system

Abstract

Provide a system. [Solution] A means of collecting CEO quotes and ideas, a means for pre-processing the collected data; means for training an artificial intelligence model using the preprocessed data; and a means for generating ideas based on user prompts.

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] Create a "Problem to be solved" and a "Means to solve the problem" using the following format.

[0005] In today's corporate environment, rapid and effective idea generation is required, but achieving this is not easy. Applying the knowledge of leaders with creative and visionary thinking to a wide range of tasks and projects is particularly challenging and requires a great deal of time and resources. Furthermore, specialized knowledge is required to generate ideas, and sharing that knowledge throughout the organization is even more difficult. Given these circumstances, there is a need for a system that can efficiently utilize the valuable knowledge of CEOs and other leaders to support rapid and effective idea generation. [Means for solving the problem]

[0006] To solve the above problems, the present invention provides the following means. First, a means for collecting CEO quotes and ideas is provided. A means for preprocessing the collected data is also provided. A means for training an artificial intelligence model using the preprocessed data is then provided, and a means for generating ideas based on user prompts is also provided. Specifically, a means for tokenizing the text portion of the collected data and removing stop words is provided. The present invention also includes a means for returning the generated ideas to the user's terminal. This enables rapid and effective idea generation within a company, allowing high-quality strategies and proposals to be developed with limited time and resources.

[0007] Understood. The following are definitions of key terms contained in the claims:

[0008] "Collection means" refers to the devices and methods used to obtain and store data from a particular source.

[0009] "Preprocessing means" refers to a processing method for preparing acquired data into a usable format.

[0010] "Training" refers to the process of using pre-processed data to train an artificial intelligence model.

[0011] "Generative means" refers to the process of generating new ideas and content using trained artificial intelligence models.

[0012] A "prompt" refers to text of instructions or questions given as input by a user.

[0013] "Stop words" are words that are frequently used in natural language processing and should be excluded from indexing and tokenization.

[0014] "Tokenization" refers to the process of breaking text into elements such as words and phrases.

[0015] "Terminal" means a computer or other device used by a User to access and operate the System.

[0016] An "artificial intelligence model" refers to a mathematical model that uses machine learning algorithms to learn patterns from input data and make predictions or generate data for new data. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. The following describes the system configuration and its specific operation.

[0039] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0040] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0041] The server then uses the preprocessed data to train an artificial intelligence model. This training method uses machine learning algorithms to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns to improve the model's ability to generate new text.

[0042] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0043] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0044] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0045] The processing flow will be explained below.

[0046] Understood. The program's processing will be explained in the following format, divided into steps.

[0047] Step 1:

[0048] The server sends an HTTP request from the specified URL list to retrieve data including the CEO's quotes and ideas. The retrieved data is saved in JSON format or similar.

[0049] Step 2:

[0050] The server preprocesses the collected data by extracting and combining text parts from the data, tokenizing the text into words, and removing frequent stop words to make it easier to analyze.

[0051] Step 3:

[0052] The server trains an artificial intelligence model (e.g., GPT-2) using the preprocessed text data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters.

[0053] Step 4:

[0054] A user sends a request to the server by entering a specific prompt from a terminal, which is text containing instructions or questions about a new idea or proposal.

[0055] Step 5:

[0056] The server tokenizes the input prompt and converts it into a generative tensor, which is then passed to a trained artificial intelligence model, which is then instructed to generate text up to a specified maximum length.

[0057] Step 6:

[0058] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0059] Step 7:

[0060] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0061] These are the specific processing steps of the program. Through these steps, users can efficiently generate new ideas and use them in business proposal materials, etc.

[0062] Example 1

[0063] 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."

[0064] Conventional idea generation systems have struggled to efficiently collect CEO quotes and ideas and generate new ideas based on them. This process requires multiple steps, such as collecting data from websites, retrieving ideas from databases, and preprocessing text, which can be labor-intensive and time-consuming when done manually. Furthermore, the quality of the generated ideas is unstable, resulting in insufficient compatibility with user needs. This has led to a need for more efficient idea generation processes within companies.

[0065] 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.

[0066] In this invention, the server includes means for scraping CEO quotes and ideas from a website, means for retrieving quotes and ideas from a database using an API, means for storing the collected data in the database, means for preprocessing the collected data, means for tokenizing the preprocessed data and removing stop words, means for normalizing the preprocessed data, means for training an AI model using the preprocessed data, and means for generating ideas based on user prompts using the trained AI model. This enables high-quality ideas to be generated quickly based on user-entered prompts. Furthermore, the preprocessing of collected data and the AI ​​model training process are automated, significantly reducing labor and time. Furthermore, the generated ideas are more tailored to user needs, contributing to the efficiency of the idea generation process within a company.

[0067] "CEO quotes and ideas" refers to statements, thoughts, strategies, visions, etc. announced by a company's chief executive officer.

[0068] "Website scraping" refers to techniques and methods for automatically obtaining information from specific web pages using a program.

[0069] "Means of obtaining comments and ideas from a database using an API" refers to the technology or method of using an application programming interface to access a specific database and obtain the required information.

[0070] "Means for storing collected data in a database" refers to the techniques and methods for storing acquired or collected data in a database in an appropriate format.

[0071] "Means for preprocessing collected data" refers to the processing carried out before data analysis, and refers to techniques and methods for formatting, cleaning, standardizing, etc. of data.

[0072] "Means for tokenizing preprocessed data and removing stop words" refers to techniques and methods for splitting text data into words or phrases and removing unnecessary common words.

[0073] "Means for normalizing preprocessed data" refers to techniques or methods for maintaining consistency in preprocessed data, such as converting to all lowercase and removing special characters and unnecessary whitespace.

[0074] "Methods for training artificial intelligence models using preprocessed data" refers to techniques and methods that use organized data to train machine learning algorithms or artificial intelligence models and improve their performance.

[0075] "Means for generating ideas based on user prompts using a trained artificial intelligence model" refers to technologies and methods that use a pre-trained artificial intelligence model to automatically generate new ideas or text in response to specified input (prompts) from a user.

[0076] "Means for analyzing the generated ideas and returning them to the user's device" refers to the technology or method for analyzing automatically generated ideas and sending the results to the device used by the user.

[0077] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects quotes and ideas from top executives of a company, trains an artificial intelligence model based on the collected ideas, and generates new ideas in response to user prompts. The system configuration and its specific operation are described below.

[0078] First, the server scrapes corporate leaders' quotes and ideas from their websites. It uses Python libraries such as BeautifulSoup and Selenium to automatically extract data from specific web pages. This allows the leaders' past quotes and ideas to be collected as text data.

[0079] The server then uses an API to retrieve the comments and ideas from the database. It uses an application programming interface, such as Firebase or the Google® Sheets API, to pull the required information from the database. This process integrates data from multiple sources.

[0080] The collected data is stored in a database by the server using a database management system such as SQLite or MySQL®, and the data is organized in an appropriate format so that it can be used efficiently in subsequent processing steps.

[0081] Next, the server preprocesses the collected data. This includes tokenizing the text data, removing stop words, and normalizing the data. Specifically, it uses Python's NLTK (Natural Language Toolkit) and Spacy to tokenize and remove frequent meaningless words (stop words). It also converts all data to lowercase and removes special characters and unnecessary whitespace to create a consistent dataset.

[0082] The preprocessed data is then used to train an artificial intelligence model. Machine learning libraries such as TENSORFLOW® and PyTorch are used to train the model on the data. The server splits the dataset into training and validation sets and trains over multiple epochs (training cycles). This optimizes the model's performance.

[0083] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter a prompt like, "Let's think of an idea for a new project. The goal is to expand the market." The server receives this prompt and analyzes it as text data. Using the preprocessed data, a trained artificial intelligence model generates new ideas.

[0084] Finally, the generated ideas are sent back from the server to the device, where the user can review the new ideas and modify or adopt them as necessary. This process allows users to quickly and efficiently obtain new ideas and suggestions.

[0085] Let's take a concrete example. When a user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market," the server generates an idea such as "Introduce digital marketing to our existing product line to expand the market" and sends it back to the device. In this way, users can easily come up with original ideas simply by inputting a prompt.

[0086] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0087] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0088] Step 1: Collect data

[0089] The server collects quotes and ideas from the CEO. The server runs scripts written in Python and uses BeautifulSoup and Selenium to scrape data from specific websites. The server also retrieves quotes and ideas from a database using Firebase and Google Sheets APIs. The input for this step is the website URL and database query, and the output is text data. Specifically, it parses the HTML source of the webpage and extracts the required information. It also sends API requests and organizes the returned data.

[0090] Step 2: Save your data

[0091] The text data collected by the server is saved in a database. The database management systems used are SQLite and MySQL. The input is the text data collected in step 1, and the output is the data stored in the database. Specifically, the process connects to the database, creates a table, and inserts data.

[0092] Step 3: Preprocessing the data

[0093] The server preprocesses the data. It uses Python's NLTK or Spacy to tokenize the collected text data and remove stop words. It also normalizes the data. The input is the raw data saved in step 2, and the output is the preprocessed, clean data. Specifically, it splits the text into words, removes unnecessary words, and converts all text to lowercase.

[0094] Step 4: Training the AI ​​model

[0095] The server uses the preprocessed data to train an artificial intelligence model. Using TensorFlow or PyTorch, a large amount of text data is input and the model is trained. The input is the data preprocessed in step 3, and the output is the trained model. Specifically, the data is divided into training and validation data, and the model is trained over multiple epochs.

