such as name, email address, and password (input: name, email address, password).

[0554] 1.2 The terminal sends the entered information to the server (output: user information).

[0555] 1.3 The server validates the received information, converts it into a format, and saves it in the database (processing: input data format validation and conversion, output: database storage).

[0556] 1.4 The server sends a confirmation email to the user (Output:Confirmation email).

[0557] 1.5 User activates account by clicking link in confirmation email (Input: link in confirmation email, Output: account activated).

[0558] Step 2: Login authentication

[0559] 2.1 The user accesses the login page and enters their email address and password (input: email address, password).

[0560] 2.2 The terminal sends the entered information to the server (output: login information).

[0561] 2.3 The server compares the received information with the database and performs authentication (process: database comparison, output: authentication result).

[0562] 2.4 If authentication is successful, the server allows the user to log in (output: session ID).

[0563] Step 3: Data collection

[0564] 3.1 The server runs a job to periodically collect public information on the Internet (output: collection schedule).

[0565] 3.2 The server collects public information using a scraping tool (input: URL list, output: collected data).

[0566] 3.3 The server temporarily stores the collected data (output: raw data).

[0567] Step 4: Data Preprocessing

[0568] 4.1 The server receives the collected data (input: raw data).

[0569] 4.2 The server filters the data and removes unnecessary information (Process: Data Cleansing, Output: Cleansed Data).

[0570] 4.3 The server converts the data into a parseable format (Process: Data normalization, Output: Preprocessed data).

[0571] Step 5: Training the AI ​​model

[0572] 5.1 The server provides the preprocessed data to the machine learning framework (input: preprocessed data).

[0573] 5.2 The server uses the data to train the AI ​​model (processing: machine learning, output: trained AI model).

[0574] 5.3 The server saves the trained AI model (output: saved AI model).

[0575] Step 6: Enter your question

[0576] 6.1 The user inputs a question about business decisions into the system (input: question content).

[0577] 6.2 The device sends the question to the server (output: question data).

[0578] Step 7: Generating Advice

[0579] 7.1 The server receives the query (input: query data).

[0580] 7.2 The server analyzes the question content and inputs it into the trained AI model (processing: question analysis, input: trained AI model, output: analyzed question data).

[0581] 7.3 The server generates optimal advice using the AI ​​model (Process: Advice generation, Output: Generated advice).

[0582] 7.4 The server sends the generated advice to the terminal (Output: Advice sent).

[0583] Step 8: Providing advice

[0584] 8.1 The terminal receives the advice sent from the server (input: advice sent).

[0585] 8.2 The terminal displays the advice on the user interface (Process: Display UI, Output: Displayed advice).

[0586] Step 9: Provide feedback

[0587] 9.1 The user inputs feedback on the effectiveness and application results of the provided advice (input: feedback content).

[0588] 9.2 The device sends feedback to the server (output: feedback data).

[0589] Step 10: Adjust the model parameters

[0590] 10.1 The server receives and parses the feedback (input: feedback data).

[0591] 10.2 The server adjusts the parameters of the AI ​​model based on the feedback (processing: parameter adjustment, output: adjusted parameters).

[0592] 10.3 The server retrains the AI ​​model using the adjusted parameters (Process: Retrain, Output: Improved AI model).

[0593] In this way, by linking users, devices, and servers, this system realizes a series of processes from user registration to learning the AI ​​model, providing advice, and improving the model through feedback.

[0594] (Application example 1)

[0595] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0596] Inventory management and work efficiency are key issues for modern logistics centers. With conventional systems, real-time data collection and analysis takes time, making it difficult to make effective management decisions. Furthermore, there are insufficient methods for efficiently reflecting the quality of advice provided and feedback on application results. For this reason, there is a demand for a system that supports fast and accurate management decisions in the operation of logistics centers.

[0597] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0598] In this invention, the server includes: means for collecting public information including speech data and behavioral data; means for preprocessing the collected public information; means for training a generative AI model using the preprocessed data; means for generating optimal advice using the generative AI model in response to a question input by a user; means for providing the generated advice to the user; means for receiving feedback from the user and adjusting parameters of the generative AI model; means for collecting real-time data via sensors and cameras in the logistics center; means for preprocessing the collected real-time data and analyzing it as business-related data; means for inputting the analyzed business data into the generative AI model and generating optimal logistics management advice in response to the user's question; means for instantly providing the generated logistics management advice to the user; and means for collecting user feedback on the logistics management advice and improving the generative AI model. This enables quick and accurate management decisions in the operation of a logistics center.

[0599] "Speech data" refers to human speech expressed in audio or text format.

[0600] "Behavioral data" refers to information about the specific actions and activities of humans and machines.

[0601] "Public information" refers to information that is publicly available via the Internet or other media.

[0602] "Preprocessing" refers to the process of removing unnecessary parts from raw data and converting it into an analyzable format.

[0603] A "generative artificial intelligence model" refers to an artificial intelligence model that can learn specific patterns or rules from input data and generate corresponding outputs based on new data.

[0604] "Real-time data" refers to the latest dynamic information collected from a system or environment.

[0605] A "logistics center" refers to a facility that stores, manages, and delivers goods and materials.

[0606] A "sensor" refers to a device that detects the surrounding physical conditions and environment and outputs the data.

[0607] "Camera" refers to a device that captures still images and video.

[0608] "Business data" refers to information related to business operations, such as inventory within the logistics center, workers, and truck operation status.

[0609] "Feedback" refers to the user's evaluation and opinion on the system output, and is used to improve the system's performance based on this.

[0610] This invention relates to a system that uses generative AI to support management decisions, primarily in logistics centers. A specific embodiment of this system is described below.

[0611] User Registration and Authentication

[0612] First, a user accesses the system using a terminal and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the terminal sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server performs authentication and allows them to log in.

[0613] Data collection and learning

[0614] The server collects real-time data from sensors and cameras installed within the distribution center. Collected data includes inventory levels, worker numbers, truck arrival status, and more. The server preprocesses the collected data and filters out unnecessary information. The preprocessed data is then used to train a generative artificial intelligence model. The trained AI model is designed to support optimal decisions regarding the operation of the distribution center.

[0615] Providing advice

[0616] Users log in to the system using a terminal and input questions related to specific business decisions. The questions include detailed business data and background information. The terminal then sends the input questions to the server. The server analyzes the input information and generates optimal advice using a trained generative AI model. The generated advice is then sent to the terminal and provided to the user. The user can then refer to the provided advice and make appropriate business decisions immediately.

[0617] Feedback and Improvements

[0618] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then uses this feedback to adjust the parameters of the generative AI model. This improves the quality of advice provided in the future.

[0619] Specific examples

[0620] For example, if a logistics center manager wants advice on how to improve inventory management, he or she can log in to the system and enter a specific question. The question includes data such as current inventory levels, number of workers, and truck arrival status. The device sends this information to a server, which uses an AI model to suggest optimal inventory management methods based on the latest logistics trends and past success stories. The manager can then immediately improve inventory management based on the advice provided.

[0621] An example of a prompt is, "Please tell us how the current inventory management system could be improved. The data collected is inventory levels, number of workers, and number of arriving trucks."

[0622] The above is a specific embodiment for carrying out the present invention. By using this system, it is expected that management decisions at logistics centers will be made more quickly and with greater accuracy.

[0623] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0624] Step 1:

[0625] User Registration and Authentication

[0626] Specific operation: A user accesses the system using a terminal and registers as a new user. The user enters information such as their name, email address, and password. The entered information is sent from the terminal to the server. The server verifies the received information and registers the new user information in the database. A confirmation email is then sent to the user. The user clicks the link in the email to activate their account, completing the registration. When the user subsequently logs in to the system, they enter their email address and password, and the terminal sends this information to the server. The server performs authentication and allows the user to log in.

[0627] Input: User input information (name, email address, password)

[0628] Output: New user registration completed and account activated

[0629] Step 2:

[0630] Data collection

[0631] How it works: The server collects real-time data from sensors and cameras installed in the distribution center, continuously collecting data on inventory levels, number of workers, truck arrival status, and more.

[0632] Input: Real-time data from sensors and cameras

[0633] Output: raw data collected

[0634] Step 3:

[0635] Data Preprocessing

[0636] Specific operation: The server preprocesses the collected raw data, filters out unnecessary information, removes noise from the data, and converts it into an analyzable format.

[0637] Input: raw data

[0638] Output: Preprocessed data

[0639] Step 4:

[0640] Training generative AI models

[0641] How it works: The server uses the preprocessed data to train a generative AI model, teaching it patterns and rules to support decisions about inventory management and work efficiency.

[0642] Input: Preprocessed data

[0643] Output: A trained generative AI model

[0644] Step 5:

[0645] Enter a question and generate advice

[0646] How it works: The user uses a device to input a question into the system. The question includes detailed business data. The device then sends the question to the server. The server analyzes the input question and uses a generative AI model to generate optimal advice.

[0647] Input: User question data

[0648] Output: The generated advice

[0649] Step 6:

[0650] Providing advice

[0651] Specific operation: The generated advice is sent to the terminal and displayed to the user, who then uses the advice to make quick business decisions.

[0652] Input: Generated advice

[0653] Output: Advice given to the user

[0654] Step 7:

[0655] Gathering feedback and improving the model

[0656] How it works: The user inputs feedback about the advice provided to the system from their device. The server receives the feedback and adjusts the parameters of the generative AI model based on that feedback, improving the accuracy of future advice.

[0657] Input: User feedback

[0658] Output: An improved generative AI model

[0659] Specific examples

[0660] For example, if a manager asks how to improve inventory management, the prompt might look something like this:

[0661] "How can we improve our current inventory management system? The data collected is about inventory levels, number of workers, and number of arriving trucks."

[0662] The above are the specific processing steps for carrying out the invention. This system enables quick and accurate management decisions at a logistics center.

[0663] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0664] This invention combines a system that uses generative AI to support business decisions with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the invention.

[0665] User Registration and Authentication

[0666] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends the entered information to the server, which verifies the received information and then registers the new user information in the database. At the same time, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server compares the information with the database and allows them to log in.

[0667] Data collection and learning

[0668] The server periodically collects publicly available information from the internet. This public information includes speech data and behavioral data of prominent business leaders. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model is trained to mimic business decisions and thought patterns.

[0669] Use of emotion engine

[0670] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the way it is input. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. Based on this, the generative AI model generates advice that best suits the user's emotional state. For example, if the user is feeling impatient or anxious, the system can provide advice on an approach that will alleviate that feeling.

[0671] Providing advice

[0672] When a user inputs a specific question, the device sends that information to the server, which then uses a generative AI model to generate optimal advice. The generated advice is adjusted to match the user's emotional state by an emotion engine and sent to the device. The device displays the advice to the user, allowing the user to make business decisions based on useful advice.

[0673] Feedback and Improvements

[0674] Users provide feedback to the system regarding the usefulness of the advice and the results of its application. This feedback also passes through the emotion engine, and the analysis results are used to adjust the parameters of the generative AI model. The device then sends the feedback to the server, which analyzes it and uses it as data to improve the AI ​​model. This can improve the accuracy of future advice and user satisfaction.

[0675] Specific examples

[0676] When CEO A (user) seeks advice for an important meeting regarding the market launch of a new product, he logs into the system and enters his question along with detailed market analysis data. The device sends this information to the server, which uses an emotion engine to recognize CEO A's emotional state. For example, if it recognizes that CEO A is feeling anxious, the server uses a generative AI model to provide specific and actionable advice to alleviate his anxiety. For example, it provides specific information regarding risk and return in the form of, "Market segment A is high risk, but has the potential for large returns. Segment B is low risk and is expected to have stable growth."

[0677] In this way, this system, which combines an emotion engine, can provide appropriate advice according to the user's emotional state and support corporate management decisions.

[0678] The processing flow will be explained below.

[0679] Step 1:

[0680] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[0681] Step 2:

[0682] The terminal transmits the input information to the server.

[0683] Step 3:

[0684] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[0685] Step 4:

[0686] The user activates their account by clicking the link in the confirmation email.

[0687] Step 5:

[0688] The server detects the link click and updates the account status to "active."

[0689] Step 6:

[0690] A user enters an email address and password to log in to the system.

[0691] Step 7:

[0692] The terminal sends the input information to the server.

[0693] Step 8:

[0694] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[0695] Step 9:

[0696] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[0697] Step 10:

[0698] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[0699] Step 11:

[0700] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[0701] Step 12:

[0702] The server saves the trained model and makes it available for the next time advice is generated.

[0703] Step 13:

[0704] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[0705] Step 14:

[0706] The terminal transmits the input question to the server.

[0707] Step 15:

[0708] Based on the information received by the server, optimal advice is generated using a generative AI model.

[0709] Step 16:

[0710] The server sends the generated advice to the terminal and displays it to the user.

[0711] Step 17:

[0712] Users make business decisions based on the advice provided.

[0713] Step 18:

[0714] The user inputs feedback about the usefulness of the advice and sends it to the system.

[0715] Step 19:

[0716] The device sends the feedback to the server.

[0717] Step 20:

[0718] The server receives the feedback and adjusts the parameters of the generative AI model.

[0719] Step 21:

[0720] The server stores the feedback information in a database and uses it to provide advice next time.

[0721] Step 22:

[0722] The emotion engine analyzes the user's emotional state from their input and feedback.

[0723] Step 23:

[0724] The server uses the analysis results of the emotion engine to generate advice suited to the user's emotional state.

[0725] Step 24:

[0726] The server uses the emotion engine's analysis results for the next advice and feedback analysis to improve the model.