[0096] Step 5: Receiving the prompt

[0097] When a user wants to get a new idea, they send a specific prompt from their terminal to the server. The input is the prompt entered by the user, and the output is the data sent to the server. For example, a user might enter the prompt "Let's think of an idea for a new project. The goal is to expand the market." The specific operation is to enter the prompt into a form on the terminal and click the send button.

[0098] Step 6: Idea generation

[0099] Based on the prompt received by the server, a trained artificial intelligence model is used to generate new ideas. The input is the user's prompt and the trained model, and the output is the generated idea. Specifically, the prompt is input into the model and new text related to it is generated.

[0100] Step 7: Return and view your ideas

[0101] The server sends the generated idea back to the user's terminal, where the user confirms it. The input is the idea generated in step 6, and the output is the text displayed on the user's terminal. Specifically, the server sends the generated idea as an HTTP response, and the text is displayed in the browser.

[0102] (Application example 1)

[0103] 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."

[0104] In order to improve factory productivity, it is essential to quickly adopt new technologies and ideas. However, it takes a lot of time and effort for on-site engineers and managers to collect the necessary information and take appropriate measures. Furthermore, there is no system in place to effectively utilize the CEO's opinions and past ideas, which means that the knowledge of the entire organization cannot be fully utilized.

[0105] 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.

[0106] In this invention, the server includes a means for collecting CEO quotes and ideas, a means for preprocessing the collected data, a means for training a generative artificial intelligence model using the preprocessed data, a means for generating ideas based on user prompts, and a means for transmitting the generated ideas to robots in the factory, thereby enabling factory engineers and managers to quickly adopt new technologies and measures and effectively utilize knowledge from the entire organization.

[0107] A "CEO" is the highest-ranking executive who, as the chief executive officer, determines the company's management policies and formulates and implements the company's strategies.

[0108] A "quote" is a statement made or recorded by a specific individual in the past.

[0109] An "idea" is an original thought or proposal for solving a particular problem.

[0110] "Collection methods" refer to the methods and techniques used to obtain and store data from a particular source.

[0111] "Preprocessing means" refers to methods and techniques for processing collected data to prepare it in a form suitable for analysis and learning.

[0112] A "generative artificial intelligence model" is an artificial intelligence system that is trained using machine learning algorithms and has the ability to generate new information.

[0113] A "prompt" is a question or instruction that a user enters to give instructions to an artificial intelligence model.

[0114] "Generative means" refers to the methods or techniques by which an AI model generates new text or ideas in response to input prompts.

[0115] "Factory robots" are autonomous mechanical devices used to automate production lines and factory operations.

[0116] A "user terminal" is a device through which a user can input or output information, such as a computing device such as a smartphone or tablet.

[0117] This invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. This system is particularly useful for quickly acquiring and implementing new technologies and improvements for factory robots. The system configuration and specific operation are described below.

[0118] First, the server collects the CEO's quotes and ideas. The collection method uses algorithms and APIs to obtain and store data from specific sources. Specifically, this can involve techniques such as scraping data from websites or retrieving information from databases via APIs. This allows the CEO's past statements and ideas to be collected as text data.

[0119] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a preprocessing method, natural language processing (NLP) libraries such as SpaCy and NLTK are used to prepare the data in a format that is easy to analyze. Tokenization divides sentences into words and removes frequent meaningless words (stop words), making the data easier to analyze.

[0120] The server then uses the preprocessed data to train a generative artificial intelligence model. The training method involves using machine learning algorithms such as OpenAI's GPT-4 to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0121] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter specific instructions such as, "Tell me how to improve the efficiency of a new production line" or "Please provide me with a new idea to reduce manufacturing costs." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0122] The generated ideas are sent from the server to robots and terminals in the factory, where users can check them. The robots in the factory present the generated ideas to managers by reading them out loud or displaying them on a screen. This allows users to quickly and efficiently obtain new ideas and suggestions. For example, specific ideas such as "To improve the efficiency of the production line, we will introduce automation technology and optimize the coordination of each process" and "To reduce manufacturing costs, it is effective to introduce energy-efficient equipment and promote resource recycling" are generated.

[0123] The above is a specific embodiment for carrying out the present invention. The roles and functions of the server, terminal, and user allow users to easily come up with new ideas and increase factory productivity.

[0124] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0125] Step 1:

[0126] The server retrieves and stores data from a specific source using a method to collect CEO quotes and ideas, such as scraping data from a website or pulling information from a database via an API. The input for this step is a specific source URL or API endpoint, and the output is the collected text data.

[0127] Step 2:

[0128] The server preprocesses the collected data using a natural language processing (NLP) library. The libraries used are SpaCy and NLTK. Specifically, the collected text data is tokenized and stop words are removed. The input of this step is the collected text data, and the output is the preprocessed tokenized data.

[0129] Step 3:

[0130] The server uses the preprocessed data to train a generative AI model. The algorithm used is a machine learning model such as OpenAI's GPT-4. Specifically, the model takes tokenized data as input and learns its patterns to improve its ability to generate new text. The input for this step is preprocessed tokenized data, and the output is a trained generative AI model.

[0131] Step 4:

[0132] A user uses a terminal to send a prompt to the server to get new ideas. Specifically, the user inputs a prompt such as "Please tell me a new method to improve the efficiency of the production line" or "Please provide me with a new idea to reduce manufacturing costs." The input of this step is the user's prompt, and the output is the transmission of the prompt to the server.

[0133] Step 5:

[0134] The server receives prompts from users and generates ideas using a trained generative AI model. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text. The input for this step is the prompt sent by the user, and the output is the generated idea text.

[0135] Step 6:

[0136] The server sends the generated ideas to the robots and terminals in the factory. Specifically, the generated text is read aloud or sent to the robots to be displayed on a display. The input of this step is the generated idea text, and the output is the specific idea displayed on the robots and terminals.

[0137] Step 7:

[0138] The user checks the generated ideas through the terminal or the robot and takes appropriate measures. The input of this step is the text of the ideas displayed on the robot and the terminal, and the output is the user's utilization of the ideas.

[0139] The above is the specific process flow for implementing the invention. This system allows users to quickly and efficiently adopt new technologies and solutions.

[0140] 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.

[0141] The following describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on the collected data, and generates ideas based on user prompts, with an emotion engine that recognizes the user's emotions. The following describes the system configuration and its specific operation.

[0142] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0143] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0144] The server then uses the preprocessed data to train an artificial intelligence model (such as GPT-2). This training method uses a machine learning algorithm to train a large amount of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0145] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0146] This is where the emotion engine comes in, recognizing emotions from the user's input prompt. The emotion engine analyzes the text in the user's prompt and evaluates their emotional state. For example, it can determine if the user is nervous or relaxed.

[0147] The server adjusts the generated ideas based on the emotions recognized by the emotion engine, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is feeling nervous, the server may generate ideas containing encouraging words.

[0148] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0149] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0150] The processing flow will be explained below.

[0151] Understood. As an embodiment of the invention, the process flow will be described in detail in the following format.

[0152] Step 1:

[0153] The server sends HTTP requests from a specified URL list to collect the CEO's quotes and ideas. The collected data is saved in JSON format.

[0154] Step 2:

[0155] The server preprocesses the collected data. Specifically, it extracts and combines text parts from the data. It also tokenizes the text data into words and removes stop words, making it easier to analyze.

[0156] Step 3:

[0157] The server trains an artificial intelligence model using the preprocessed data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters, thereby improving the model's ability to generate new text.

[0158] Step 4:

[0159] A user inputs a specific prompt from a terminal and sends a request to the server. For example, the user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market."

[0160] Step 5:

[0161] The server tokenizes the input prompt and converts it into tensor data for generation. The emotion engine analyzes the prompt text and recognizes the user's emotion. For example, it determines whether the user is "excited" or "nervous" from the prompt text.

[0162] Step 6:

[0163] The server inputs the trained AI model with the emotional information recognized by the emotion engine, which allows the generated ideas to be optimized for the user's emotional state.

[0164] Step 7:

[0165] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0166] Step 8:

[0167] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0168] For example, if a user inputs the prompt "Let's think of a new project idea with the goal of market expansion," the server uses the emotion engine to recognize that the user's emotion is "excited." Based on this, the AI ​​model generates ideas such as "Introduce digital marketing to existing product lines to target new customer segments in order to expand the market" and sends them back to the user in an encouraging and hopeful tone.

[0169] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0170] Example 2

[0171] 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."

[0172] Conventional systems were unable to efficiently collect the CEO's knowledge and ideas and then effectively generate useful ideas for users based on them. Furthermore, the generated ideas were not adapted to the user's emotional state, resulting in low user satisfaction and effectiveness. Furthermore, there was a lack of a way to quickly and reliably deliver the generated ideas to the user's device.

[0173] 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.

[0174] In this invention, the server includes means for collecting CEO quotes and ideas, means for tokenizing the collected data and removing stop words and preprocessing the data, means for training a generative artificial intelligence model using the preprocessed data, means for generating ideas based on user prompts, means for performing sentiment analysis and adjusting the generated ideas based on the results, and means for returning the generated ideas to the user's terminal. This makes it possible to efficiently generate useful ideas while taking the user's sentiment into consideration and quickly and reliably provide them to the user's terminal.

[0175] "Means for collecting CEO quotes and ideas" refers to technology that obtains past statements and ideas of a company's chief executive officer (CEO) from various sources and stores them in a database.

[0176] "Tokenization" refers to the process of dividing text data into words, sentences, and other semantic units.

[0177] "Stop word removal" refers to a technique for removing meaningless words (such as "the" and "and") that are frequent but not very useful for analysis from text.

[0178] "Preprocessing methods" refers to a series of operations (e.g., tokenization, stop word removal, normalization, etc.) performed on collected data to make it easier for machine learning models to process.

[0179] A "generative artificial intelligence model" refers to a machine learning model that has been trained on a large amount of data in advance and is capable of generating new text based on given prompts.

[0180] "Sentiment analysis" refers to the technology of evaluating and classifying emotions and emotional states contained in text data.

[0181] "Means for generating ideas" refers to a technology that uses a pre-trained generative artificial intelligence model to generate new ideas based on user-entered prompts.

[0182] "Means for adjusting ideas" refers to a technology that adapts the tone and content of generated ideas to the user's emotional state based on the results of sentiment analysis.

[0183] "Means for sending back to the user's terminal" refers to technology that sends the generated ideas to the user's computing device so that they can be viewed.

[0184] This section describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains a generative AI model based on the collected data, and generates ideas based on user prompts, with emotion analysis technology that recognizes user emotions. The following describes the system configuration and its specific operation.

[0185] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, web scraping technology (BeautifulSoup or Scrapy) can be used to collect text data from interviews and speeches. Another method is to retrieve the CEO's past statements from a company's internal database via API.

[0186] The server then preprocesses the collected data, which includes tokenization and stop word removal. Natural language processing libraries (such as NLTK and SpaCy) are used to split the text into words and remove stop words, making the data easier to analyze.

[0187] The server then uses the preprocessed data to train a generative artificial intelligence model. The model used is GPT-2. Hugging Face's Transformers library is used to train the model using the preprocessed data. This process trains the model using a large amount of text data, improving its ability to generate new text.

[0188] When a user wants to get new ideas, they send a specific prompt from their device to the server, for example, "Think of an idea for a new project. The goal is to expand the market." This prompt is sent to the server and parsed using a tokenizer.

[0189] This is where sentiment analysis technology comes in, recognizing emotions from the user's prompts. The server uses sentiment analysis tools (such as IBM Watson® or Hume AI) to analyze the text in the user's prompts and assess their emotional state. For example, it can identify when the user is tense or relaxed.

[0190] The server then adjusts the generated ideas based on the emotions recognized through emotion analysis, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is nervous, the server generates ideas containing encouraging words.

[0191] Finally, the generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. As a specific example, an idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. Users can easily generate original ideas by simply entering prompts.

[0192] This system will be an effective means of streamlining idea generation within a company, making extensive use of leaders' knowledge, and enabling ideas to be provided that take into consideration users' emotions.

[0193] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0194] Step 1:

[0195] The server collects CEO quotes and ideas. The input is the URL of a specific website or database. The server uses web scraping technology (BeautifulSoup or Scrapy) to obtain the data and save it in text format. Specifically, the server accesses the website, parses the HTML document, and extracts the required text data.

[0196] Input: URL, API endpoint

[0197] Output: Text data (CEO quotes and ideas)

[0198] Step 2:

[0199] The server preprocesses the collected text data. First, the collected text is tokenized. Next, stop words are removed. To do this, a natural language processing library (NLTK or SpaCy) is used. Specifically, the text is divided into words and words with high frequency but low information content are filtered out.

[0200] Input: Text data

[0201] Output: Preprocessed text data (tokenized and stop words removed)

[0202] Step 3:

[0203] The server uses the preprocessed text data to train a generative artificial intelligence model. The model used is GPT-2. Using Hugging Face's Transformers library, the preprocessed data is fed to the model, which is trained over multiple epochs. Specifically, a training dataset is prepared, and the model's training parameters are set and run.

[0204] Input: Preprocessed text data

[0205] Output: A trained generative artificial intelligence model

[0206] Step 4:

[0207] The user inputs a prompt for a new idea from the terminal and sends it to the server. For example, the user inputs the instruction "Let's think of an idea for a new project. The goal is to expand the market," and clicks the send button.

[0208] Input: User prompt

[0209] Output: Send prompt to server

[0210] Step 5:

[0211] The server passes the prompt received to a sentiment analysis engine for analysis. The sentiment analysis engine uses IBM Watson or Hume AI. This evaluates the emotional state of the text contained in the prompt. Specifically, it obtains an emotional score and an emotional label.

[0212] Input: User prompt

[0213] Output: Sentiment analysis results (sentiment score, emotion label)

[0214] Step 6:

[0215] The server uses a generative artificial intelligence model to generate ideas based on the results of sentiment analysis and user prompts. The tone and content of the generated ideas are adjusted depending on the results of sentiment analysis. For example, if the prompt "Let's think of an idea for a new project. The goal is to expand the market," and the user feels nervous, the server will generate an idea that includes encouraging words.

[0216] Input: User prompt, sentiment analysis results

[0217] Output: Generated ideas

[0218] Step 7:

[0219] The server sends the generated ideas back to the terminal so that the user can review them. Specifically, the generated ideas are displayed in text format on the user's screen. An idea such as "Introduce digital marketing to existing product lines to expand the market" is displayed.

[0220] Input: Generated ideas

[0221] Output: The idea displayed on the user's device

[0222] Through each of the above processing steps, the system can efficiently generate and quickly provide useful ideas while taking into consideration the user's emotional state.

[0223] (Application example 2)

[0224] 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."

[0225] In idea generation systems using artificial intelligence, there is a need for a method that appropriately reflects the user's emotional state and provides specific and optimal ideas that are suited to the user's purpose and situation. In such systems, the user experience can be improved by dynamically adjusting the tone and content of the ideas generated based on the user's emotions, but the specific means for achieving this have been unclear.

[0226] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0227] In this invention, the server includes means for collecting CEO quotes and ideas, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for recognizing emotions from user input text, means for adjusting generated ideas based on the recognized emotion data, and means for optimizing the tone and content of the generated ideas, thereby enabling the server to accurately grasp the user's emotional state and quickly provide optimal ideas corresponding to that state.

[0228] "Quotations" refers to the content or records of past statements made by a specific person or group.

[0229] "Idea" refers to creative thoughts such as new ideas, plans, and strategies.

[0230] "Collection" refers to the act of gathering necessary data or information using specific means.

[0231] "Preprocessing" refers to a series of tasks that involve formatting data and removing unnecessary elements in order to improve the efficiency of data analysis and machine learning.

[0232] "Artificial intelligence model" refers to a computational model designed to learn from collected data and provide appropriate outputs based on new data.

[0233] "User" refers to an individual or corporation that uses a system or application.

[0234] A "prompt" refers to a sentence of instructions or questions that a user inputs to a system.

[0235] "Emotions" refer to psychological states such as joy, sadness, and anger that people experience.

[0236] "Recognition" refers to understanding and identifying specific patterns or meanings from data or information.

[0237] "Data" refers to facts, measurements, or records obtained from a particular source.

[0238] "Tone" refers to the mood, attitude, and style of a piece of writing or speech.

[0239] As an embodiment of the present invention, a system that incorporates emotion recognition and generates optimal ideas in response to user prompts will be described. This system efficiently collects CEO quotes and past ideas, trains an AI model using the collected data, and generates ideas that correspond to the user's emotional state. The detailed configuration and specific operation of the system will be described below.

[0240] The server first collects the CEO's quotes and ideas, for example by scraping the website or by retrieving information from a database via an API. The collected data is stored in text format and then preprocessed. Preprocessing includes tokenization and stop word removal, and is performed using a natural language processing library (e.g., nltk).

[0241] Next, an artificial intelligence model (e.g., GPT-2) is trained using the preprocessed data. The training process uses a large amount of high-quality text data, allowing the model to effectively learn patterns, which improves its ability to generate new text.

[0242] When a user wants to get a new idea, they send a specific prompt from their device to the server. For example, it may contain specific instructions such as "Think of an idea for a new project. The goal is to expand the market." Based on this prompt, the emotion engine recognizes emotions from the user's input text. Using natural language processing techniques, the emotion engine analyzes the emotional state of the input text and determines states such as "relaxed" or "tense."

[0243] The server then adjusts the generated ideas based on the recognized emotion data. This can include changing the tone or specific content of the generated text. For example, if the user is nervous, the server might generate ideas that include words of encouragement or support. The generated ideas are then sent back to the user's device for review.

[0244] As a concrete example, if a user inputs the prompt "I would like to think of a new initiative to expand our current market. Competition is intensifying, and I feel a little nervous," the emotion engine will recognize the emotion of "tension" and ultimately generate an idea such as "To expand our market, we recommend introducing a new product line and formulating a comprehensive strategy to deal with the intensifying competition. In the process, we should also introduce refreshing activities to increase employee motivation." In this way, the system can provide appropriate ideas that take into account the user's emotional state.

[0245] The required hardware is a server with a high-performance processor (e.g., GPU) and sufficient memory, and the required software is Python, a natural language processing library (e.g., transformers, nltk), and a machine learning framework (e.g., PyTorch).

[0246] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0247] Step 1:

[0248] The server collects CEO quotes and ideas. The collection method is to use techniques such as scraping data from websites and retrieving information from databases via APIs. This step requires website URLs and database API endpoints as input, and generates text data as output.

[0249] Step 2:

[0250] The server preprocesses the collected data. Specifically, it tokenizes the text and removes stop words using a natural language processing library (e.g., nltk). The input of this step is the text data collected in step 1, and the output is the tokenized, clean text data.

[0251] Step 3:

[0252] The server uses the preprocessed data to train an artificial intelligence model (e.g., GPT-2) using a machine learning framework (e.g., PyTorch). The input required is the preprocessed tokenized text data, and the output generated is a trained model.