[0727] Example 2

[0728] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0729] Today's business environment is complex and diverse, requiring managers to make quick and appropriate decisions based on a variety of data and information. However, systems that support business decisions do not take into account the user's emotional state, making it difficult to alleviate the anxiety and stress felt by the user and provide optimal advice. Furthermore, continuous learning and model improvement are necessary to improve the usefulness of generated advice. The purpose of this invention is to solve these problems.

[0730] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0731] In this invention, the server includes means for collecting public information, means for preprocessing the collected public information, means for training a generative AI model using the preprocessed data, means for recognizing a user's emotional state, means for adjusting the generated advice based on the recognized emotional state, and means for receiving feedback from the user and adjusting parameters of the generative AI model. This makes it possible to provide appropriate advice tailored to the user's emotional state and effectively support business decisions.

[0732] "Public information" refers to data or information that is publicly accessible on the Internet, including, for example, news articles, blogs, social media posts, research papers, statements and behavioral data of management, etc.

[0733] "Preprocessing" refers to the process of applying data cleansing, text normalization, filtering, and other processes to collected data to prepare it in a format suitable for analysis.

[0734] A "generative artificial intelligence model" is an AI model trained using machine learning and deep learning techniques that performs inference and generation based on user input.

[0735] "Emotional state" refers to the psychological state or emotion that the user is feeling, and involves analyzing emotions such as anxiety, impatience, and joy.

[0736] "Adjusting advice" means appropriately modifying the generated advice in accordance with the user's emotional state and providing it to the user in an optimal form.

[0737] "Feedback" refers to the user inputting into the system evaluations and opinions about the usefulness of the advice provided and the results of its application.

[0738] "Parameter tuning" refers to readjusting the internal settings and weights of an AI model based on feedback from users to improve the model's performance and accuracy.

[0739] This invention combines a system that uses a generative AI model to support business decisions with an emotion engine that recognizes user emotions. Below, we will explain in detail the embodiments of the invention.

[0740] Overall structure

[0741] The system mainly consists of a server, a terminal, and a user interface. The server is responsible for data collection, preprocessing, AI model training, emotion recognition, and advice generation, while the terminal is responsible for inputting questions from users and sending and receiving feedback. Users access the system using various devices.

[0742] User Registration and Authentication

[0743] A user accesses the system and enters the required information, such as name, email address, and password, into the new user registration page. The terminal sends the entered information to the server, which verifies the information and then registers the new user information in the database. Once registration is complete, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. Thereafter, the user enters their email address and password to log in to the system. The terminal sends the information to the server, which verifies it against the information in the database and allows the user to log in.

[0744] Data collection and learning

[0745] The server periodically collects publicly available information on the Internet, particularly executive speech and behavioral data. This process utilizes web scraping and API access. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This training is carried out using deep learning frameworks such as TensorFlow and PyTorch.

[0746] Use of emotion engine

[0747] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the input method. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. The recognized emotional state is used as an important factor in the generative AI model to generate optimal advice.

[0748] Providing advice

[0749] When a user inputs a specific question into the system, the device sends that information to the server. The server uses a generative AI model to generate optimal advice. The generated advice is then adjusted to the user's emotional state by an emotion engine. The adjusted advice is then provided to the user via the device. For example, if the user is feeling anxious, specific advice to alleviate that anxiety is provided.

[0750] Feedback and Improvements

[0751] The user enters feedback about the usefulness of the advice provided and the results of its application. This feedback information is sent from the device to the server, which analyzes it. The results of analyzing the feedback data are used to retrain the generative AI model next time, improving the model's performance and accuracy.

[0752] Specific examples

[0753] For example, if a manager seeks advice on launching a new product, he or she logs into the system and enters, "Please give me some advice on launching a new product. I'm currently feeling anxious about the intensifying competition in the online market." The device sends this information to the server, which uses an emotion engine to recognize the manager's emotional state. If anxiety is recognized, the server generates specific advice to alleviate the anxiety, such as, "Market segment A is high risk, but you can expect a big return. Segment B is low risk and is expected to grow steadily." Based on this advice, the manager can make business decisions with confidence.

[0754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] A user accesses the system and enters required information such as name, email address, and password into the new user registration page.

[0757] Input: Username, Email Address, Password

[0758] Output: Complete set of input data

[0759] Specific operation: The user enters information into a form on a web browser and presses the submit button.

[0760] Step 2:

[0761] The terminal transmits the input information to the server.

[0762] Input: All input data (user name, email address, password)

[0763] Output: HTTP request to the server

[0764] Specific behavior: The form data is sent to the server as an HTTP POST request.

[0765] Step 3:

[0766] The server verifies the received information and registers the new user information in the database.

[0767] Input: Submitted user registration information

[0768] Output: Registration results in the database

[0769] Specific operation: The server checks the format of the input data and the strength of the password, and if there are no problems, it saves the information in the database.

[0770] Step 4:

[0771] The server sends a confirmation email to the user's email address.

[0772] Input: User's email address and confirmation email content

[0773] Output:Confirmation email

[0774] What happens: The server will send a confirmation email via the SMTP server, which will contain a link to activate your account.

[0775] Step 5:

[0776] The user activates their account by clicking the link in the confirmation email.

[0777] Input: Link in confirmation email

[0778] Output: Account enabled

[0779] What happens: When a user clicks on the link, the server receives the request and updates the user status in the database to active.

[0780] Step 6:

[0781] The user enters their email address and password, and the device sends that information to the server, which checks it against a database and allows them to log in.

[0782] Input: Email address, password

[0783] Output: Session information for successful login

[0784] Specific operation: The entered information is sent to the server and compared with the user information in the database. If authentication is successful, a session is created.

[0785] Step 7:

[0786] The server periodically collects public information on the Internet.

[0787] Input: Public data sources on the internet

[0788] Output: Collected dataset

[0789] Specific operations: The server periodically performs scraping and API access to collect data on managerial statements and behavior.

[0790] Step 8:

[0791] The server preprocesses the collected data, normalizing the text and filtering out unnecessary information.

[0792] Input: Collected public data

[0793] Output: Preprocessed dataset

[0794] Specific operation: Data is cleansed using an NLP library (e.g., spaCy) and formatted for analysis.

[0795] Step 9:

[0796] The server uses the preprocessed data to train the generative AI model.

[0797] Input: Preprocessed dataset

[0798] Output: The trained AI model

[0799] Specific operation: Train generative AI models using TensorFlow and PyTorch. Use high-performance GPUs to streamline learning.

[0800] Step 10:

[0801] A user uses the system to enter a question and the terminal sends the information to the server.

[0802] Input: Question data from the user

[0803] Output: Submitted question data

[0804] What happens: A user uses a web interface to enter a question and presses the submit button, which sends the data to the server as an HTTP POST request.

[0805] Step 11:

[0806] The server uses an emotion engine to recognize the user's emotional state.

[0807] Input: Submitted question data

[0808] Output: Perceived emotional state

[0809] Specific operation: The server calls an emotion analysis API (e.g., IBM Watson Natural Language Understanding) to perform emotion recognition.

[0810] Step 12:

[0811] The server uses a generative AI model to generate optimal advice, which is then adjusted by an emotion engine.

[0812] Input: User question data, perceived emotional state

[0813] Output: Adjusted advice

[0814] Specific operation: The prompt sentence "Please give me some advice on launching a new product to market" is passed as input to the generative AI model, and the generated text is adjusted using the emotion engine.

[0815] Step 13:

[0816] The terminal displays the received advice to the user.

[0817] Input: Tailored Advice

[0818] Output: Advice displayed to the user

[0819] Specific operation: The received advice content is displayed on the web browser.

[0820] Step 14:

[0821] The user inputs feedback into the system regarding the usefulness of the advice and the results of its application.

[0822] Input: Feedback data

[0823] Output: Input feedback data

[0824] Specific operation: The user uses the web interface to enter ratings and comments and presses the submit button.

[0825] Step 15:

[0826] The terminal sends feedback information to the server.

[0827] Input: Feedback data

[0828] Output: HTTP request to the server

[0829] Specific behavior: The form data is sent to the server as an HTTP POST request.

[0830] Step 16:

[0831] The server analyzes the feedback and uses it as data to improve the generative AI model.

[0832] Input: Submitted feedback data

[0833] Output: AI model calibration data

[0834] What it does: Analyzes the feedback data and uses it to retrain the generative AI model, improving its performance and accuracy.

[0835] (Application example 2)

[0836] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0837] Conventional systems using generative AI provide management decisions and advice without considering the user's emotional state, resulting in a lack of advice that is optimal for the user's psychological state. Furthermore, when dealing with customers in brick-and-mortar stores, there is a lack of means to recognize emotions in real time and provide advice that is in line with the user's needs, making it difficult to improve customer satisfaction.

[0838] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting public information including utterance data and behavioral data, means for preprocessing the collected public information, means for training a generative artificial intelligence model using the preprocessed data, emotion analysis means for recognizing the user's emotional state, means for generating advice optimal for the user's question based on the generative artificial intelligence model, means for providing the generated advice to the user, means for displaying or outputting advice by voice in real time according to the usage environment, and means for receiving feedback from the user and adjusting parameters of the generative artificial intelligence model. This makes it possible to provide optimal advice based on the user's emotional state in real time and improve customer satisfaction.

[0839] "Speech data" refers to information converted from speech into text format.

[0840] "Behavioral data" refers to information that records a user's actions, location, operation history, etc.

[0841] "Public Information" means publicly accessible information that is published on the Internet.

[0842] "Preprocessing" refers to the process of formatting collected data into a form that is easy to analyze.

[0843] A "generative artificial intelligence model" is an AI model that is trained using large amounts of data.

[0844] "Emotion analysis means" refers to technology or equipment for recognizing a user's emotional state from text or voice data.

[0845] "Advice generation means" refers to AI technologies and algorithms that provide optimal advice based on user input and status.

[0846] The "advice providing means" refers to devices such as a display and a speaker for presenting the generated advice to the user.

[0847] "Real-time display means" refers to technology or equipment for displaying advice on the user's condition without delay.

[0848] "Real-time voice output means" refers to technology or equipment for instantly providing generated advice in voice form.

[0849] "Feedback receiving means" refers to the technology and equipment used to collect opinions and reactions from users.

[0850] "Parameter adjustment means" refers to techniques or equipment for improving the performance of an artificial intelligence model based on collected feedback information.

[0851] The present invention provides a system for recognizing a user's emotional state and providing appropriate management decisions and advice based on the recognition. The system is configured using various hardware and software.

[0852] User Registration and Authentication

[0853] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends this information to the server, which then registers the new user information in the database based on the received information. At the same time, a confirmation email is sent to the user's email address. When the user clicks on the link contained in the confirmation email, their account is activated and they can then log in to the system.

[0854] Data collection and learning

[0855] The server periodically collects public information from the Internet (such as speech data and behavioral data). This is done using Python scraping technology and public APIs. The collected data is preprocessed to normalize the text and filter out unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model uses Hugging Face's Transformers library and TensorFlow.

[0856] Use of emotion engine

[0857] When a user uses the system to input a question, the device sends that information to the server. The server's emotion analysis means analyzes the user's emotional state from their text and voice data. Based on the analysis results, the generative AI model generates optimal advice based on the user's emotional state.

[0858] Providing advice

[0859] The generated advice is provided to the user via the device. The display of the smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The advice is displayed or output as audio in real time, allowing the user to respond immediately.

[0860] Feedback and Improvements

[0861] User feedback is sent to the server via the device, which then adjusts the parameters of the generative AI model to improve its accuracy. This process uses a specific algorithm (e.g., backpropagation).

[0862] Specific examples

[0863] For example, if a store staff member receives feedback from a customer saying, "I'd like to learn more about this product, but I have some concerns.":

[0864] Provided prompt: The user is feeling anxious. Please give some advice to ease their anxiety.

[0865] The server uses a generative AI model to generate advice such as, "This product is of high quality and has satisfied many customers in the past. Don't worry."

[0866] In this way, the system can provide optimal advice according to the user's emotional state, increasing customer satisfaction.

[0867] To implement this invention, we use a smartphone or tablet as hardware and Python, TensorFlow, the Hugging Face Transformers library, etc. as software. This system enables real-time emotion analysis and advice provision.

[0868] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0869] Step 1: User Registration and Authentication

[0870] A user accesses the new user registration page and enters the required information, such as name, email address, and password. The terminal sends this information to the server, which registers the received information in a database. At the same time, a confirmation email is sent to the user's email address. The user clicks the link in the confirmation email to activate their account. When the user then logs in with their email address and password, the terminal sends that information to the server, which collates it with the database information and allows them to log in. The input is the user's registration information, and the output is the sending of a confirmation email and account activation information.

[0871] Step 2: Data collection and preprocessing

[0872] The server periodically collects public information (speech data, behavioral data) from the Internet. Collection methods include scraping technology using Python and public APIs. The server preprocesses the collected data, such as normalizing the text and filtering out unnecessary information, and stores it in a database. The input is public information from the Internet, and the output is the preprocessed data.

[0873] Step 3: Training the generative AI model

[0874] Using the preprocessed data, the server trains a generative AI model using TensorFlow or Hugging Face's Transformers library. This is to optimize the model parameters based on large amounts of data and apply them to business decisions and advice generation. The input is the preprocessed data, and the output is a trained generative AI model.