[0253] Step 4:

[0254] To get new ideas, the user sends a prompt from their terminal to the server. A specific prompt might be, "Let's think of an idea for a new project. The goal is to expand the market." The input for this step is the user's prompt, and the output is the prompt sent to the server.

[0255] Step 5:

[0256] The server recognizes the emotion from the user's prompt. It uses an emotion engine to analyze the text and evaluate the emotional state. The input of this step is the prompt, and the output is the emotional state (e.g., "tense" or "relaxed").

[0257] Step 6:

[0258] The server adjusts the generated ideas based on the recognized emotion data. It uses a generative AI model (e.g., GPT-2) to generate emotion-based ideas. The input for this step is the prompt and emotion data, and the output is the adjusted idea.

[0259] Step 7:

[0260] The server sends the generated ideas back to the user's terminal. The input of this step is the adjusted ideas, and the output is the ideas displayed on the user's terminal.

[0261] Step 8:

[0262] The user confirms the idea sent to the terminal and receives guidance on the next step. The input of this step is the idea displayed on the terminal, and the output is the user's confirmation of the idea and feedback.

[0263] 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.

[0264] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0265] 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.

[0266] [Second embodiment]

[0267] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0268] 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.

[0269] 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).

[0270] 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.

[0271] 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.

[0272] 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).

[0273] 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.

[0274] 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.

[0275] 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.

[0276] 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.

[0277] 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.

[0278] 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."

[0279] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. The following describes the system configuration and its specific operation.

[0280] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0281] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0282] The server then uses the preprocessed data to train an artificial intelligence model. This training method uses machine learning algorithms to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns to improve the model's ability to generate new text.

[0283] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0284] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0285] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0286] The processing flow will be explained below.

[0287] Understood. The program's processing will be explained in the following format, divided into steps.

[0288] Step 1:

[0289] The server sends an HTTP request from the specified URL list to retrieve data including the CEO's quotes and ideas. The retrieved data is saved in JSON format or similar.

[0290] Step 2:

[0291] The server preprocesses the collected data by extracting and combining text parts from the data, tokenizing the text into words, and removing frequent stop words to make it easier to analyze.

[0292] Step 3:

[0293] The server trains an artificial intelligence model (e.g., GPT-2) using the preprocessed text data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters.

[0294] Step 4:

[0295] A user sends a request to the server by entering a specific prompt from a terminal, which is text containing instructions or questions about a new idea or proposal.

[0296] Step 5:

[0297] The server tokenizes the input prompt and converts it into a generative tensor, which is then passed to a trained artificial intelligence model, which is then instructed to generate text up to a specified maximum length.

[0298] Step 6:

[0299] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0300] Step 7:

[0301] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0302] These are the specific processing steps of the program. Through these steps, users can efficiently generate new ideas and use them in business proposal materials, etc.

[0303] Example 1

[0304] 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."

[0305] Conventional idea generation systems have struggled to efficiently collect CEO quotes and ideas and generate new ideas based on them. This process requires multiple steps, such as collecting data from websites, retrieving ideas from databases, and preprocessing text, which can be labor-intensive and time-consuming when done manually. Furthermore, the quality of the generated ideas is unstable, resulting in insufficient compatibility with user needs. This has led to a need for more efficient idea generation processes within companies.

[0306] 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.

[0307] In this invention, the server includes means for scraping CEO quotes and ideas from a website, means for retrieving quotes and ideas from a database using an API, means for storing the collected data in the database, means for preprocessing the collected data, means for tokenizing the preprocessed data and removing stop words, means for normalizing the preprocessed data, means for training an AI model using the preprocessed data, and means for generating ideas based on user prompts using the trained AI model. This enables high-quality ideas to be generated quickly based on user-entered prompts. Furthermore, the preprocessing of collected data and the AI ​​model training process are automated, significantly reducing labor and time. Furthermore, the generated ideas are more tailored to user needs, contributing to the efficiency of the idea generation process within a company.

[0308] "CEO quotes and ideas" refers to statements, thoughts, strategies, visions, etc. announced by a company's chief executive officer.

[0309] "Website scraping" refers to techniques and methods for automatically obtaining information from specific web pages using a program.

[0310] "Means of obtaining comments and ideas from a database using an API" refers to the technology or method of using an application programming interface to access a specific database and obtain the required information.

[0311] "Means for storing collected data in a database" refers to the techniques and methods for storing acquired or collected data in a database in an appropriate format.

[0312] "Means for preprocessing collected data" refers to the processing carried out before data analysis, and refers to techniques and methods for formatting, cleaning, standardizing, etc. of data.

[0313] "Means for tokenizing preprocessed data and removing stop words" refers to techniques and methods for splitting text data into words or phrases and removing unnecessary common words.

[0314] "Means for normalizing preprocessed data" refers to techniques or methods for maintaining consistency in preprocessed data, such as converting to all lowercase and removing special characters and unnecessary whitespace.

[0315] "Methods for training artificial intelligence models using preprocessed data" refers to techniques and methods that use organized data to train machine learning algorithms or artificial intelligence models and improve their performance.

[0316] "Means for generating ideas based on user prompts using a trained artificial intelligence model" refers to technologies and methods that use a pre-trained artificial intelligence model to automatically generate new ideas or text in response to specified input (prompts) from a user.

[0317] "Means for analyzing the generated ideas and returning them to the user's device" refers to the technology or method for analyzing automatically generated ideas and sending the results to the device used by the user.

[0318] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects quotes and ideas from top executives of a company, trains an artificial intelligence model based on the collected ideas, and generates new ideas in response to user prompts. The system configuration and its specific operation are described below.

[0319] First, the server scrapes corporate leaders' quotes and ideas from their websites. It uses Python libraries such as BeautifulSoup and Selenium to automatically extract data from specific web pages. This allows the leaders' past quotes and ideas to be collected as text data.

[0320] The server then uses an API to retrieve the comments and ideas from the database. It uses an application programming interface, such as Firebase or Google Sheets API, to pull the required information from the database. This process integrates data from multiple sources.

[0321] The collected data is stored by the server in a database using a database management system such as SQLite or MySQL, and the data is organized in a suitable format so that it can be used efficiently in subsequent processing steps.

[0322] Next, the server preprocesses the collected data. This includes tokenizing the text data, removing stop words, and normalizing the data. Specifically, it uses Python's NLTK (Natural Language Toolkit) and Spacy to tokenize and remove frequent meaningless words (stop words). It also converts all data to lowercase and removes special characters and unnecessary whitespace to create a consistent dataset.

[0323] The preprocessed data is then used to train an artificial intelligence model. Machine learning libraries such as TensorFlow and PyTorch are used to train the model on the data. The server splits the dataset into training and validation sets and trains them over multiple epochs (training cycles), optimizing the model's performance.

[0324] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter a prompt like, "Let's think of an idea for a new project. The goal is to expand the market." The server receives this prompt and analyzes it as text data. Using the preprocessed data, a trained artificial intelligence model generates new ideas.

[0325] Finally, the generated ideas are sent back from the server to the device, where the user can review the new ideas and modify or adopt them as necessary. This process allows users to quickly and efficiently obtain new ideas and suggestions.

[0326] Let's take a concrete example. When a user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market," the server generates an idea such as "Introduce digital marketing to our existing product line to expand the market" and sends it back to the device. In this way, users can easily come up with original ideas simply by inputting a prompt.

[0327] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0328] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0329] Step 1: Collect data

[0330] The server collects quotes and ideas from the CEO. The server runs scripts written in Python and uses BeautifulSoup and Selenium to scrape data from specific websites. The server also retrieves quotes and ideas from a database using Firebase and Google Sheets APIs. The input for this step is the website URL and database query, and the output is text data. Specifically, it parses the HTML source of the webpage and extracts the required information. It also sends API requests and organizes the returned data.

[0331] Step 2: Save your data

[0332] The text data collected by the server is saved in a database. The database management systems used are SQLite and MySQL. The input is the text data collected in step 1, and the output is the data stored in the database. Specifically, the process connects to the database, creates a table, and inserts data.

[0333] Step 3: Preprocessing the data

[0334] The server preprocesses the data. It uses Python's NLTK or Spacy to tokenize the collected text data and remove stop words. It also normalizes the data. The input is the raw data saved in step 2, and the output is the preprocessed, clean data. Specifically, it splits the text into words, removes unnecessary words, and converts all text to lowercase.

[0335] Step 4: Training the AI ​​model

[0336] The server uses the preprocessed data to train an artificial intelligence model. Using TensorFlow or PyTorch, a large amount of text data is input and the model is trained. The input is the data preprocessed in step 3, and the output is the trained model. Specifically, the data is divided into training and validation data, and the model is trained over multiple epochs.

[0337] Step 5: Receiving the prompt

[0338] When a user wants to get a new idea, they send a specific prompt from their terminal to the server. The input is the prompt entered by the user, and the output is the data sent to the server. For example, a user might enter the prompt "Let's think of an idea for a new project. The goal is to expand the market." The specific operation is to enter the prompt into a form on the terminal and click the send button.

[0339] Step 6: Idea generation

[0340] Based on the prompt received by the server, a trained artificial intelligence model is used to generate new ideas. The input is the user's prompt and the trained model, and the output is the generated idea. Specifically, the prompt is input into the model and new text related to it is generated.

[0341] Step 7: Return and view your ideas

[0342] The server sends the generated idea back to the user's terminal, where the user confirms it. The input is the idea generated in step 6, and the output is the text displayed on the user's terminal. Specifically, the server sends the generated idea as an HTTP response, and the text is displayed in the browser.

[0343] (Application example 1)

[0344] 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."

[0345] In order to improve factory productivity, it is essential to quickly adopt new technologies and ideas. However, it takes a lot of time and effort for on-site engineers and managers to collect the necessary information and take appropriate measures. Furthermore, there is no system in place to effectively utilize the CEO's opinions and past ideas, which means that the knowledge of the entire organization cannot be fully utilized.

[0346] 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.

[0347] In this invention, the server includes a means for collecting CEO quotes and ideas, a means for preprocessing the collected data, a means for training a generative artificial intelligence model using the preprocessed data, a means for generating ideas based on user prompts, and a means for transmitting the generated ideas to robots in the factory, thereby enabling factory engineers and managers to quickly adopt new technologies and measures and effectively utilize knowledge from the entire organization.

[0348] A "CEO" is the highest-ranking executive who, as the chief executive officer, determines the company's management policies and formulates and implements the company's strategies.

[0349] A "quote" is a statement made or recorded by a specific individual in the past.

[0350] An "idea" is an original thought or proposal for solving a particular problem.

[0351] "Collection methods" refer to the methods and techniques used to obtain and store data from a particular source.

[0352] "Preprocessing means" refers to methods and techniques for processing collected data to prepare it in a form suitable for analysis and learning.

[0353] A "generative artificial intelligence model" is an artificial intelligence system that is trained using machine learning algorithms and has the ability to generate new information.

[0354] A "prompt" is a question or instruction that a user enters to give instructions to an artificial intelligence model.

[0355] "Generative means" refers to the methods or techniques by which an AI model generates new text or ideas in response to input prompts.

[0356] "Factory robots" are autonomous mechanical devices used to automate production lines and factory operations.

[0357] A "user terminal" is a device through which a user can input or output information, such as a computing device such as a smartphone or tablet.

[0358] This invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. This system is particularly useful for quickly acquiring and implementing new technologies and improvements for factory robots. The system configuration and specific operation are described below.

[0359] First, the server collects the CEO's quotes and ideas. The collection method uses algorithms and APIs to obtain and store data from specific sources. Specifically, this can involve techniques such as scraping data from websites or retrieving information from databases via APIs. This allows the CEO's past statements and ideas to be collected as text data.

[0360] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a preprocessing method, natural language processing (NLP) libraries such as SpaCy and NLTK are used to prepare the data in a format that is easy to analyze. Tokenization divides sentences into words and removes frequent meaningless words (stop words), making the data easier to analyze.

[0361] The server then uses the preprocessed data to train a generative AI model. The training method involves using machine learning algorithms such as OpenAI's GPT-4 to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0362] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter specific instructions such as, "Tell me how to improve the efficiency of a new production line" or "Please provide me with a new idea to reduce manufacturing costs." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0363] The generated ideas are sent from the server to robots and terminals in the factory, where users can check them. The robots in the factory present the generated ideas to managers by reading them out loud or displaying them on a screen. This allows users to quickly and efficiently obtain new ideas and suggestions. For example, specific ideas such as "To improve the efficiency of the production line, we will introduce automation technology and optimize the coordination of each process" and "To reduce manufacturing costs, it is effective to introduce energy-efficient equipment and promote resource recycling" are generated.

[0364] The above is a specific embodiment for carrying out the present invention. The roles and functions of the server, terminal, and user allow users to easily come up with new ideas and increase factory productivity.

[0365] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0366] Step 1:

[0367] The server retrieves and stores data from a specific source using a method to collect CEO quotes and ideas, such as scraping data from a website or pulling information from a database via an API. The input for this step is a specific source URL or API endpoint, and the output is the collected text data.

[0368] Step 2:

[0369] The server preprocesses the collected data using a natural language processing (NLP) library. The libraries used are SpaCy and NLTK. Specifically, the collected text data is tokenized and stop words are removed. The input of this step is the collected text data, and the output is the preprocessed tokenized data.

[0370] Step 3:

[0371] The server uses the preprocessed data to train a generative AI model. The algorithm used is a machine learning model such as OpenAI's GPT-4. Specifically, the model takes tokenized data as input and learns its patterns to improve its ability to generate new text. The input for this step is preprocessed tokenized data, and the output is a trained generative AI model.

[0372] Step 4:

[0373] A user uses a terminal to send a prompt to the server to get new ideas. Specifically, the user inputs a prompt such as "Please tell me a new method to improve the efficiency of the production line" or "Please provide me with a new idea to reduce manufacturing costs." The input of this step is the user's prompt, and the output is the transmission of the prompt to the server.

[0374] Step 5:

[0375] The server receives prompts from users and generates ideas using a trained generative AI model. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text. The input for this step is the prompt sent by the user, and the output is the generated idea text.

[0376] Step 6:

[0377] The server sends the generated ideas to the robots and terminals in the factory. Specifically, the generated text is read aloud or sent to the robots to be displayed on a display. The input of this step is the generated idea text, and the output is the specific idea displayed on the robots and terminals.

[0378] Step 7:

[0379] The user checks the generated ideas through the terminal or the robot and takes appropriate measures. The input of this step is the text of the ideas displayed on the robot and the terminal, and the output is the user's utilization of the ideas.

[0380] The above is the specific process flow for implementing the invention. This system allows users to quickly and efficiently adopt new technologies and solutions.

[0381] 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.

[0382] The following describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on the collected data, and generates ideas based on user prompts, with an emotion engine that recognizes the user's emotions. The following describes the system configuration and its specific operation.

[0383] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0384] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0385] The server then uses the preprocessed data to train an artificial intelligence model (such as GPT-2). This training method uses a machine learning algorithm to train a large amount of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0386] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0387] This is where the emotion engine comes in, recognizing emotions from the user's input prompt. The emotion engine analyzes the text in the user's prompt and evaluates their emotional state. For example, it can determine if the user is nervous or relaxed.

[0388] The server adjusts the generated ideas based on the emotions recognized by the emotion engine, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is feeling nervous, the server may generate ideas containing encouraging words.

[0389] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0390] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0391] The processing flow will be explained below.

[0392] Understood. As an embodiment of the invention, the process flow will be described in detail in the following format.

[0393] Step 1:

[0394] The server sends HTTP requests from a specified URL list to collect the CEO's quotes and ideas. The collected data is saved in JSON format.

[0395] Step 2:

[0396] The server preprocesses the collected data. Specifically, it extracts and combines text parts from the data. It also tokenizes the text data into words and removes stop words, making it easier to analyze.

[0397] Step 3:

[0398] The server trains an artificial intelligence model using the preprocessed data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters, thereby improving the model's ability to generate new text.

[0399] Step 4:

[0400] A user inputs a specific prompt from a terminal and sends a request to the server. For example, the user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market."

[0401] Step 5:

[0402] The server tokenizes the input prompt and converts it into tensor data for generation. The emotion engine analyzes the prompt text and recognizes the user's emotion. For example, it determines whether the user is "excited" or "nervous" from the prompt text.

[0403] Step 6:

[0404] The server inputs the trained AI model with the emotional information recognized by the emotion engine, which allows the generated ideas to be optimized for the user's emotional state.

[0405] Step 7:

[0406] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0407] Step 8:

[0408] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0409] For example, if a user inputs the prompt "Let's think of a new project idea with the goal of market expansion," the server uses the emotion engine to recognize that the user's emotion is "excited." Based on this, the AI ​​model generates ideas such as "Introduce digital marketing to existing product lines to target new customer segments in order to expand the market" and sends them back to the user in an encouraging and hopeful tone.

[0410] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0411] Example 2

[0412] 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."

[0413] Conventional systems were unable to efficiently collect the CEO's knowledge and ideas and then effectively generate useful ideas for users based on them. Furthermore, the generated ideas were not adapted to the user's emotional state, resulting in low user satisfaction and effectiveness. Furthermore, there was a lack of a way to quickly and reliably deliver the generated ideas to the user's device.

[0414] 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.

[0415] In this invention, the server includes means for collecting CEO quotes and ideas, means for tokenizing the collected data and removing stop words and preprocessing the data, means for training a generative artificial intelligence model using the preprocessed data, means for generating ideas based on user prompts, means for performing sentiment analysis and adjusting the generated ideas based on the results, and means for returning the generated ideas to the user's terminal. This makes it possible to efficiently generate useful ideas while taking the user's sentiment into consideration and quickly and reliably provide them to the user's terminal.

[0416] "Means for collecting CEO quotes and ideas" refers to technology that obtains past statements and ideas of a company's chief executive officer (CEO) from various sources and stores them in a database.

[0417] "Tokenization" refers to the process of dividing text data into words, sentences, and other semantic units.

[0418] "Stop word removal" refers to a technique for removing meaningless words (such as "the" and "and") that are frequent but not very useful for analysis from text.

[0419] "Preprocessing methods" refers to a series of operations (e.g., tokenization, stop word removal, normalization, etc.) performed on collected data to make it easier for machine learning models to process.

[0420] A "generative artificial intelligence model" refers to a machine learning model that has been trained on a large amount of data in advance and is capable of generating new text based on given prompts.

[0421] "Sentiment analysis" refers to the technology of evaluating and classifying emotions and emotional states contained in text data.

[0422] "Means for generating ideas" refers to a technology that uses a pre-trained generative artificial intelligence model to generate new ideas based on user-entered prompts.

[0423] "Means for adjusting ideas" refers to a technology that adapts the tone and content of generated ideas to the user's emotional state based on the results of sentiment analysis.