[0875] Step 4: Sentiment Analysis

[0876] When a user uses the system to input a question, the device sends that information to the server. The server uses an emotion analysis means (emotion engine) to analyze the user's emotional state from text and voice data and provides the results to the generative AI model. The input is the user's question data, and the output is the user's emotional state.

[0877] Step 5: Advice Generation

[0878] The server uses a generative AI model to generate optimal advice based on the emotional state. A prompt such as "The user is feeling anxious. Please give us some advice to alleviate their anxiety" is input into the generative AI model, which then outputs specific advice. The inputs are the emotion analysis results and the prompt, and the output is the generated advice.

[0879] Step 6: Providing advice

[0880] The generated advice is sent from the server to the terminal, which then presents it to the user. The display of a smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The input is the generated advice, and the output is the advice display or audio provided to the user.

[0881] Step 7: Feedback and model adjustment

[0882] The user inputs feedback into the system about the usefulness of the advice that was implemented. The device sends the feedback to the server, which analyzes it and adjusts the parameters of the generative AI model. The input is the user's feedback, and the output is the adjusted generative AI model.

[0883] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0884] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0885] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0886] [Third embodiment]

[0887] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0888] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0889] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0890] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0891] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0892] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0893] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0894] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0895] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0896] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0897] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0898] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0899] This invention relates to a system that uses generative AI to support companies in making important business decisions. The following is a detailed description of the mode for carrying out the invention.

[0900] User Registration and Authentication

[0901] A user first accesses the system and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the device sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email sent to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the device sends that information to the server. The server performs authentication and allows the user to log in.

[0902] Data collection and learning

[0903] The server periodically collects publicly available information from the internet. This information includes speech and behavioral data of prominent business leaders. The collected data is preprocessed by the server, filtering out unnecessary information and converting it into an analyzable format. The server then uses the preprocessed data to train a generative artificial intelligence model. This AI model is trained to mimic business decisions and thought patterns.

[0904] Providing advice

[0905] The user uses the system to input a question related to business decisions. The question includes specific situational and background information. The terminal sends the input question to the server. The server analyzes the input information and generates optimal advice using a trained generative artificial intelligence model. The generated advice is sent to the terminal and provided to the user. The user makes business decisions based on the provided advice.

[0906] Feedback and Improvements

[0907] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then adjusts the parameters of the generative AI model based on this feedback. This improves the quality of advice provided in the future.

[0908] Specific examples

[0909] When CEO A (user) wants advice for an important meeting regarding the market launch of a new product, he logs into the system and enters a question including detailed market analysis data and competitive information. The device sends this information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch a new product?", the AI ​​model will refer to past success stories and market trends to provide advice recommending the most appropriate market segment.

[0910] In this way, by using this system, companies can easily obtain advice from outside experts, thereby improving the quality of important management decisions.

[0911] The processing flow will be explained below.

[0912] Step 1:

[0913] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[0914] Step 2:

[0915] The terminal transmits the input information to the server.

[0916] Step 3:

[0917] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[0918] Step 4:

[0919] The user activates their account by clicking the link in the confirmation email.

[0920] Step 5:

[0921] The server detects the link click and updates the account status to "active."

[0922] Step 6:

[0923] A user enters an email address and password to log in to the system.

[0924] Step 7:

[0925] The terminal sends the input information to the server.

[0926] Step 8:

[0927] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[0928] Step 9:

[0929] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[0930] Step 10:

[0931] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[0932] Step 11:

[0933] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[0934] Step 12:

[0935] The server saves the trained model and makes it available for the next time advice is generated.

[0936] Step 13:

[0937] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[0938] Step 14:

[0939] The terminal transmits the input question to the server.

[0940] Step 15:

[0941] Based on the information received by the server, optimal advice is generated using a generative AI model.

[0942] Step 16:

[0943] The server sends the generated advice to the terminal and displays it to the user.

[0944] Step 17:

[0945] Users make business decisions based on the advice provided.

[0946] Step 18:

[0947] The user inputs feedback about the usefulness of the advice and sends it to the system.

[0948] Step 19:

[0949] The device sends the feedback to the server.

[0950] Step 20:

[0951] The server receives the feedback and adjusts the parameters of the generative AI model.

[0952] Step 21:

[0953] The server stores the feedback information in a database and uses it to provide advice next time.

[0954] Example 1

[0955] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0956] In today's business environment, quick and accurate management decisions are essential for a company's success. However, many companies lack sufficient resources to identify important data from vast amounts of information and make appropriate decisions. Small and medium-sized enterprises, in particular, face the challenge of finding advice from outside experts. Therefore, there is a need for a system that allows companies to easily obtain high-quality management advice and make quick decisions.

[0957] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0958] In this invention, the server includes: means for user registration and authentication in which a user inputs information such as a name, email address, and password and sends it from the terminal to the server; means for the server to periodically collect public information on the Internet; means for the server to preprocess the collected public information to remove unnecessary information and convert it into an analyzable format; means for the server to train a generative artificial intelligence model using the preprocessed data; means for a user to input a question to the system and send it from the terminal to the server; means for the server to analyze the content of the user's question and generate optimal advice using the trained generative artificial intelligence model; means for the server to send the generated advice to the terminal and provide it to the user; means for the user to input feedback on the effectiveness or application results of the advice and send it from the terminal to the server; and means for the server to adjust parameters of the generative artificial intelligence model based on the feedback received. This enables companies to obtain quick, high-quality management advice and improve the quality of management decisions.

[0959] "User registration and authentication" refers to the process in which a user enters information such as name, email address, and password to access the system and sends it from their terminal to the server, including verification of user information and account activation.

[0960] "Public information collection" refers to the collection of data that is regularly accessible on the Internet by a server (e.g., speech data and behavioral data of prominent business executives).

[0961] "Data preprocessing" is a means to refer to the process by which the server filters the collected data, removes unnecessary information, and converts it into an analyzable format.

[0962] A "generative artificial intelligence model" is an artificial intelligence model trained by a machine learning framework using pre-processed data, and is a means used to mimic business decisions.

[0963] "Question input" refers to a process in which a user inputs a specific question about business decisions into the system and transmits it from the terminal to the server.

[0964] "Advice generation" is the process in which the server analyzes the question entered by the user and generates optimal advice using a trained artificial intelligence model.

[0965] "Providing advice" is a means to refer to the process in which the server sends the advice generated by the server to the terminal and displays it to the user.

[0966] "Feedback input" refers to a process in which a user inputs into the system an evaluation of the effectiveness of the advice provided and the results of its application, and transmits the input from the terminal to the server.

[0967] "Model parameter adjustment" refers to a process or means by which the server adjusts the parameters of the generative artificial intelligence model based on feedback received from the user to improve the accuracy of the model.

[0968] A "scraping tool" refers to a software tool used to automatically retrieve data from websites on the Internet.

[0969] "Real-time advice" refers to a process in which, upon receiving a question from a user, the server quickly generates specific advice using an artificial intelligence model and provides it immediately.

[0970] The present invention relates to a system that uses generative artificial intelligence (AI) models to help companies make important business decisions. The following describes in detail the embodiments of the invention.

[0971] User Registration and Authentication

[0972] A user first accesses the system and registers as a new user. The user enters the required information on the registration page, such as name, email address, and password. The terminal then sends this information to the server. The server verifies the received information, converts it into the required format, and saves the new user information in a database. The server also sends a confirmation email to the user, and the user clicks on a link to activate the account. After that, when the user logs into the system, they enter their email address and password, and the terminal sends the information to the server. The server authenticates and allows them to log in. The software used includes a database management system (e.g., MySQL) and an email sending system (e.g., SendGrid).

[0973] Data collection and learning

[0974] The server periodically collects publicly available information on the Internet using a scraping tool (e.g., Beautiful Soup). This public information includes speech data and behavioral data of prominent business leaders. The server receives the collected data, filters it to remove unnecessary information, and converts it into an analyzable format (e.g., text normalization, JSON format). The server then uses the preprocessed data to train a generative artificial intelligence model using a machine learning framework (e.g., TensorFlow). The trained AI model is saved to mimic business decisions and thought patterns.

[0975] Providing advice

[0976] The user inputs a question related to business decisions into the system. The question includes specific situational and background information. The device sends the input question to the server. The server analyzes the question and generates optimal advice using a trained generative AI model. The generated advice is sent to the device and provided to the user. The user makes business decisions based on the advice provided. The software used includes data analysis software (e.g., Python library).

[0977] As a concrete example, if CEO A (user) wants advice for an important meeting regarding the launch of a new product, he logs into the system and inputs a question including detailed market analysis data and competitive information. The terminal sends the information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch our new product?", the AI ​​model will provide advice recommending the optimal market segment by referring to past success stories and market trends. An example of a prompt for this process is, "Please tell me the optimal market segment for launching a new product. We will provide current market analysis data and competitive information."

[0978] Feedback and Improvements

[0979] Users input feedback into the system regarding the effectiveness of the advice provided and the results of its application. The feedback includes evaluation items related to the advice's specificity, usefulness, and feasibility. The device sends the feedback to the server, which then adjusts the parameters of the generative AI model based on the received feedback. This improves the quality of advice provided in the future. The system continuously learns and improves through this feedback loop, providing more accurate management advice.

[0980] In this way, by using this system, companies can easily obtain high-quality advice for making quick and accurate management decisions. Furthermore, the system can be further improved through user feedback, allowing for continuous improvement in the quality of corporate management decisions.

[0981] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0982] Step 1: User Registration

[0983] 1.1 A user accesses the new user registration page and enters information such as name, email address, and password (input: name, email address, password).

[0984] 1.2 The terminal sends the entered information to the server (output: user information).

[0985] 1.3 The server validates the received information, converts it into a format, and saves it in the database (processing: input data format validation and conversion, output: database storage).

[0986] 1.4 The server sends a confirmation email to the user (Output:Confirmation email).

[0987] 1.5 User activates account by clicking link in confirmation email (Input: link in confirmation email, Output: account activated).

[0988] Step 2: Login authentication

[0989] 2.1 The user accesses the login page and enters their email address and password (input: email address, password).

[0990] 2.2 The terminal sends the entered information to the server (output: login information).

[0991] 2.3 The server compares the received information with the database and performs authentication (process: database comparison, output: authentication result).

[0992] 2.4 If authentication is successful, the server allows the user to log in (output: session ID).

[0993] Step 3: Data collection

[0994] 3.1 The server runs a job to periodically collect public information on the Internet (output: collection schedule).

[0995] 3.2 The server collects public information using a scraping tool (input: URL list, output: collected data).

[0996] 3.3 The server temporarily stores the collected data (output: raw data).

[0997] Step 4: Data Preprocessing

[0998] 4.1 The server receives the collected data (input: raw data).

[0999] 4.2 The server filters the data and removes unnecessary information (Process: Data Cleansing, Output: Cleansed Data).

[1000] 4.3 The server converts the data into a parseable format (Process: Data normalization, Output: Preprocessed data).

[1001] Step 5: Training the AI ​​model

[1002] 5.1 The server provides the preprocessed data to the machine learning framework (input: preprocessed data).

[1003] 5.2 The server uses the data to train the AI ​​model (processing: machine learning, output: trained AI model).

[1004] 5.3 The server saves the trained AI model (output: saved AI model).

[1005] Step 6: Enter your question

[1006] 6.1 The user inputs a question about business decisions into the system (input: question content).

[1007] 6.2 The device sends the question to the server (output: question data).

[1008] Step 7: Generating Advice

[1009] 7.1 The server receives the query (input: query data).

[1010] 7.2 The server analyzes the question content and inputs it into the trained AI model (processing: question analysis, input: trained AI model, output: analyzed question data).

[1011] 7.3 The server generates optimal advice using the AI ​​model (Process: Advice generation, Output: Generated advice).

[1012] 7.4 The server sends the generated advice to the terminal (Output: Advice sent).

[1013] Step 8: Providing advice

[1014] 8.1 The terminal receives the advice sent from the server (input: advice sent).

[1015] 8.2 The terminal displays the advice on the user interface (Process: Display UI, Output: Displayed advice).

[1016] Step 9: Provide feedback

[1017] 9.1 The user inputs feedback on the effectiveness and application results of the provided advice (input: feedback content).

[1018] 9.2 The device sends feedback to the server (output: feedback data).

[1019] Step 10: Adjust the model parameters

[1020] 10.1 The server receives and parses the feedback (input: feedback data).

[1021] 10.2 The server adjusts the parameters of the AI ​​model based on the feedback (processing: parameter adjustment, output: adjusted parameters).

[1022] 10.3 The server retrains the AI ​​model using the adjusted parameters (Process: Retrain, Output: Improved AI model).

[1023] In this way, by linking users, devices, and servers, this system realizes a series of processes from user registration to learning the AI ​​model, providing advice, and improving the model through feedback.

[1024] (Application example 1)

[1025] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1026] Inventory management and work efficiency are key issues for modern logistics centers. With conventional systems, real-time data collection and analysis takes time, making it difficult to make effective management decisions. Furthermore, there are insufficient methods for efficiently reflecting the quality of advice provided and feedback on application results. For this reason, there is a demand for a system that supports fast and accurate management decisions in the operation of logistics centers.

[1027] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1028] In this invention, the server includes: means for collecting public information including speech data and behavioral data; means for preprocessing the collected public information; means for training a generative AI model using the preprocessed data; means for generating optimal advice using the generative AI model in response to a question input by a user; means for providing the generated advice to the user; means for receiving feedback from the user and adjusting parameters of the generative AI model; means for collecting real-time data via sensors and cameras in the logistics center; means for preprocessing the collected real-time data and analyzing it as business-related data; means for inputting the analyzed business data into the generative AI model and generating optimal logistics management advice in response to the user's question; means for instantly providing the generated logistics management advice to the user; and means for collecting user feedback on the logistics management advice and improving the generative AI model. This enables quick and accurate management decisions in the operation of a logistics center.