[0424] "Means for sending back to the user's terminal" refers to technology that sends the generated ideas to the user's computing device so that they can be viewed.

[0425] This section describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains a generative AI model based on the collected data, and generates ideas based on user prompts, with emotion analysis technology that recognizes user emotions. The following describes the system configuration and its specific operation.

[0426] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, web scraping technology (BeautifulSoup or Scrapy) can be used to collect text data from interviews and speeches. Another method is to retrieve the CEO's past statements from a company's internal database via API.

[0427] The server then preprocesses the collected data, which includes tokenization and stop word removal. Natural language processing libraries (such as NLTK and SpaCy) are used to split the text into words and remove stop words, making the data easier to analyze.

[0428] The server then uses the preprocessed data to train a generative artificial intelligence model. The model used is GPT-2. Hugging Face's Transformers library is used to train the model using the preprocessed data. This process trains the model using a large amount of text data, improving its ability to generate new text.

[0429] When a user wants to get new ideas, they send a specific prompt from their device to the server, for example, "Think of an idea for a new project. The goal is to expand the market." This prompt is sent to the server and parsed using a tokenizer.

[0430] This is where sentiment analysis technology comes in, recognizing emotions from the user's prompts. The server uses sentiment analysis tools (such as IBM Watson or Hume AI) to analyze the text in the user's prompts and assess their emotional state. For example, it can identify when the user is tense or relaxed.

[0431] The server then adjusts the generated ideas based on the emotions recognized through emotion analysis, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is nervous, the server generates ideas containing encouraging words.

[0432] Finally, the generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. As a specific example, an idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. Users can easily generate original ideas by simply entering prompts.

[0433] This system will be an effective means of streamlining idea generation within a company, making extensive use of leaders' knowledge, and enabling ideas to be provided that take into consideration users' emotions.

[0434] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0435] Step 1:

[0436] The server collects CEO quotes and ideas. The input is the URL of a specific website or database. The server uses web scraping technology (BeautifulSoup or Scrapy) to obtain the data and save it in text format. Specifically, the server accesses the website, parses the HTML document, and extracts the required text data.

[0437] Input: URL, API endpoint

[0438] Output: Text data (CEO quotes and ideas)

[0439] Step 2:

[0440] The server preprocesses the collected text data. First, the collected text is tokenized. Next, stop words are removed. To do this, a natural language processing library (NLTK or SpaCy) is used. Specifically, the text is divided into words and words with high frequency but low information content are filtered out.

[0441] Input: Text data

[0442] Output: Preprocessed text data (tokenized and stop words removed)

[0443] Step 3:

[0444] The server uses the preprocessed text data to train a generative artificial intelligence model. The model used is GPT-2. Using Hugging Face's Transformers library, the preprocessed data is fed to the model, which is trained over multiple epochs. Specifically, a training dataset is prepared, and the model's training parameters are set and run.

[0445] Input: Preprocessed text data

[0446] Output: A trained generative artificial intelligence model

[0447] Step 4:

[0448] The user inputs a prompt for a new idea from the terminal and sends it to the server. For example, the user inputs the instruction "Let's think of an idea for a new project. The goal is to expand the market," and clicks the send button.

[0449] Input: User prompt

[0450] Output: Send prompt to server

[0451] Step 5:

[0452] The server passes the prompt received to a sentiment analysis engine for analysis. The sentiment analysis engine uses IBM Watson or Hume AI. This evaluates the emotional state of the text contained in the prompt. Specifically, it obtains an emotional score and an emotional label.

[0453] Input: User prompt

[0454] Output: Sentiment analysis results (sentiment score, emotion label)

[0455] Step 6:

[0456] The server uses a generative artificial intelligence model to generate ideas based on the results of sentiment analysis and user prompts. The tone and content of the generated ideas are adjusted depending on the results of sentiment analysis. For example, if the prompt "Let's think of an idea for a new project. The goal is to expand the market," and the user feels nervous, the server will generate an idea that includes encouraging words.

[0457] Input: User prompt, sentiment analysis results

[0458] Output: Generated ideas

[0459] Step 7:

[0460] The server sends the generated ideas back to the terminal so that the user can review them. Specifically, the generated ideas are displayed in text format on the user's screen. An idea such as "Introduce digital marketing to existing product lines to expand the market" is displayed.

[0461] Input: Generated ideas

[0462] Output: The idea displayed on the user's device

[0463] Through each of the above processing steps, the system can efficiently generate and quickly provide useful ideas while taking into consideration the user's emotional state.

[0464] (Application example 2)

[0465] 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."

[0466] In idea generation systems using artificial intelligence, there is a need for a method that appropriately reflects the user's emotional state and provides specific and optimal ideas that are suited to the user's purpose and situation. In such systems, the user experience can be improved by dynamically adjusting the tone and content of the ideas generated based on the user's emotions, but the specific means for achieving this have been unclear.

[0467] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0468] In this invention, the server includes means for collecting CEO quotes and ideas, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for recognizing emotions from user input text, means for adjusting generated ideas based on the recognized emotion data, and means for optimizing the tone and content of the generated ideas, thereby enabling the server to accurately grasp the user's emotional state and quickly provide optimal ideas corresponding to that state.

[0469] "Quotations" refers to the content or records of past statements made by a specific person or group.

[0470] "Idea" refers to creative thoughts such as new ideas, plans, and strategies.

[0471] "Collection" refers to the act of gathering necessary data or information using specific means.

[0472] "Preprocessing" refers to a series of tasks that involve formatting data and removing unnecessary elements in order to improve the efficiency of data analysis and machine learning.

[0473] "Artificial intelligence model" refers to a computational model designed to learn from collected data and provide appropriate outputs based on new data.

[0474] "User" refers to an individual or corporation that uses a system or application.

[0475] A "prompt" refers to a sentence of instructions or questions that a user inputs to a system.

[0476] "Emotions" refer to psychological states such as joy, sadness, and anger that people experience.

[0477] "Recognition" refers to understanding and identifying specific patterns or meanings from data or information.

[0478] "Data" refers to facts, measurements, or records obtained from a particular source.

[0479] "Tone" refers to the mood, attitude, and style of a piece of writing or speech.

[0480] As an embodiment of the present invention, a system that incorporates emotion recognition and generates optimal ideas in response to user prompts will be described. This system efficiently collects CEO quotes and past ideas, trains an AI model using the collected data, and generates ideas that correspond to the user's emotional state. The detailed configuration and specific operation of the system will be described below.

[0481] The server first collects the CEO's quotes and ideas, for example by scraping the website or by retrieving information from a database via an API. The collected data is stored in text format and then preprocessed. Preprocessing includes tokenization and stop word removal, and is performed using a natural language processing library (e.g., nltk).

[0482] Next, an artificial intelligence model (e.g., GPT-2) is trained using the preprocessed data. The training process uses a large amount of high-quality text data, allowing the model to effectively learn patterns, which improves its ability to generate new text.

[0483] When a user wants to get a new idea, they send a specific prompt from their device to the server. For example, it may contain specific instructions such as "Think of an idea for a new project. The goal is to expand the market." Based on this prompt, the emotion engine recognizes emotions from the user's input text. Using natural language processing techniques, the emotion engine analyzes the emotional state of the input text and determines states such as "relaxed" or "tense."

[0484] The server then adjusts the generated ideas based on the recognized emotion data. This can include changing the tone or specific content of the generated text. For example, if the user is nervous, the server might generate ideas that include words of encouragement or support. The generated ideas are then sent back to the user's device for review.

[0485] As a concrete example, if a user inputs the prompt "I would like to think of a new initiative to expand our current market. Competition is intensifying, and I feel a little nervous," the emotion engine will recognize the emotion of "tension" and ultimately generate an idea such as "To expand our market, we recommend introducing a new product line and formulating a comprehensive strategy to deal with the intensifying competition. In the process, we should also introduce refreshing activities to increase employee motivation." In this way, the system can provide appropriate ideas that take into account the user's emotional state.

[0486] The required hardware is a server with a high-performance processor (e.g., GPU) and sufficient memory, and the required software is Python, a natural language processing library (e.g., transformers, nltk), and a machine learning framework (e.g., PyTorch).

[0487] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0488] Step 1:

[0489] The server collects CEO quotes and ideas. The collection method is to use techniques such as scraping data from websites and retrieving information from databases via APIs. This step requires website URLs and database API endpoints as input, and generates text data as output.

[0490] Step 2:

[0491] The server preprocesses the collected data. Specifically, it tokenizes the text and removes stop words using a natural language processing library (e.g., nltk). The input of this step is the text data collected in step 1, and the output is the tokenized, clean text data.

[0492] Step 3:

[0493] The server uses the preprocessed data to train an artificial intelligence model (e.g., GPT-2) using a machine learning framework (e.g., PyTorch). The input required is the preprocessed tokenized text data, and the output generated is a trained model.

[0494] Step 4:

[0495] To get new ideas, the user sends a prompt from their terminal to the server. A specific prompt might be, "Let's think of an idea for a new project. The goal is to expand the market." The input for this step is the user's prompt, and the output is the prompt sent to the server.

[0496] Step 5:

[0497] The server recognizes the emotion from the user's prompt. It uses an emotion engine to analyze the text and evaluate the emotional state. The input of this step is the prompt, and the output is the emotional state (e.g., "tense" or "relaxed").

[0498] Step 6:

[0499] The server adjusts the generated ideas based on the recognized emotion data. It uses a generative AI model (e.g., GPT-2) to generate emotion-based ideas. The input for this step is the prompt and emotion data, and the output is the adjusted idea.

[0500] Step 7:

[0501] The server sends the generated ideas back to the user's terminal. The input of this step is the adjusted ideas, and the output is the ideas displayed on the user's terminal.

[0502] Step 8:

[0503] The user confirms the idea sent to the terminal and receives guidance on the next step. The input of this step is the idea displayed on the terminal, and the output is the user's confirmation of the idea and feedback.

[0504] 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.

[0505] 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.

[0506] 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.

[0507] [Third embodiment]

[0508] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0509] 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.

[0510] 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).

[0511] 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.

[0512] 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.

[0513] 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).

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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.

[0518] 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.

[0519] 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."

[0520] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. The following describes the system configuration and its specific operation.

[0521] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0522] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0523] The server then uses the preprocessed data to train an artificial intelligence model. This training method uses machine learning algorithms to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns to improve the model's ability to generate new text.

[0524] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0525] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0526] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0527] The processing flow will be explained below.

[0528] Understood. The program's processing will be explained in the following format, divided into steps.

[0529] Step 1:

[0530] The server sends an HTTP request from the specified URL list to retrieve data including the CEO's quotes and ideas. The retrieved data is saved in JSON format or similar.

[0531] Step 2:

[0532] The server preprocesses the collected data by extracting and combining text parts from the data, tokenizing the text into words, and removing frequent stop words to make it easier to analyze.

[0533] Step 3:

[0534] The server trains an artificial intelligence model (e.g., GPT-2) using the preprocessed text data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters.

[0535] Step 4:

[0536] A user sends a request to the server by entering a specific prompt from a terminal, which is text containing instructions or questions about a new idea or proposal.

[0537] Step 5:

[0538] The server tokenizes the input prompt and converts it into a generative tensor, which is then passed to a trained artificial intelligence model, which is then instructed to generate text up to a specified maximum length.

[0539] Step 6:

[0540] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0541] Step 7:

[0542] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0543] These are the specific processing steps of the program. Through these steps, users can efficiently generate new ideas and use them in business proposal materials, etc.

[0544] Example 1

[0545] 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."

[0546] Conventional idea generation systems have struggled to efficiently collect CEO quotes and ideas and generate new ideas based on them. This process requires multiple steps, such as collecting data from websites, retrieving ideas from databases, and preprocessing text, which can be labor-intensive and time-consuming when done manually. Furthermore, the quality of the generated ideas is unstable, resulting in insufficient compatibility with user needs. This has led to a need for more efficient idea generation processes within companies.

[0547] 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.

[0548] In this invention, the server includes means for scraping CEO quotes and ideas from a website, means for retrieving quotes and ideas from a database using an API, means for storing the collected data in the database, means for preprocessing the collected data, means for tokenizing the preprocessed data and removing stop words, means for normalizing the preprocessed data, means for training an AI model using the preprocessed data, and means for generating ideas based on user prompts using the trained AI model. This enables high-quality ideas to be generated quickly based on user-entered prompts. Furthermore, the preprocessing of collected data and the AI ​​model training process are automated, significantly reducing labor and time. Furthermore, the generated ideas are more tailored to user needs, contributing to the efficiency of the idea generation process within a company.

[0549] "CEO quotes and ideas" refers to statements, thoughts, strategies, visions, etc. announced by a company's chief executive officer.

[0550] "Website scraping" refers to techniques and methods for automatically obtaining information from specific web pages using a program.

[0551] "Means of obtaining comments and ideas from a database using an API" refers to the technology or method of using an application programming interface to access a specific database and obtain the required information.

[0552] "Means for storing collected data in a database" refers to the techniques and methods for storing acquired or collected data in a database in an appropriate format.

[0553] "Means for preprocessing collected data" refers to the processing carried out before data analysis, and refers to techniques and methods for formatting, cleaning, standardizing, etc. of data.

[0554] "Means for tokenizing preprocessed data and removing stop words" refers to techniques and methods for splitting text data into words or phrases and removing unnecessary common words.

[0555] "Means for normalizing preprocessed data" refers to techniques or methods for maintaining consistency in preprocessed data, such as converting to all lowercase and removing special characters and unnecessary whitespace.

[0556] "Methods for training artificial intelligence models using preprocessed data" refers to techniques and methods that use organized data to train machine learning algorithms or artificial intelligence models and improve their performance.

[0557] "Means for generating ideas based on user prompts using a trained artificial intelligence model" refers to technologies and methods that use a pre-trained artificial intelligence model to automatically generate new ideas or text in response to specified input (prompts) from a user.

[0558] "Means for analyzing the generated ideas and returning them to the user's device" refers to the technology or method for analyzing automatically generated ideas and sending the results to the device used by the user.

[0559] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects quotes and ideas from top executives of a company, trains an artificial intelligence model based on the collected ideas, and generates new ideas in response to user prompts. The system configuration and its specific operation are described below.

[0560] First, the server scrapes corporate leaders' quotes and ideas from their websites. It uses Python libraries such as BeautifulSoup and Selenium to automatically extract data from specific web pages. This allows the leaders' past quotes and ideas to be collected as text data.

[0561] The server then uses an API to retrieve the comments and ideas from the database. It uses an application programming interface, such as Firebase or Google Sheets API, to pull the required information from the database. This process integrates data from multiple sources.

[0562] The collected data is stored by the server in a database using a database management system such as SQLite or MySQL, and the data is organized in a suitable format so that it can be used efficiently in subsequent processing steps.

[0563] Next, the server preprocesses the collected data. This includes tokenizing the text data, removing stop words, and normalizing the data. Specifically, it uses Python's NLTK (Natural Language Toolkit) and Spacy to tokenize and remove frequent meaningless words (stop words). It also converts all data to lowercase and removes special characters and unnecessary whitespace to create a consistent dataset.

[0564] The preprocessed data is then used to train an artificial intelligence model. Machine learning libraries such as TensorFlow and PyTorch are used to train the model on the data. The server splits the dataset into training and validation sets and trains them over multiple epochs (training cycles), optimizing the model's performance.

[0565] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter a prompt like, "Let's think of an idea for a new project. The goal is to expand the market." The server receives this prompt and analyzes it as text data. Using the preprocessed data, a trained artificial intelligence model generates new ideas.

[0566] Finally, the generated ideas are sent back from the server to the device, where the user can review the new ideas and modify or adopt them as necessary. This process allows users to quickly and efficiently obtain new ideas and suggestions.

[0567] Let's take a concrete example. When a user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market," the server generates an idea such as "Introduce digital marketing to our existing product line to expand the market" and sends it back to the device. In this way, users can easily come up with original ideas simply by inputting a prompt.

[0568] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0569] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0570] Step 1: Collect data

[0571] The server collects quotes and ideas from the CEO. The server runs scripts written in Python and uses BeautifulSoup and Selenium to scrape data from specific websites. The server also retrieves quotes and ideas from a database using Firebase and Google Sheets APIs. The input for this step is the website URL and database query, and the output is text data. Specifically, it parses the HTML source of the webpage and extracts the required information. It also sends API requests and organizes the returned data.

[0572] Step 2: Save your data

[0573] The text data collected by the server is saved in a database. The database management systems used are SQLite and MySQL. The input is the text data collected in step 1, and the output is the data stored in the database. Specifically, the process connects to the database, creates a table, and inserts data.

[0574] Step 3: Preprocessing the data

[0575] The server preprocesses the data. It uses Python's NLTK or Spacy to tokenize the collected text data and remove stop words. It also normalizes the data. The input is the raw data saved in step 2, and the output is the preprocessed, clean data. Specifically, it splits the text into words, removes unnecessary words, and converts all text to lowercase.

[0576] Step 4: Training the AI ​​model

[0577] The server uses the preprocessed data to train an artificial intelligence model. Using TensorFlow or PyTorch, a large amount of text data is input and the model is trained. The input is the data preprocessed in step 3, and the output is the trained model. Specifically, the data is divided into training and validation data, and the model is trained over multiple epochs.

[0578] Step 5: Receiving the prompt

[0579] When a user wants to get a new idea, they send a specific prompt from their terminal to the server. The input is the prompt entered by the user, and the output is the data sent to the server. For example, a user might enter the prompt "Let's think of an idea for a new project. The goal is to expand the market." The specific operation is to enter the prompt into a form on the terminal and click the send button.

[0580] Step 6: Idea generation

[0581] Based on the prompt received by the server, a trained artificial intelligence model is used to generate new ideas. The input is the user's prompt and the trained model, and the output is the generated idea. Specifically, the prompt is input into the model and new text related to it is generated.

[0582] Step 7: Return and view your ideas

[0583] The server sends the generated idea back to the user's terminal, where the user confirms it. The input is the idea generated in step 6, and the output is the text displayed on the user's terminal. Specifically, the server sends the generated idea as an HTTP response, and the text is displayed in the browser.

[0584] (Application example 1)

[0585] 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."

[0586] In order to improve factory productivity, it is essential to quickly adopt new technologies and ideas. However, it takes a lot of time and effort for on-site engineers and managers to collect the necessary information and take appropriate measures. Furthermore, there is no system in place to effectively utilize the CEO's opinions and past ideas, which means that the knowledge of the entire organization cannot be fully utilized.

[0587] 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.

[0588] In this invention, the server includes a means for collecting CEO quotes and ideas, a means for preprocessing the collected data, a means for training a generative artificial intelligence model using the preprocessed data, a means for generating ideas based on user prompts, and a means for transmitting the generated ideas to robots in the factory, thereby enabling factory engineers and managers to quickly adopt new technologies and measures and effectively utilize knowledge from the entire organization.