[1029] "Speech data" refers to human speech expressed in audio or text format.

[1030] "Behavioral data" refers to information about the specific actions and activities of humans and machines.

[1031] "Public information" refers to information that is publicly available via the Internet or other media.

[1032] "Preprocessing" refers to the process of removing unnecessary parts from raw data and converting it into an analyzable format.

[1033] A "generative artificial intelligence model" refers to an artificial intelligence model that can learn specific patterns or rules from input data and generate corresponding outputs based on new data.

[1034] "Real-time data" refers to the latest dynamic information collected from a system or environment.

[1035] A "logistics center" refers to a facility that stores, manages, and delivers goods and materials.

[1036] A "sensor" refers to a device that detects the surrounding physical conditions and environment and outputs the data.

[1037] "Camera" refers to a device that captures still images and video.

[1038] "Business data" refers to information related to business operations, such as inventory within the logistics center, workers, and truck operation status.

[1039] "Feedback" refers to the user's evaluation and opinion on the system output, and is used to improve the system's performance based on this.

[1040] This invention relates to a system that uses generative AI to support management decisions, primarily in logistics centers. A specific embodiment of this system is described below.

[1041] User Registration and Authentication

[1042] First, a user accesses the system using a terminal and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the terminal sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server performs authentication and allows them to log in.

[1043] Data collection and learning

[1044] The server collects real-time data from sensors and cameras installed within the distribution center. Collected data includes inventory levels, worker numbers, truck arrival status, and more. The server preprocesses the collected data and filters out unnecessary information. The preprocessed data is then used to train a generative artificial intelligence model. The trained AI model is designed to support optimal decisions regarding the operation of the distribution center.

[1045] Providing advice

[1046] Users log in to the system using a terminal and input questions related to specific business decisions. The questions include detailed business data and background information. The terminal then sends the input questions to the server. The server analyzes the input information and generates optimal advice using a trained generative AI model. The generated advice is then sent to the terminal and provided to the user. The user can then refer to the provided advice and make appropriate business decisions immediately.

[1047] Feedback and Improvements

[1048] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then uses this feedback to adjust the parameters of the generative AI model. This improves the quality of advice provided in the future.

[1049] Specific examples

[1050] For example, if a logistics center manager wants advice on how to improve inventory management, he or she can log in to the system and enter a specific question. The question includes data such as current inventory levels, number of workers, and truck arrival status. The device sends this information to a server, which uses an AI model to suggest optimal inventory management methods based on the latest logistics trends and past success stories. The manager can then immediately improve inventory management based on the advice provided.

[1051] An example of a prompt is, "Please tell us how the current inventory management system could be improved. The data collected is inventory levels, number of workers, and number of arriving trucks."

[1052] The above is a specific embodiment for carrying out the present invention. By using this system, it is expected that management decisions at logistics centers will be made more quickly and with greater accuracy.

[1053] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1054] Step 1:

[1055] User Registration and Authentication

[1056] Specific operation: A user accesses the system using a terminal and registers as a new user. The user enters information such as their name, email address, and password. The entered information is sent from the terminal to the server. The server verifies the received information and registers the new user information in the database. A confirmation email is then sent to the user. The user clicks the link in the email to activate their account, completing the registration. When the user subsequently logs in to the system, they enter their email address and password, and the terminal sends this information to the server. The server performs authentication and allows the user to log in.

[1057] Input: User input information (name, email address, password)

[1058] Output: New user registration completed and account activated

[1059] Step 2:

[1060] Data collection

[1061] How it works: The server collects real-time data from sensors and cameras installed in the distribution center, continuously collecting data on inventory levels, number of workers, truck arrival status, and more.

[1062] Input: Real-time data from sensors and cameras

[1063] Output: raw data collected

[1064] Step 3:

[1065] Data Preprocessing

[1066] Specific operation: The server preprocesses the collected raw data, filters out unnecessary information, removes noise from the data, and converts it into an analyzable format.

[1067] Input: raw data

[1068] Output: Preprocessed data

[1069] Step 4:

[1070] Training generative AI models

[1071] How it works: The server uses the preprocessed data to train a generative AI model, teaching it patterns and rules to support decisions about inventory management and work efficiency.

[1072] Input: Preprocessed data

[1073] Output: A trained generative AI model

[1074] Step 5:

[1075] Enter a question and generate advice

[1076] How it works: The user uses a device to input a question into the system. The question includes detailed business data. The device then sends the question to the server. The server analyzes the input question and uses a generative AI model to generate optimal advice.

[1077] Input: User question data

[1078] Output: The generated advice

[1079] Step 6:

[1080] Providing advice

[1081] Specific operation: The generated advice is sent to the terminal and displayed to the user, who then uses the advice to make quick business decisions.

[1082] Input: Generated advice

[1083] Output: Advice given to the user

[1084] Step 7:

[1085] Gathering feedback and improving the model

[1086] How it works: The user inputs feedback about the advice provided to the system from their device. The server receives the feedback and adjusts the parameters of the generative AI model based on that feedback, improving the accuracy of future advice.

[1087] Input: User feedback

[1088] Output: An improved generative AI model

[1089] Specific examples

[1090] For example, if a manager asks how to improve inventory management, the prompt might look something like this:

[1091] "How can we improve our current inventory management system? The data collected is about inventory levels, number of workers, and number of arriving trucks."

[1092] The above are the specific processing steps for carrying out the invention. This system enables quick and accurate management decisions at a logistics center.

[1093] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1094] This invention combines a system that uses generative AI to support business decisions with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the invention.

[1095] User Registration and Authentication

[1096] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends the entered information to the server, which verifies the received information and then registers the new user information in the database. At the same time, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server compares the information with the database and allows them to log in.

[1097] Data collection and learning

[1098] The server periodically collects publicly available information from the internet. This public information includes speech data and behavioral data of prominent business leaders. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model is trained to mimic business decisions and thought patterns.

[1099] Use of emotion engine

[1100] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the way it is input. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. Based on this, the generative AI model generates advice that best suits the user's emotional state. For example, if the user is feeling impatient or anxious, the system can provide advice on an approach that will alleviate that feeling.

[1101] Providing advice

[1102] When a user inputs a specific question, the device sends that information to the server, which then uses a generative AI model to generate optimal advice. The generated advice is adjusted to match the user's emotional state by an emotion engine and sent to the device. The device displays the advice to the user, allowing the user to make business decisions based on useful advice.

[1103] Feedback and Improvements

[1104] Users provide feedback to the system regarding the usefulness of the advice and the results of its application. This feedback also passes through the emotion engine, and the analysis results are used to adjust the parameters of the generative AI model. The device then sends the feedback to the server, which analyzes it and uses it as data to improve the AI ​​model. This can improve the accuracy of future advice and user satisfaction.

[1105] Specific examples

[1106] When CEO A (user) seeks advice for an important meeting regarding the market launch of a new product, he logs into the system and enters his question along with detailed market analysis data. The device sends this information to the server, which uses an emotion engine to recognize CEO A's emotional state. For example, if it recognizes that CEO A is feeling anxious, the server uses a generative AI model to provide specific and actionable advice to alleviate his anxiety. For example, it provides specific information regarding risk and return in the form of, "Market segment A is high risk, but has the potential for large returns. Segment B is low risk and is expected to have stable growth."

[1107] In this way, this system, which combines an emotion engine, can provide appropriate advice according to the user's emotional state and support corporate management decisions.

[1108] The processing flow will be explained below.

[1109] Step 1:

[1110] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[1111] Step 2:

[1112] The terminal transmits the input information to the server.

[1113] Step 3:

[1114] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[1115] Step 4:

[1116] The user activates their account by clicking the link in the confirmation email.

[1117] Step 5:

[1118] The server detects the link click and updates the account status to "active."

[1119] Step 6:

[1120] A user enters an email address and password to log in to the system.

[1121] Step 7:

[1122] The terminal sends the input information to the server.

[1123] Step 8:

[1124] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[1125] Step 9:

[1126] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[1127] Step 10:

[1128] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[1129] Step 11:

[1130] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[1131] Step 12:

[1132] The server saves the trained model and makes it available for the next time advice is generated.

[1133] Step 13:

[1134] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[1135] Step 14:

[1136] The terminal transmits the input question to the server.

[1137] Step 15:

[1138] Based on the information received by the server, optimal advice is generated using a generative AI model.

[1139] Step 16:

[1140] The server sends the generated advice to the terminal and displays it to the user.

[1141] Step 17:

[1142] Users make business decisions based on the advice provided.

[1143] Step 18:

[1144] The user inputs feedback about the usefulness of the advice and sends it to the system.

[1145] Step 19:

[1146] The device sends the feedback to the server.

[1147] Step 20:

[1148] The server receives the feedback and adjusts the parameters of the generative AI model.

[1149] Step 21:

[1150] The server stores the feedback information in a database and uses it to provide advice next time.

[1151] Step 22:

[1152] The emotion engine analyzes the user's emotional state from their input and feedback.

[1153] Step 23:

[1154] The server uses the analysis results of the emotion engine to generate advice suited to the user's emotional state.

[1155] Step 24:

[1156] The server uses the emotion engine's analysis results for the next advice and feedback analysis to improve the model.

[1157] Example 2

[1158] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1159] Today's business environment is complex and diverse, requiring managers to make quick and appropriate decisions based on a variety of data and information. However, systems that support business decisions do not take into account the user's emotional state, making it difficult to alleviate the anxiety and stress felt by the user and provide optimal advice. Furthermore, continuous learning and model improvement are necessary to improve the usefulness of generated advice. The purpose of this invention is to solve these problems.

[1160] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1161] In this invention, the server includes means for collecting public information, means for preprocessing the collected public information, means for training a generative AI model using the preprocessed data, means for recognizing a user's emotional state, means for adjusting the generated advice based on the recognized emotional state, and means for receiving feedback from the user and adjusting parameters of the generative AI model. This makes it possible to provide appropriate advice tailored to the user's emotional state and effectively support business decisions.

[1162] "Public information" refers to data or information that is publicly accessible on the Internet, including, for example, news articles, blogs, social media posts, research papers, statements and behavioral data of management, etc.

[1163] "Preprocessing" refers to the process of applying data cleansing, text normalization, filtering, and other processes to collected data to prepare it in a format suitable for analysis.

[1164] A "generative artificial intelligence model" is an AI model trained using machine learning and deep learning techniques that performs inference and generation based on user input.

[1165] "Emotional state" refers to the psychological state or emotion that the user is feeling, and involves analyzing emotions such as anxiety, impatience, and joy.

[1166] "Adjusting advice" means appropriately modifying the generated advice in accordance with the user's emotional state and providing it to the user in an optimal form.

[1167] "Feedback" refers to the user inputting into the system evaluations and opinions about the usefulness of the advice provided and the results of its application.

[1168] "Parameter tuning" refers to readjusting the internal settings and weights of an AI model based on feedback from users to improve the model's performance and accuracy.

[1169] This invention combines a system that uses a generative AI model to support business decisions with an emotion engine that recognizes user emotions. Below, we will explain in detail the embodiments of the invention.

[1170] Overall structure

[1171] The system mainly consists of a server, a terminal, and a user interface. The server is responsible for data collection, preprocessing, AI model training, emotion recognition, and advice generation, while the terminal is responsible for inputting questions from users and sending and receiving feedback. Users access the system using various devices.

[1172] User Registration and Authentication

[1173] A user accesses the system and enters the required information, such as name, email address, and password, into the new user registration page. The terminal sends the entered information to the server, which verifies the information and then registers the new user information in the database. Once registration is complete, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. Thereafter, the user enters their email address and password to log in to the system. The terminal sends the information to the server, which verifies it against the information in the database and allows the user to log in.

[1174] Data collection and learning

[1175] The server periodically collects publicly available information on the Internet, particularly executive speech and behavioral data. This process utilizes web scraping and API access. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This training is carried out using deep learning frameworks such as TensorFlow and PyTorch.

[1176] Use of emotion engine

[1177] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the input method. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. The recognized emotional state is used as an important factor in the generative AI model to generate optimal advice.

[1178] Providing advice

[1179] When a user inputs a specific question into the system, the device sends that information to the server. The server uses a generative AI model to generate optimal advice. The generated advice is then adjusted to the user's emotional state by an emotion engine. The adjusted advice is then provided to the user via the device. For example, if the user is feeling anxious, specific advice to alleviate that anxiety is provided.

[1180] Feedback and Improvements

[1181] The user enters feedback about the usefulness of the advice provided and the results of its application. This feedback information is sent from the device to the server, which analyzes it. The results of analyzing the feedback data are used to retrain the generative AI model next time, improving the model's performance and accuracy.

[1182] Specific examples

[1183] For example, if a manager seeks advice on launching a new product, he or she logs into the system and enters, "Please give me some advice on launching a new product. I'm currently feeling anxious about the intensifying competition in the online market." The device sends this information to the server, which uses an emotion engine to recognize the manager's emotional state. If anxiety is recognized, the server generates specific advice to alleviate the anxiety, such as, "Market segment A is high risk, but you can expect a big return. Segment B is low risk and is expected to grow steadily." Based on this advice, the manager can make business decisions with confidence.

[1184] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1185] Step 1:

[1186] A user accesses the system and enters required information such as name, email address, and password into the new user registration page.

[1187] Input: Username, Email Address, Password

[1188] Output: Complete set of input data

[1189] Specific operation: The user enters information into a form on a web browser and presses the submit button.

[1190] Step 2:

[1191] The terminal transmits the input information to the server.

[1192] Input: All input data (user name, email address, password)

[1193] Output: HTTP request to the server

[1194] Specific behavior: The form data is sent to the server as an HTTP POST request.

[1195] Step 3:

[1196] The server verifies the received information and registers the new user information in the database.

[1197] Input: Submitted user registration information

[1198] Output: Registration results in the database

[1199] Specific operation: The server checks the format of the input data and the strength of the password, and if there are no problems, it saves the information in the database.

[1200] Step 4:

[1201] The server sends a confirmation email to the user's email address.

[1202] Input: User's email address and confirmation email content

[1203] Output:Confirmation email

[1204] What happens: The server will send a confirmation email via the SMTP server, which will contain a link to activate your account.

[1205] Step 5:

[1206] The user activates their account by clicking the link in the confirmation email.

[1207] Input: Link in confirmation email

[1208] Output: Account enabled

[1209] What happens: When a user clicks on the link, the server receives the request and updates the user status in the database to active.

[1210] Step 6:

[1211] The user enters their email address and password, and the device sends that information to the server, which checks it against a database and allows them to log in.

[1212] Input: Email address, password

[1213] Output: Session information for successful login

[1214] Specific operation: The entered information is sent to the server and compared with the user information in the database. If authentication is successful, a session is created.

[1215] Step 7:

[1216] The server periodically collects public information on the Internet.

[1217] Input: Public data sources on the internet

[1218] Output: Collected dataset

[1219] Specific operations: The server periodically performs scraping and API access to collect data on managerial statements and behavior.

[1220] Step 8:

[1221] The server preprocesses the collected data, normalizing the text and filtering out unnecessary information.

[1222] Input: Collected public data

[1223] Output: Preprocessed dataset

[1224] Specific operation: Data is cleansed using an NLP library (e.g., spaCy) and formatted for analysis.

[1225] Step 9:

[1226] The server uses the preprocessed data to train the generative AI model.

[1227] Input: Preprocessed dataset

[1228] Output: The trained AI model

[1229] Specific operation: Train generative AI models using TensorFlow and PyTorch. Use high-performance GPUs to streamline learning.

[1230] Step 10:

[1231] A user uses the system to enter a question and the terminal sends the information to the server.

[1232] Input: Question data from the user

[1233] Output: Submitted question data

[1234] What happens: A user uses a web interface to enter a question and presses the submit button, which sends the data to the server as an HTTP POST request.

[1235] Step 11:

[1236] The server uses an emotion engine to recognize the user's emotional state.

[1237] Input: Submitted question data

[1238] Output: Perceived emotional state

[1239] Specific operation: The server calls an emotion analysis API (e.g., IBM Watson Natural Language Understanding) to perform emotion recognition.

[1240] Step 12:

[1241] The server uses a generative AI model to generate optimal advice, which is then adjusted by an emotion engine.

[1242] Input: User question data, perceived emotional state

[1243] Output: Adjusted advice

[1244] Specific operation: The prompt sentence "Please give me some advice on launching a new product to market" is passed as input to the generative AI model, and the generated text is adjusted using the emotion engine.

[1245] Step 13:

[1246] The terminal displays the received advice to the user.

[1247] Input: Tailored Advice

[1248] Output: Advice displayed to the user

[1249] Specific operation: The received advice content is displayed on the web browser.

[1250] Step 14:

[1251] The user inputs feedback into the system regarding the usefulness of the advice and the results of its application.

[1252] Input: Feedback data

[1253] Output: Input feedback data

[1254] Specific operation: The user uses the web interface to enter ratings and comments and presses the submit button.

[1255] Step 15:

[1256] The terminal sends feedback information to the server.

[1257] Input: Feedback data

[1258] Output: HTTP request to the server

[1259] Specific behavior: The form data is sent to the server as an HTTP POST request.

[1260] Step 16:

[1261] The server analyzes the feedback and uses it as data to improve the generative AI model.

[1262] Input: Submitted feedback data

[1263] Output: AI model calibration data

[1264] What it does: Analyzes the feedback data and uses it to retrain the generative AI model, improving its performance and accuracy.

[1265] (Application example 2)

[1266] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1267] Conventional systems using generative AI provide management decisions and advice without considering the user's emotional state, resulting in a lack of advice that is optimal for the user's psychological state. Furthermore, when dealing with customers in brick-and-mortar stores, there is a lack of means to recognize emotions in real time and provide advice that is in line with the user's needs, making it difficult to improve customer satisfaction.

[1268] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting public information including utterance data and behavioral data, means for preprocessing the collected public information, means for training a generative artificial intelligence model using the preprocessed data, emotion analysis means for recognizing the user's emotional state, means for generating advice optimal for the user's question based on the generative artificial intelligence model, means for providing the generated advice to the user, means for displaying or outputting advice by voice in real time according to the usage environment, and means for receiving feedback from the user and adjusting parameters of the generative artificial intelligence model. This makes it possible to provide optimal advice based on the user's emotional state in real time and improve customer satisfaction.

[1269] "Speech data" refers to information converted from speech into text format.

[1270] "Behavioral data" refers to information that records a user's actions, location, operation history, etc.

[1271] "Public Information" means publicly accessible information that is published on the Internet.

[1272] "Preprocessing" refers to the process of formatting collected data into a form that is easy to analyze.

[1273] A "generative artificial intelligence model" is an AI model that is trained using large amounts of data.

[1274] "Emotion analysis means" refers to technology or equipment for recognizing a user's emotional state from text or voice data.

[1275] "Advice generation means" refers to AI technologies and algorithms that provide optimal advice based on user input and status.

[1276] The "advice providing means" refers to devices such as a display and a speaker for presenting the generated advice to the user.

[1277] "Real-time display means" refers to technology or equipment for displaying advice on the user's condition without delay.

[1278] "Real-time voice output means" refers to technology or equipment for instantly providing generated advice in voice form.

[1279] "Feedback receiving means" refers to the technology and equipment used to collect opinions and reactions from users.

[1280] "Parameter adjustment means" refers to techniques or equipment for improving the performance of an artificial intelligence model based on collected feedback information.

[1281] The present invention provides a system for recognizing a user's emotional state and providing appropriate management decisions and advice based on the recognition. The system is configured using various hardware and software.

[1282] User Registration and Authentication

[1283] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends this information to the server, which then registers the new user information in the database based on the received information. At the same time, a confirmation email is sent to the user's email address. When the user clicks on the link contained in the confirmation email, their account is activated and they can then log in to the system.

[1284] Data collection and learning

[1285] The server periodically collects public information from the Internet (such as speech data and behavioral data). This is done using Python scraping technology and public APIs. The collected data is preprocessed to normalize the text and filter out unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model uses Hugging Face's Transformers library and TensorFlow.

[1286] Use of emotion engine

[1287] When a user uses the system to input a question, the device sends that information to the server. The server's emotion analysis means analyzes the user's emotional state from their text and voice data. Based on the analysis results, the generative AI model generates optimal advice based on the user's emotional state.

[1288] Providing advice

[1289] The generated advice is provided to the user via the device. The display of the smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The advice is displayed or output as audio in real time, allowing the user to respond immediately.

[1290] Feedback and Improvements

[1291] User feedback is sent to the server via the device, which then adjusts the parameters of the generative AI model to improve its accuracy. This process uses a specific algorithm (e.g., backpropagation).

[1292] Specific examples

[1293] For example, if a store staff member receives feedback from a customer saying, "I'd like to learn more about this product, but I have some concerns.":

[1294] Provided prompt: The user is feeling anxious. Please give some advice to ease their anxiety.

[1295] The server uses a generative AI model to generate advice such as, "This product is of high quality and has satisfied many customers in the past. Don't worry."

[1296] In this way, the system can provide optimal advice according to the user's emotional state, increasing customer satisfaction.

[1297] To implement this invention, we use a smartphone or tablet as hardware and Python, TensorFlow, the Hugging Face Transformers library, etc. as software. This system enables real-time emotion analysis and advice provision.

[1298] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1299] Step 1: User Registration and Authentication

[1300] A user accesses the new user registration page and enters the required information, such as name, email address, and password. The terminal sends this information to the server, which registers the received information in a database. At the same time, a confirmation email is sent to the user's email address. The user clicks the link in the confirmation email to activate their account. When the user then logs in with their email address and password, the terminal sends that information to the server, which collates it with the database information and allows them to log in. The input is the user's registration information, and the output is the sending of a confirmation email and account activation information.

[1301] Step 2: Data collection and preprocessing

[1302] The server periodically collects public information (speech data, behavioral data) from the Internet. Collection methods include scraping technology using Python and public APIs. The server preprocesses the collected data, such as normalizing the text and filtering out unnecessary information, and stores it in a database. The input is public information from the Internet, and the output is the preprocessed data.

[1303] Step 3: Training the generative AI model

[1304] Using the preprocessed data, the server trains a generative AI model using TensorFlow or Hugging Face's Transformers library. This is to optimize the model parameters based on large amounts of data and apply them to business decisions and advice generation. The input is the preprocessed data, and the output is a trained generative AI model.

[1305] Step 4: Sentiment Analysis

[1306] When a user uses the system to input a question, the device sends that information to the server. The server uses an emotion analysis means (emotion engine) to analyze the user's emotional state from text and voice data and provides the results to the generative AI model. The input is the user's question data, and the output is the user's emotional state.

[1307] Step 5: Advice Generation

[1308] The server uses a generative AI model to generate optimal advice based on the emotional state. A prompt such as "The user is feeling anxious. Please give us some advice to alleviate their anxiety" is input into the generative AI model, which then outputs specific advice. The inputs are the emotion analysis results and the prompt, and the output is the generated advice.

[1309] Step 6: Providing advice

[1310] The generated advice is sent from the server to the terminal, which then presents it to the user. The display of a smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The input is the generated advice, and the output is the advice display or audio provided to the user.

[1311] Step 7: Feedback and model adjustment

[1312] The user inputs feedback into the system about the usefulness of the advice that was implemented. The device sends the feedback to the server, which analyzes it and adjusts the parameters of the generative AI model. The input is the user's feedback, and the output is the adjusted generative AI model.

[1313] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1314] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1315] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1316] [Fourth embodiment]

[1317] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1318] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1319] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1320] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1321] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1322] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1323] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1324] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1325] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1326] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1327] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1328] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1329] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1330] This invention relates to a system that uses generative AI to support companies in making important business decisions. The following is a detailed description of the mode for carrying out the invention.

[1331] User Registration and Authentication

[1332] A user first accesses the system and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the device sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email sent to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the device sends that information to the server. The server performs authentication and allows the user to log in.

[1333] Data collection and learning

[1334] The server periodically collects publicly available information from the internet. This information includes speech and behavioral data of prominent business leaders. The collected data is preprocessed by the server, filtering out unnecessary information and converting it into an analyzable format. The server then uses the preprocessed data to train a generative artificial intelligence model. This AI model is trained to mimic business decisions and thought patterns.

[1335] Providing advice

[1336] The user uses the system to input a question related to business decisions. The question includes specific situational and background information. The terminal sends the input question to the server. The server analyzes the input information and generates optimal advice using a trained generative artificial intelligence model. The generated advice is sent to the terminal and provided to the user. The user makes business decisions based on the provided advice.

[1337] Feedback and Improvements

[1338] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then adjusts the parameters of the generative AI model based on this feedback. This improves the quality of advice provided in the future.

[1339] Specific examples

[1340] When CEO A (user) wants advice for an important meeting regarding the market launch of a new product, he logs into the system and enters a question including detailed market analysis data and competitive information. The device sends this information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch a new product?", the AI ​​model will refer to past success stories and market trends to provide advice recommending the most appropriate market segment.

[1341] In this way, by using this system, companies can easily obtain advice from outside experts, thereby improving the quality of important management decisions.

[1342] The processing flow will be explained below.

[1343] Step 1:

[1344] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[1345] Step 2:

[1346] The terminal transmits the input information to the server.

[1347] Step 3:

[1348] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[1349] Step 4:

[1350] The user activates their account by clicking the link in the confirmation email.

[1351] Step 5:

[1352] The server detects the link click and updates the account status to "active."

[1353] Step 6:

[1354] A user enters an email address and password to log in to the system.

[1355] Step 7:

[1356] The terminal sends the input information to the server.

[1357] Step 8:

[1358] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[1359] Step 9:

[1360] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[1361] Step 10:

[1362] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[1363] Step 11:

[1364] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[1365] Step 12:

[1366] The server saves the trained model and makes it available for the next time advice is generated.

[1367] Step 13:

[1368] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[1369] Step 14:

[1370] The terminal transmits the input question to the server.

[1371] Step 15:

[1372] Based on the information received by the server, optimal advice is generated using a generative AI model.

[1373] Step 16:

[1374] The server sends the generated advice to the terminal and displays it to the user.

[1375] Step 17:

[1376] Users make business decisions based on the advice provided.

[1377] Step 18:

[1378] The user inputs feedback about the usefulness of the advice and sends it to the system.

[1379] Step 19:

[1380] The device sends the feedback to the server.

[1381] Step 20:

[1382] The server receives the feedback and adjusts the parameters of the generative AI model.

[1383] Step 21:

[1384] The server stores the feedback information in a database and uses it to provide advice next time.

[1385] Example 1

[1386] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1387] In today's business environment, quick and accurate management decisions are essential for a company's success. However, many companies lack sufficient resources to identify important data from vast amounts of information and make appropriate decisions. Small and medium-sized enterprises, in particular, face the challenge of finding advice from outside experts. Therefore, there is a need for a system that allows companies to easily obtain high-quality management advice and make quick decisions.

[1388] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1389] In this invention, the server includes: means for user registration and authentication in which a user inputs information such as a name, email address, and password and sends it from the terminal to the server; means for the server to periodically collect public information on the Internet; means for the server to preprocess the collected public information to remove unnecessary information and convert it into an analyzable format; means for the server to train a generative artificial intelligence model using the preprocessed data; means for a user to input a question to the system and send it from the terminal to the server; means for the server to analyze the content of the user's question and generate optimal advice using the trained generative artificial intelligence model; means for the server to send the generated advice to the terminal and provide it to the user; means for the user to input feedback on the effectiveness or application results of the advice and send it from the terminal to the server; and means for the server to adjust parameters of the generative artificial intelligence model based on the feedback received. This enables companies to obtain quick, high-quality management advice and improve the quality of management decisions.

[1390] "User registration and authentication" refers to the process in which a user enters information such as name, email address, and password to access the system and sends it from their terminal to the server, including verification of user information and account activation.

[1391] "Public information collection" refers to the collection of data that is regularly accessible on the Internet by a server (e.g., speech data and behavioral data of prominent business executives).

[1392] "Data preprocessing" is a means to refer to the process by which the server filters the collected data, removes unnecessary information, and converts it into an analyzable format.

[1393] A "generative artificial intelligence model" is an artificial intelligence model trained by a machine learning framework using pre-processed data, and is a means used to mimic business decisions.

[1394] "Question input" refers to a process in which a user inputs a specific question about business decisions into the system and transmits it from the terminal to the server.

[1395] "Advice generation" is the process in which the server analyzes the question entered by the user and generates optimal advice using a trained artificial intelligence model.

[1396] "Providing advice" is a means to refer to the process in which the server sends the advice generated by the server to the terminal and displays it to the user.

[1397] "Feedback input" refers to a process in which a user inputs into the system an evaluation of the effectiveness of the advice provided and the results of its application, and transmits the input from the terminal to the server.

[1398] "Model parameter adjustment" refers to a process or means by which the server adjusts the parameters of the generative artificial intelligence model based on feedback received from the user to improve the accuracy of the model.

[1399] A "scraping tool" refers to a software tool used to automatically retrieve data from websites on the Internet.

[1400] "Real-time advice" refers to a process in which, upon receiving a question from a user, the server quickly generates specific advice using an artificial intelligence model and provides it immediately.

[1401] The present invention relates to a system that uses generative artificial intelligence (AI) models to help companies make important business decisions. The following describes in detail the embodiments of the invention.

[1402] User Registration and Authentication

[1403] A user first accesses the system and registers as a new user. The user enters the required information on the registration page, such as name, email address, and password. The terminal then sends this information to the server. The server verifies the received information, converts it into the required format, and saves the new user information in a database. The server also sends a confirmation email to the user, and the user clicks on a link to activate the account. After that, when the user logs into the system, they enter their email address and password, and the terminal sends the information to the server. The server authenticates and allows them to log in. The software used includes a database management system (e.g., MySQL) and an email sending system (e.g., SendGrid).

[1404] Data collection and learning

[1405] The server periodically collects publicly available information on the Internet using a scraping tool (e.g., Beautiful Soup). This public information includes speech data and behavioral data of prominent business leaders. The server receives the collected data, filters it to remove unnecessary information, and converts it into an analyzable format (e.g., text normalization, JSON format). The server then uses the preprocessed data to train a generative artificial intelligence model using a machine learning framework (e.g., TensorFlow). The trained AI model is saved to mimic business decisions and thought patterns.

[1406] Providing advice

[1407] The user inputs a question related to business decisions into the system. The question includes specific situational and background information. The device sends the input question to the server. The server analyzes the question and generates optimal advice using a trained generative AI model. The generated advice is sent to the device and provided to the user. The user makes business decisions based on the advice provided. The software used includes data analysis software (e.g., Python library).

[1408] As a concrete example, if CEO A (user) wants advice for an important meeting regarding the launch of a new product, he logs into the system and inputs a question including detailed market analysis data and competitive information. The terminal sends the information to the server, which uses an AI model to generate fast and accurate advice. For example, in response to the question, "In which market segment should we launch our new product?", the AI ​​model will provide advice recommending the optimal market segment by referring to past success stories and market trends. An example of a prompt for this process is, "Please tell me the optimal market segment for launching a new product. We will provide current market analysis data and competitive information."

[1409] Feedback and Improvements

[1410] Users input feedback into the system regarding the effectiveness of the advice provided and the results of its application. The feedback includes evaluation items related to the advice's specificity, usefulness, and feasibility. The device sends the feedback to the server, which then adjusts the parameters of the generative AI model based on the received feedback. This improves the quality of advice provided in the future. The system continuously learns and improves through this feedback loop, providing more accurate management advice.

[1411] In this way, by using this system, companies can easily obtain high-quality advice for making quick and accurate management decisions. Furthermore, the system can be further improved through user feedback, allowing for continuous improvement in the quality of corporate management decisions.

[1412] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1413] Step 1: User Registration

[1414] 1.1 A user accesses the new user registration page and enters information such as name, email address, and password (input: name, email address, password).

[1415] 1.2 The terminal sends the entered information to the server (output: user information).

[1416] 1.3 The server validates the received information, converts it into a format, and saves it in the database (processing: input data format validation and conversion, output: database storage).

[1417] 1.4 The server sends a confirmation email to the user (Output:Confirmation email).

[1418] 1.5 User activates account by clicking link in confirmation email (Input: link in confirmation email, Output: account activated).

[1419] Step 2: Login authentication

[1420] 2.1 The user accesses the login page and enters their email address and password (input: email address, password).

[1421] 2.2 The terminal sends the entered information to the server (output: login information).

[1422] 2.3 The server compares the received information with the database and performs authentication (process: database comparison, output: authentication result).

[1423] 2.4 If authentication is successful, the server allows the user to log in (output: session ID).

[1424] Step 3: Data collection

[1425] 3.1 The server runs a job to periodically collect public information on the Internet (output: collection schedule).

[1426] 3.2 The server collects public information using a scraping tool (input: URL list, output: collected data).

[1427] 3.3 The server temporarily stores the collected data (output: raw data).

[1428] Step 4: Data Preprocessing

[1429] 4.1 The server receives the collected data (input: raw data).

[1430] 4.2 The server filters the data and removes unnecessary information (Process: Data Cleansing, Output: Cleansed Data).

[1431] 4.3 The server converts the data into a parseable format (Process: Data normalization, Output: Preprocessed data).

[1432] Step 5: Training the AI ​​model

[1433] 5.1 The server provides the preprocessed data to the machine learning framework (input: preprocessed data).

[1434] 5.2 The server uses the data to train the AI ​​model (processing: machine learning, output: trained AI model).

[1435] 5.3 The server saves the trained AI model (output: saved AI model).

[1436] Step 6: Enter your question

[1437] 6.1 The user inputs a question about business decisions into the system (input: question content).

[1438] 6.2 The device sends the question to the server (output: question data).

[1439] Step 7: Generating Advice

[1440] 7.1 The server receives the query (input: query data).

[1441] 7.2 The server analyzes the question content and inputs it into the trained AI model (processing: question analysis, input: trained AI model, output: analyzed question data).

[1442] 7.3 The server generates optimal advice using the AI ​​model (Process: Advice generation, Output: Generated advice).

[1443] 7.4 The server sends the generated advice to the terminal (Output: Advice sent).

[1444] Step 8: Providing advice

[1445] 8.1 The terminal receives the advice sent from the server (input: advice sent).

[1446] 8.2 The terminal displays the advice on the user interface (Process: Display UI, Output: Displayed advice).

[1447] Step 9: Provide feedback

[1448] 9.1 The user inputs feedback on the effectiveness and application results of the provided advice (input: feedback content).

[1449] 9.2 The device sends feedback to the server (output: feedback data).

[1450] Step 10: Adjust the model parameters

[1451] 10.1 The server receives and parses the feedback (input: feedback data).

[1452] 10.2 The server adjusts the parameters of the AI ​​model based on the feedback (processing: parameter adjustment, output: adjusted parameters).

[1453] 10.3 The server retrains the AI ​​model using the adjusted parameters (Process: Retrain, Output: Improved AI model).

[1454] In this way, by linking users, devices, and servers, this system realizes a series of processes from user registration to learning the AI ​​model, providing advice, and improving the model through feedback.

[1455] (Application example 1)

[1456] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1457] Inventory management and work efficiency are key issues for modern logistics centers. With conventional systems, real-time data collection and analysis takes time, making it difficult to make effective management decisions. Furthermore, there are insufficient methods for efficiently reflecting the quality of advice provided and feedback on application results. For this reason, there is a demand for a system that supports fast and accurate management decisions in the operation of logistics centers.

[1458] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1459] In this invention, the server includes: means for collecting public information including speech data and behavioral data; means for preprocessing the collected public information; means for training a generative AI model using the preprocessed data; means for generating optimal advice using the generative AI model in response to a question input by a user; means for providing the generated advice to the user; means for receiving feedback from the user and adjusting parameters of the generative AI model; means for collecting real-time data via sensors and cameras in the logistics center; means for preprocessing the collected real-time data and analyzing it as business-related data; means for inputting the analyzed business data into the generative AI model and generating optimal logistics management advice in response to the user's question; means for instantly providing the generated logistics management advice to the user; and means for collecting user feedback on the logistics management advice and improving the generative AI model. This enables quick and accurate management decisions in the operation of a logistics center.

[1460] "Speech data" refers to human speech expressed in audio or text format.

[1461] "Behavioral data" refers to information about the specific actions and activities of humans and machines.

[1462] "Public information" refers to information that is publicly available via the Internet or other media.

[1463] "Preprocessing" refers to the process of removing unnecessary parts from raw data and converting it into an analyzable format.

[1464] A "generative artificial intelligence model" refers to an artificial intelligence model that can learn specific patterns or rules from input data and generate corresponding outputs based on new data.

[1465] "Real-time data" refers to the latest dynamic information collected from a system or environment.

[1466] A "logistics center" refers to a facility that stores, manages, and delivers goods and materials.

[1467] A "sensor" refers to a device that detects the surrounding physical conditions and environment and outputs the data.

[1468] "Camera" refers to a device that captures still images and video.

[1469] "Business data" refers to information related to business operations, such as inventory within the logistics center, workers, and truck operation status.

[1470] "Feedback" refers to the user's evaluation and opinion on the system output, and is used to improve the system's performance based on this.

[1471] This invention relates to a system that uses generative AI to support management decisions, primarily in logistics centers. A specific embodiment of this system is described below.

[1472] User Registration and Authentication

[1473] First, a user accesses the system using a terminal and registers as a new user. They enter the required information (name, email address, password, etc.) on the registration page, and the terminal sends that information to the server. The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user. The user clicks the link in the email to activate their account, completing the registration. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server performs authentication and allows them to log in.

[1474] Data collection and learning

[1475] The server collects real-time data from sensors and cameras installed within the distribution center. Collected data includes inventory levels, worker numbers, truck arrival status, and more. The server preprocesses the collected data and filters out unnecessary information. The preprocessed data is then used to train a generative artificial intelligence model. The trained AI model is designed to support optimal decisions regarding the operation of the distribution center.

[1476] Providing advice

[1477] Users log in to the system using a terminal and input questions related to specific business decisions. The questions include detailed business data and background information. The terminal then sends the input questions to the server. The server analyzes the input information and generates optimal advice using a trained generative AI model. The generated advice is then sent to the terminal and provided to the user. The user can then refer to the provided advice and make appropriate business decisions immediately.

[1478] Feedback and Improvements

[1479] The user inputs feedback into the system regarding the effectiveness of the advice and the results of its application. The feedback includes evaluation items regarding the specificity, usefulness, and feasibility of the advice. The device sends the input feedback to the server, which then uses this feedback to adjust the parameters of the generative AI model. This improves the quality of advice provided in the future.

[1480] Specific examples

[1481] For example, if a logistics center manager wants advice on how to improve inventory management, he or she can log in to the system and enter a specific question. The question includes data such as current inventory levels, number of workers, and truck arrival status. The device sends this information to a server, which uses an AI model to suggest optimal inventory management methods based on the latest logistics trends and past success stories. The manager can then immediately improve inventory management based on the advice provided.

[1482] An example of a prompt is, "Please tell us how the current inventory management system could be improved. The data collected is inventory levels, number of workers, and number of arriving trucks."

[1483] The above is a specific embodiment for carrying out the present invention. By using this system, it is expected that management decisions at logistics centers will be made more quickly and with greater accuracy.

[1484] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1485] Step 1:

[1486] User Registration and Authentication

[1487] Specific operation: A user accesses the system using a terminal and registers as a new user. The user enters information such as their name, email address, and password. The entered information is sent from the terminal to the server. The server verifies the received information and registers the new user information in the database. A confirmation email is then sent to the user. The user clicks the link in the email to activate their account, completing the registration. When the user subsequently logs in to the system, they enter their email address and password, and the terminal sends this information to the server. The server performs authentication and allows the user to log in.

[1488] Input: User input information (name, email address, password)

[1489] Output: New user registration completed and account activated

[1490] Step 2:

[1491] Data collection

[1492] How it works: The server collects real-time data from sensors and cameras installed in the distribution center, continuously collecting data on inventory levels, number of workers, truck arrival status, and more.

[1493] Input: Real-time data from sensors and cameras

[1494] Output: raw data collected

[1495] Step 3:

[1496] Data Preprocessing

[1497] Specific operation: The server preprocesses the collected raw data, filters out unnecessary information, removes noise from the data, and converts it into an analyzable format.

[1498] Input: raw data

[1499] Output: Preprocessed data

[1500] Step 4:

[1501] Training generative AI models

[1502] How it works: The server uses the preprocessed data to train a generative AI model, teaching it patterns and rules to support decisions about inventory management and work efficiency.

[1503] Input: Preprocessed data

[1504] Output: A trained generative AI model

[1505] Step 5:

[1506] Enter a question and generate advice

[1507] How it works: The user uses a device to input a question into the system. The question includes detailed business data. The device then sends the question to the server. The server analyzes the input question and uses a generative AI model to generate optimal advice.

[1508] Input: User question data

[1509] Output: The generated advice

[1510] Step 6:

[1511] Providing advice

[1512] Specific operation: The generated advice is sent to the terminal and displayed to the user, who then uses the advice to make quick business decisions.

[1513] Input: Generated advice

[1514] Output: Advice given to the user

[1515] Step 7:

[1516] Gathering feedback and improving the model

[1517] How it works: The user inputs feedback about the advice provided to the system from their device. The server receives the feedback and adjusts the parameters of the generative AI model based on that feedback, improving the accuracy of future advice.

[1518] Input: User feedback

[1519] Output: An improved generative AI model

[1520] Specific examples

[1521] For example, if a manager asks how to improve inventory management, the prompt might look something like this:

[1522] "How can we improve our current inventory management system? The data collected is about inventory levels, number of workers, and number of arriving trucks."

[1523] The above are the specific processing steps for carrying out the invention. This system enables quick and accurate management decisions at a logistics center.

[1524] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1525] This invention combines a system that uses generative AI to support business decisions with an emotion engine that recognizes user emotions. The following describes in detail the embodiments of the invention.

[1526] User Registration and Authentication

[1527] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends the entered information to the server, which verifies the received information and then registers the new user information in the database. At the same time, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. After that, when the user logs in to the system, they enter their email address and password, and the terminal sends that information to the server. The server compares the information with the database and allows them to log in.

[1528] Data collection and learning

[1529] The server periodically collects publicly available information from the internet. This public information includes speech data and behavioral data of prominent business leaders. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model is trained to mimic business decisions and thought patterns.

[1530] Use of emotion engine

[1531] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the way it is input. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. Based on this, the generative AI model generates advice that best suits the user's emotional state. For example, if the user is feeling impatient or anxious, the system can provide advice on an approach that will alleviate that feeling.

[1532] Providing advice

[1533] When a user inputs a specific question, the device sends that information to the server, which then uses a generative AI model to generate optimal advice. The generated advice is adjusted to match the user's emotional state by an emotion engine and sent to the device. The device displays the advice to the user, allowing the user to make business decisions based on useful advice.

[1534] Feedback and Improvements

[1535] Users provide feedback to the system regarding the usefulness of the advice and the results of its application. This feedback also passes through the emotion engine, and the analysis results are used to adjust the parameters of the generative AI model. The device then sends the feedback to the server, which analyzes it and uses it as data to improve the AI ​​model. This can improve the accuracy of future advice and user satisfaction.

[1536] Specific examples

[1537] When CEO A (user) seeks advice for an important meeting regarding the market launch of a new product, he logs into the system and enters his question along with detailed market analysis data. The device sends this information to the server, which uses an emotion engine to recognize CEO A's emotional state. For example, if it recognizes that CEO A is feeling anxious, the server uses a generative AI model to provide specific and actionable advice to alleviate his anxiety. For example, it provides specific information regarding risk and return in the form of, "Market segment A is high risk, but has the potential for large returns. Segment B is low risk and is expected to have stable growth."

[1538] In this way, this system, which combines an emotion engine, can provide appropriate advice according to the user's emotional state and support corporate management decisions.

[1539] The processing flow will be explained below.

[1540] Step 1:

[1541] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page.

[1542] Step 2:

[1543] The terminal transmits the input information to the server.

[1544] Step 3:

[1545] The server verifies the received information, registers the new user information in the database, and sends a confirmation email to the user's email address.

[1546] Step 4:

[1547] The user activates their account by clicking the link in the confirmation email.

[1548] Step 5:

[1549] The server detects the link click and updates the account status to "active."

[1550] Step 6:

[1551] A user enters an email address and password to log in to the system.

[1552] Step 7:

[1553] The terminal sends the input information to the server.

[1554] Step 8:

[1555] The server checks the information against a database and, if correct, allows login and displays a welcome page to the user.

[1556] Step 9:

[1557] The server runs a crawler to collect speech data and behavioral data that are publicly available on the Internet.

[1558] Step 10:

[1559] The server stores the collected data in a database and performs preprocessing such as text normalization and filtering of unnecessary information.

[1560] Step 11:

[1561] The server uses the preprocessed data to train a generative AI model, using supervised learning and reinforcement learning.

[1562] Step 12:

[1563] The server saves the trained model and makes it available for the next time advice is generated.

[1564] Step 13:

[1565] A user logs into the system seeking advice for a board meeting or management meeting and enters their question and background information.

[1566] Step 14:

[1567] The terminal transmits the input question to the server.

[1568] Step 15:

[1569] Based on the information received by the server, optimal advice is generated using a generative AI model.

[1570] Step 16:

[1571] The server sends the generated advice to the terminal and displays it to the user.

[1572] Step 17:

[1573] Users make business decisions based on the advice provided.

[1574] Step 18:

[1575] The user inputs feedback about the usefulness of the advice and sends it to the system.

[1576] Step 19:

[1577] The device sends the feedback to the server.

[1578] Step 20:

[1579] The server receives the feedback and adjusts the parameters of the generative AI model.

[1580] Step 21:

[1581] The server stores the feedback information in a database and uses it to provide advice next time.

[1582] Step 22:

[1583] The emotion engine analyzes the user's emotional state from their input and feedback.

[1584] Step 23:

[1585] The server uses the analysis results of the emotion engine to generate advice suited to the user's emotional state.

[1586] Step 24:

[1587] The server uses the emotion engine's analysis results for the next advice and feedback analysis to improve the model.

[1588] Example 2

[1589] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1590] Today's business environment is complex and diverse, requiring managers to make quick and appropriate decisions based on a variety of data and information. However, systems that support business decisions do not take into account the user's emotional state, making it difficult to alleviate the anxiety and stress felt by the user and provide optimal advice. Furthermore, continuous learning and model improvement are necessary to improve the usefulness of generated advice. The purpose of this invention is to solve these problems.

[1591] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1592] In this invention, the server includes means for collecting public information, means for preprocessing the collected public information, means for training a generative AI model using the preprocessed data, means for recognizing a user's emotional state, means for adjusting the generated advice based on the recognized emotional state, and means for receiving feedback from the user and adjusting parameters of the generative AI model. This makes it possible to provide appropriate advice tailored to the user's emotional state and effectively support business decisions.

[1593] "Public information" refers to data or information that is publicly accessible on the Internet, including, for example, news articles, blogs, social media posts, research papers, statements and behavioral data of management, etc.

[1594] "Preprocessing" refers to the process of applying data cleansing, text normalization, filtering, and other processes to collected data to prepare it in a format suitable for analysis.

[1595] A "generative artificial intelligence model" is an AI model trained using machine learning and deep learning techniques that performs inference and generation based on user input.

[1596] "Emotional state" refers to the psychological state or emotion that the user is feeling, and involves analyzing emotions such as anxiety, impatience, and joy.

[1597] "Adjusting advice" means appropriately modifying the generated advice in accordance with the user's emotional state and providing it to the user in an optimal form.

[1598] "Feedback" refers to the user inputting into the system evaluations and opinions about the usefulness of the advice provided and the results of its application.

[1599] "Parameter tuning" refers to readjusting the internal settings and weights of an AI model based on feedback from users to improve the model's performance and accuracy.

[1600] This invention combines a system that uses a generative AI model to support business decisions with an emotion engine that recognizes user emotions. Below, we will explain in detail the embodiments of the invention.

[1601] Overall structure

[1602] The system mainly consists of a server, a terminal, and a user interface. The server is responsible for data collection, preprocessing, AI model training, emotion recognition, and advice generation, while the terminal is responsible for inputting questions from users and sending and receiving feedback. Users access the system using various devices.

[1603] User Registration and Authentication

[1604] A user accesses the system and enters the required information, such as name, email address, and password, into the new user registration page. The terminal sends the entered information to the server, which verifies the information and then registers the new user information in the database. Once registration is complete, a confirmation email is sent to the user's email address. The user clicks on the link contained in the confirmation email to activate their account. Thereafter, the user enters their email address and password to log in to the system. The terminal sends the information to the server, which verifies it against the information in the database and allows the user to log in.

[1605] Data collection and learning

[1606] The server periodically collects publicly available information on the Internet, particularly executive speech and behavioral data. This process utilizes web scraping and API access. The server preprocesses the collected data, normalizing the text and filtering unnecessary information. The preprocessed data is then used to train a generative AI model. This training is carried out using deep learning frameworks such as TensorFlow and PyTorch.

[1607] Use of emotion engine

[1608] When a user uses the system to input a question, the input information includes the user's emotional state. For example, emotions are analyzed from the content of the text and the input method. The device sends this information to the server, which then uses an emotion engine to recognize the user's emotional state. The recognized emotional state is used as an important factor in the generative AI model to generate optimal advice.

[1609] Providing advice

[1610] When a user inputs a specific question into the system, the device sends that information to the server. The server uses a generative AI model to generate optimal advice. The generated advice is then adjusted to the user's emotional state by an emotion engine. The adjusted advice is then provided to the user via the device. For example, if the user is feeling anxious, specific advice to alleviate that anxiety is provided.

[1611] Feedback and Improvements

[1612] The user enters feedback about the usefulness of the advice provided and the results of its application. This feedback information is sent from the device to the server, which analyzes it. The results of analyzing the feedback data are used to retrain the generative AI model next time, improving the model's performance and accuracy.

[1613] Specific examples

[1614] For example, if a manager seeks advice on launching a new product, he or she logs into the system and enters, "Please give me some advice on launching a new product. I'm currently feeling anxious about the intensifying competition in the online market." The device sends this information to the server, which uses an emotion engine to recognize the manager's emotional state. If anxiety is recognized, the server generates specific advice to alleviate the anxiety, such as, "Market segment A is high risk, but you can expect a big return. Segment B is low risk and is expected to grow steadily." Based on this advice, the manager can make business decisions with confidence.

[1615] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1616] Step 1:

[1617] A user accesses the system and enters required information such as name, email address, and password into the new user registration page.

[1618] Input: Username, Email Address, Password

[1619] Output: Complete set of input data

[1620] Specific operation: The user enters information into a form on a web browser and presses the submit button.

[1621] Step 2:

[1622] The terminal transmits the input information to the server.

[1623] Input: All input data (user name, email address, password)

[1624] Output: HTTP request to the server

[1625] Specific behavior: The form data is sent to the server as an HTTP POST request.

[1626] Step 3:

[1627] The server verifies the received information and registers the new user information in the database.

[1628] Input: Submitted user registration information

[1629] Output: Registration results in the database

[1630] Specific operation: The server checks the format of the input data and the strength of the password, and if there are no problems, it saves the information in the database.

[1631] Step 4:

[1632] The server sends a confirmation email to the user's email address.

[1633] Input: User's email address and confirmation email content

[1634] Output:Confirmation email

[1635] What happens: The server will send a confirmation email via the SMTP server, which will contain a link to activate your account.

[1636] Step 5:

[1637] The user activates their account by clicking the link in the confirmation email.

[1638] Input: Link in confirmation email

[1639] Output: Account enabled

[1640] What happens: When a user clicks on the link, the server receives the request and updates the user status in the database to active.

[1641] Step 6:

[1642] The user enters their email address and password, and the device sends that information to the server, which checks it against a database and allows them to log in.

[1643] Input: Email address, password

[1644] Output: Session information for successful login

[1645] Specific operation: The entered information is sent to the server and compared with the user information in the database. If authentication is successful, a session is created.

[1646] Step 7:

[1647] The server periodically collects public information on the Internet.

[1648] Input: Public data sources on the internet

[1649] Output: Collected dataset

[1650] Specific operations: The server periodically performs scraping and API access to collect data on managerial statements and behavior.

[1651] Step 8:

[1652] The server preprocesses the collected data, normalizing the text and filtering out unnecessary information.

[1653] Input: Collected public data

[1654] Output: Preprocessed dataset

[1655] Specific operation: Data is cleansed using an NLP library (e.g., spaCy) and formatted for analysis.

[1656] Step 9:

[1657] The server uses the preprocessed data to train the generative AI model.

[1658] Input: Preprocessed dataset

[1659] Output: The trained AI model

[1660] Specific operation: Train generative AI models using TensorFlow and PyTorch. Use high-performance GPUs to streamline learning.

[1661] Step 10:

[1662] A user uses the system to enter a question and the terminal sends the information to the server.

[1663] Input: Question data from the user

[1664] Output: Submitted question data

[1665] What happens: A user uses a web interface to enter a question and presses the submit button, which sends the data to the server as an HTTP POST request.

[1666] Step 11:

[1667] The server uses an emotion engine to recognize the user's emotional state.

[1668] Input: Submitted question data

[1669] Output: Perceived emotional state

[1670] Specific operation: The server calls an emotion analysis API (e.g., IBM Watson Natural Language Understanding) to perform emotion recognition.

[1671] Step 12:

[1672] The server uses a generative AI model to generate optimal advice, which is then adjusted by an emotion engine.

[1673] Input: User question data, perceived emotional state

[1674] Output: Adjusted advice

[1675] Specific operation: The prompt sentence "Please give me some advice on launching a new product to market" is passed as input to the generative AI model, and the generated text is adjusted using the emotion engine.

[1676] Step 13:

[1677] The terminal displays the received advice to the user.

[1678] Input: Tailored Advice

[1679] Output: Advice displayed to the user

[1680] Specific operation: The received advice content is displayed on the web browser.

[1681] Step 14:

[1682] The user inputs feedback into the system regarding the usefulness of the advice and the results of its application.

[1683] Input: Feedback data

[1684] Output: Input feedback data

[1685] Specific operation: The user uses the web interface to enter ratings and comments and presses the submit button.

[1686] Step 15:

[1687] The terminal sends feedback information to the server.

[1688] Input: Feedback data

[1689] Output: HTTP request to the server

[1690] Specific behavior: The form data is sent to the server as an HTTP POST request.

[1691] Step 16:

[1692] The server analyzes the feedback and uses it as data to improve the generative AI model.

[1693] Input: Submitted feedback data

[1694] Output: AI model calibration data

[1695] What it does: Analyzes the feedback data and uses it to retrain the generative AI model, improving its performance and accuracy.

[1696] (Application example 2)

[1697] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1698] Conventional systems using generative AI provide management decisions and advice without considering the user's emotional state, resulting in a lack of advice that is optimal for the user's psychological state. Furthermore, when dealing with customers in brick-and-mortar stores, there is a lack of means to recognize emotions in real time and provide advice that is in line with the user's needs, making it difficult to improve customer satisfaction.

[1699] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting public information including utterance data and behavioral data, means for preprocessing the collected public information, means for training a generative artificial intelligence model using the preprocessed data, emotion analysis means for recognizing the user's emotional state, means for generating advice optimal for the user's question based on the generative artificial intelligence model, means for providing the generated advice to the user, means for displaying or outputting advice by voice in real time according to the usage environment, and means for receiving feedback from the user and adjusting parameters of the generative artificial intelligence model. This makes it possible to provide optimal advice based on the user's emotional state in real time and improve customer satisfaction.

[1700] "Speech data" refers to information converted from speech into text format.

[1701] "Behavioral data" refers to information that records a user's actions, location, operation history, etc.

[1702] "Public Information" means publicly accessible information that is published on the Internet.

[1703] "Preprocessing" refers to the process of formatting collected data into a form that is easy to analyze.

[1704] A "generative artificial intelligence model" is an AI model that is trained using large amounts of data.

[1705] "Emotion analysis means" refers to technology or equipment for recognizing a user's emotional state from text or voice data.

[1706] "Advice generation means" refers to AI technologies and algorithms that provide optimal advice based on user input and status.

[1707] The "advice providing means" refers to devices such as a display and a speaker for presenting the generated advice to the user.

[1708] "Real-time display means" refers to technology or equipment for displaying advice on the user's condition without delay.

[1709] "Real-time voice output means" refers to technology or equipment for instantly providing generated advice in voice form.

[1710] "Feedback receiving means" refers to the technology and equipment used to collect opinions and reactions from users.

[1711] "Parameter adjustment means" refers to techniques or equipment for improving the performance of an artificial intelligence model based on collected feedback information.

[1712] The present invention provides a system for recognizing a user's emotional state and providing appropriate management decisions and advice based on the recognition. The system is configured using various hardware and software.

[1713] User Registration and Authentication

[1714] A user accesses the system and enters the required information (name, email address, password, etc.) on the new user registration page. The terminal sends this information to the server, which then registers the new user information in the database based on the received information. At the same time, a confirmation email is sent to the user's email address. When the user clicks on the link contained in the confirmation email, their account is activated and they can then log in to the system.

[1715] Data collection and learning

[1716] The server periodically collects public information from the Internet (such as speech data and behavioral data). This is done using Python scraping technology and public APIs. The collected data is preprocessed to normalize the text and filter out unnecessary information. The preprocessed data is then used to train a generative AI model. This generative AI model uses Hugging Face's Transformers library and TensorFlow.

[1717] Use of emotion engine

[1718] When a user uses the system to input a question, the device sends that information to the server. The server's emotion analysis means analyzes the user's emotional state from their text and voice data. Based on the analysis results, the generative AI model generates optimal advice based on the user's emotional state.

[1719] Providing advice

[1720] The generated advice is provided to the user via the device. The display of the smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The advice is displayed or output as audio in real time, allowing the user to respond immediately.

[1721] Feedback and Improvements

[1722] User feedback is sent to the server via the device, which then adjusts the parameters of the generative AI model to improve its accuracy. This process uses a specific algorithm (e.g., backpropagation).

[1723] Specific examples

[1724] For example, if a store staff member receives feedback from a customer saying, "I'd like to learn more about this product, but I have some concerns.":

[1725] Provided prompt: The user is feeling anxious. Please give some advice to ease their anxiety.

[1726] The server uses a generative AI model to generate advice such as, "This product is of high quality and has satisfied many customers in the past. Don't worry."

[1727] In this way, the system can provide optimal advice according to the user's emotional state, increasing customer satisfaction.

[1728] To implement this invention, we use a smartphone or tablet as hardware and Python, TensorFlow, the Hugging Face Transformers library, etc. as software. This system enables real-time emotion analysis and advice provision.

[1729] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1730] Step 1: User Registration and Authentication

[1731] A user accesses the new user registration page and enters the required information, such as name, email address, and password. The terminal sends this information to the server, which registers the received information in a database. At the same time, a confirmation email is sent to the user's email address. The user clicks the link in the confirmation email to activate their account. When the user then logs in with their email address and password, the terminal sends that information to the server, which collates it with the database information and allows them to log in. The input is the user's registration information, and the output is the sending of a confirmation email and account activation information.

[1732] Step 2: Data collection and preprocessing

[1733] The server periodically collects public information (speech data, behavioral data) from the Internet. Collection methods include scraping technology using Python and public APIs. The server preprocesses the collected data, such as normalizing the text and filtering out unnecessary information, and stores it in a database. The input is public information from the Internet, and the output is the preprocessed data.

[1734] Step 3: Training the generative AI model

[1735] Using the preprocessed data, the server trains a generative AI model using TensorFlow or Hugging Face's Transformers library. This is to optimize the model parameters based on large amounts of data and apply them to business decisions and advice generation. The input is the preprocessed data, and the output is a trained generative AI model.

[1736] Step 4: Sentiment Analysis

[1737] When a user uses the system to input a question, the device sends that information to the server. The server uses an emotion analysis means (emotion engine) to analyze the user's emotional state from text and voice data and provides the results to the generative AI model. The input is the user's question data, and the output is the user's emotional state.

[1738] Step 5: Advice Generation

[1739] The server uses a generative AI model to generate optimal advice based on the emotional state. A prompt such as "The user is feeling anxious. Please give us some advice to alleviate their anxiety" is input into the generative AI model, which then outputs specific advice. The inputs are the emotion analysis results and the prompt, and the output is the generated advice.

[1740] Step 6: Providing advice

[1741] The generated advice is sent from the server to the terminal, which then presents it to the user. The display of a smartphone or tablet is used as the display means, and the speaker is used as the audio output means. The input is the generated advice, and the output is the advice display or audio provided to the user.

[1742] Step 7: Feedback and model adjustment

[1743] The user inputs feedback into the system about the usefulness of the advice that was implemented. The device sends the feedback to the server, which analyzes it and adjusts the parameters of the generative AI model. The input is the user's feedback, and the output is the adjusted generative AI model.

[1744] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1745] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1746] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1747] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1748] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1749] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1750] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1751] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1752] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1753] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1754] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1755] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1756] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1757] 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.

[1758] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1759] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1760] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1761] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1762] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1763] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1764] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1765] The following is further disclosed regarding the above embodiment.

[1766] (Claim 1)

[1767] means for collecting public information including speech data and behavioral data;

[1768] a means for preprocessing the collected public information;

[1769] means for training a generative artificial intelligence model using the preprocessed data;

[1770] A means for generating optimal advice using a generative artificial intelligence model in response to a question input by a user;

[1771] means for providing the generated advice to a user;

[1772] a means for receiving feedback from a user and adjusting parameters of the generative artificial intelligence model;

[1773] A system including:

[1774] (Claim 2)

[1775] 10. The system of claim 1, further comprising means for periodically collecting public information on the Internet.

[1776] (Claim 3)

[1777] 10. The system of claim 1, further comprising means for generating specific advice in real time based on a user's question.

[1778] "Example 1"

[1779] (Claim 1)

[1780] A means for user registration and authentication in which the user inputs information such as name, email address, and password and sends it from the terminal to the server;

[1781] A means for the server to periodically collect public information on the Internet;

[1782] a means for preprocessing the public information collected by the server to remove unnecessary information and convert it into an analyzable format;

[1783] A means for the server to train a generative artificial intelligence model using the preprocessed data;

[1784] A means for a user to input a question into the system and transmit it from the terminal to the server;

[1785] A means for the server to analyze the content of the user's question and generate optimal advice using a trained generative artificial intelligence model;

[1786] a means for the server to transmit the generated advice to the terminal and provide it to the user;

[1787] A means for a user to input feedback on the effectiveness or application result of the advice and transmit the feedback from the terminal to the server;

[1788] a means for adjusting parameters of the generative artificial intelligence model based on the feedback received by the server;

[1789] A system including:

[1790] (Claim 2)

[1791] 10. The system of claim 1, further comprising: means for collecting the collected public information using a scraping tool.

[1792] (Claim 3)

[1793] 10. The system of claim 1, further comprising means for the server to generate specific advice in real time based on questions from the user.

[1794] "Application Example 1"

[1795] (Claim 1)

[1796] means for collecting public information including speech data and behavioral data;

[1797] a means for preprocessing the collected public information;

[1798] means for training a generative artificial intelligence model using the preprocessed data;

[1799] A means for generating optimal advice using a generative artificial intelligence model in response to a question input by a user;

[1800] means for providing the generated advice to a user;

[1801] a means for receiving feedback from a user and adjusting parameters of the generative artificial intelligence model;

[1802] A means of collecting real-time data through sensors and cameras in logistics centers,

[1803] A means of pre-processing the collected real-time data and analyzing it as business-related data;

[1804] A means to input the analyzed business data into a generative AI model and generate optimal logistics management advice in response to user questions;

[1805] a means for instantly providing the generated logistics management advice to a user;

[1806] A means of collecting user feedback on logistics management advice and improving the generative AI model; and

[1807] A system including:

[1808] (Claim 2)

[1809] 10. The system of claim 1, further comprising means for periodically collecting public information on the Internet.

[1810] (Claim 3)

[1811] 10. The system of claim 1, further comprising means for generating specific advice in real time based on a user's question.

[1812] "Example 2: Combining Emotion Engines"

[1813] (Claim 1)

[1814] means of collecting public information;

[1815] a means for preprocessing the collected public information;

[1816] means for training a generative artificial intelligence model using the preprocessed data;

[1817] A means for generating optimal advice using a generative artificial intelligence model in response to a question input by a user;

[1818] means for recognizing the emotional state of a user;

[1819] means for adjusting the generated advice based on the perceived emotional state;

[1820] means for providing the generated advice to a user;

[1821] a means for receiving feedback from a user and adjusting parameters of the generative artificial intelligence model;

[1822] A system including:

[1823] (Claim 2)

[1824] 10. The system of claim 1, further comprising means for periodically collecting public information on the Internet.

[1825] (Claim 3)

[1826] 10. The system of claim 1, further comprising means for generating specific advice in real time based on a user's question.

[1827] "Application example 2 when combining emotion engines"

[1828] (Claim 1)

[1829] means for collecting public information including speech data and behavioral data;

[1830] a means for preprocessing the collected public information;

[1831] means for training a generative artificial intelligence model using the preprocessed data;

[1832] A means for generating optimal advice using a generative artificial intelligence model in response to a question input by a user;

[1833] means for providing the generated advice to a user;

[1834] a means for receiving feedback from a user and adjusting parameters of the generative artificial intelligence model;

[1835] emotion analysis means for recognizing the emotional state of a user;

[1836] A means for displaying advice or outputting sound in real time according to the usage environment;

[1837] A system including:

[1838] (Claim 2)

[1839] 10. The system of claim 1, further comprising means for periodically collecting public information on the Internet.

[1840] (Claim 3)

[1841] 10. The system of claim 1, further comprising means for generating specific advice in real time in cooperation with the sentiment analysis means based on the user's sentiment. [Explanation of symbols]

[1842] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. means for collecting public information including speech data and behavioral data; a means for preprocessing the collected public information; means for training a generative artificial intelligence model using the preprocessed data; A means for generating optimal advice using a generative artificial intelligence model in response to a question input by a user; means for providing the generated advice to a user; a means for receiving feedback from a user and adjusting parameters of the generative artificial intelligence model; A system including:

2. 10. The system of claim 1, further comprising means for periodically collecting public information on the Internet.

3. The system of claim 1 , further comprising means for generating specific advice in real time based on a user's question.

Images