[0589] A "CEO" is the highest-ranking executive who, as the chief executive officer, determines the company's management policies and formulates and implements the company's strategies.

[0590] A "quote" is a statement made or recorded by a specific individual in the past.

[0591] An "idea" is an original thought or proposal for solving a particular problem.

[0592] "Collection methods" refer to the methods and techniques used to obtain and store data from a particular source.

[0593] "Preprocessing means" refers to methods and techniques for processing collected data to prepare it in a form suitable for analysis and learning.

[0594] A "generative artificial intelligence model" is an artificial intelligence system that is trained using machine learning algorithms and has the ability to generate new information.

[0595] A "prompt" is a question or instruction that a user enters to give instructions to an artificial intelligence model.

[0596] "Generative means" refers to the methods or techniques by which an AI model generates new text or ideas in response to input prompts.

[0597] "Factory robots" are autonomous mechanical devices used to automate production lines and factory operations.

[0598] A "user terminal" is a device through which a user can input or output information, such as a computing device such as a smartphone or tablet.

[0599] This invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. This system is particularly useful for quickly acquiring and implementing new technologies and improvements for factory robots. The system configuration and specific operation are described below.

[0600] First, the server collects the CEO's quotes and ideas. The collection method uses algorithms and APIs to obtain and store data from specific sources. Specifically, this can involve techniques such as scraping data from websites or retrieving information from databases via APIs. This allows the CEO's past statements and ideas to be collected as text data.

[0601] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a preprocessing method, natural language processing (NLP) libraries such as SpaCy and NLTK are used to prepare the data in a format that is easy to analyze. Tokenization divides sentences into words and removes frequent meaningless words (stop words), making the data easier to analyze.

[0602] The server then uses the preprocessed data to train a generative AI model. The training method involves using machine learning algorithms such as OpenAI's GPT-4 to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0603] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter specific instructions such as, "Tell me how to improve the efficiency of a new production line" or "Please provide me with a new idea to reduce manufacturing costs." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0604] The generated ideas are sent from the server to robots and terminals in the factory, where users can check them. The robots in the factory present the generated ideas to managers by reading them out loud or displaying them on a screen. This allows users to quickly and efficiently obtain new ideas and suggestions. For example, specific ideas such as "To improve the efficiency of the production line, we will introduce automation technology and optimize the coordination of each process" and "To reduce manufacturing costs, it is effective to introduce energy-efficient equipment and promote resource recycling" are generated.

[0605] The above is a specific embodiment for carrying out the present invention. The roles and functions of the server, terminal, and user allow users to easily come up with new ideas and increase factory productivity.

[0606] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0607] Step 1:

[0608] The server retrieves and stores data from a specific source using a method to collect CEO quotes and ideas, such as scraping data from a website or pulling information from a database via an API. The input for this step is a specific source URL or API endpoint, and the output is the collected text data.

[0609] Step 2:

[0610] The server preprocesses the collected data using a natural language processing (NLP) library. The libraries used are SpaCy and NLTK. Specifically, the collected text data is tokenized and stop words are removed. The input of this step is the collected text data, and the output is the preprocessed tokenized data.

[0611] Step 3:

[0612] The server uses the preprocessed data to train a generative AI model. The algorithm used is a machine learning model such as OpenAI's GPT-4. Specifically, the model takes tokenized data as input and learns its patterns to improve its ability to generate new text. The input for this step is preprocessed tokenized data, and the output is a trained generative AI model.

[0613] Step 4:

[0614] A user uses a terminal to send a prompt to the server to get new ideas. Specifically, the user inputs a prompt such as "Please tell me a new method to improve the efficiency of the production line" or "Please provide me with a new idea to reduce manufacturing costs." The input of this step is the user's prompt, and the output is the transmission of the prompt to the server.

[0615] Step 5:

[0616] The server receives prompts from users and generates ideas using a trained generative AI model. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text. The input for this step is the prompt sent by the user, and the output is the generated idea text.

[0617] Step 6:

[0618] The server sends the generated ideas to the robots and terminals in the factory. Specifically, the generated text is read aloud or sent to the robots to be displayed on a display. The input of this step is the generated idea text, and the output is the specific idea displayed on the robots and terminals.

[0619] Step 7:

[0620] The user checks the generated ideas through the terminal or the robot and takes appropriate measures. The input of this step is the text of the ideas displayed on the robot and the terminal, and the output is the user's utilization of the ideas.

[0621] The above is the specific process flow for implementing the invention. This system allows users to quickly and efficiently adopt new technologies and solutions.

[0622] 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.

[0623] The following describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on the collected data, and generates ideas based on user prompts, with an emotion engine that recognizes the user's emotions. The following describes the system configuration and its specific operation.

[0624] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0625] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0626] The server then uses the preprocessed data to train an artificial intelligence model (such as GPT-2). This training method uses a machine learning algorithm to train a large amount of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0627] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0628] This is where the emotion engine comes in, recognizing emotions from the user's input prompt. The emotion engine analyzes the text in the user's prompt and evaluates their emotional state. For example, it can determine if the user is nervous or relaxed.

[0629] The server adjusts the generated ideas based on the emotions recognized by the emotion engine, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is feeling nervous, the server may generate ideas containing encouraging words.

[0630] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0631] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0632] The processing flow will be explained below.

[0633] Understood. As an embodiment of the invention, the process flow will be described in detail in the following format.

[0634] Step 1:

[0635] The server sends HTTP requests from a specified URL list to collect the CEO's quotes and ideas. The collected data is saved in JSON format.

[0636] Step 2:

[0637] The server preprocesses the collected data. Specifically, it extracts and combines text parts from the data. It also tokenizes the text data into words and removes stop words, making it easier to analyze.

[0638] Step 3:

[0639] The server trains an artificial intelligence model using the preprocessed data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters, thereby improving the model's ability to generate new text.

[0640] Step 4:

[0641] A user inputs a specific prompt from a terminal and sends a request to the server. For example, the user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market."

[0642] Step 5:

[0643] The server tokenizes the input prompt and converts it into tensor data for generation. The emotion engine analyzes the prompt text and recognizes the user's emotion. For example, it determines whether the user is "excited" or "nervous" from the prompt text.

[0644] Step 6:

[0645] The server inputs the trained AI model with the emotional information recognized by the emotion engine, which allows the generated ideas to be optimized for the user's emotional state.

[0646] Step 7:

[0647] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0648] Step 8:

[0649] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0650] For example, if a user inputs the prompt "Let's think of a new project idea with the goal of market expansion," the server uses the emotion engine to recognize that the user's emotion is "excited." Based on this, the AI ​​model generates ideas such as "Introduce digital marketing to existing product lines to target new customer segments in order to expand the market" and sends them back to the user in an encouraging and hopeful tone.

[0651] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0652] Example 2

[0653] 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."

[0654] Conventional systems were unable to efficiently collect the CEO's knowledge and ideas and then effectively generate useful ideas for users based on them. Furthermore, the generated ideas were not adapted to the user's emotional state, resulting in low user satisfaction and effectiveness. Furthermore, there was a lack of a way to quickly and reliably deliver the generated ideas to the user's device.

[0655] 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.

[0656] In this invention, the server includes means for collecting CEO quotes and ideas, means for tokenizing the collected data and removing stop words and preprocessing the data, means for training a generative artificial intelligence model using the preprocessed data, means for generating ideas based on user prompts, means for performing sentiment analysis and adjusting the generated ideas based on the results, and means for returning the generated ideas to the user's terminal. This makes it possible to efficiently generate useful ideas while taking the user's sentiment into consideration and quickly and reliably provide them to the user's terminal.

[0657] "Means for collecting CEO quotes and ideas" refers to technology that obtains past statements and ideas of a company's chief executive officer (CEO) from various sources and stores them in a database.

[0658] "Tokenization" refers to the process of dividing text data into words, sentences, and other semantic units.

[0659] "Stop word removal" refers to a technique for removing meaningless words (such as "the" and "and") that are frequent but not very useful for analysis from text.

[0660] "Preprocessing methods" refers to a series of operations (e.g., tokenization, stop word removal, normalization, etc.) performed on collected data to make it easier for machine learning models to process.

[0661] A "generative artificial intelligence model" refers to a machine learning model that has been trained on a large amount of data in advance and is capable of generating new text based on given prompts.

[0662] "Sentiment analysis" refers to the technology of evaluating and classifying emotions and emotional states contained in text data.

[0663] "Means for generating ideas" refers to a technology that uses a pre-trained generative artificial intelligence model to generate new ideas based on user-entered prompts.

[0664] "Means for adjusting ideas" refers to a technology that adapts the tone and content of generated ideas to the user's emotional state based on the results of sentiment analysis.

[0665] "Means for sending back to the user's terminal" refers to technology that sends the generated ideas to the user's computing device so that they can be viewed.

[0666] This section describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains a generative AI model based on the collected data, and generates ideas based on user prompts, with emotion analysis technology that recognizes user emotions. The following describes the system configuration and its specific operation.

[0667] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, web scraping technology (BeautifulSoup or Scrapy) can be used to collect text data from interviews and speeches. Another method is to retrieve the CEO's past statements from a company's internal database via API.

[0668] The server then preprocesses the collected data, which includes tokenization and stop word removal. Natural language processing libraries (such as NLTK and SpaCy) are used to split the text into words and remove stop words, making the data easier to analyze.

[0669] The server then uses the preprocessed data to train a generative artificial intelligence model. The model used is GPT-2. Hugging Face's Transformers library is used to train the model using the preprocessed data. This process trains the model using a large amount of text data, improving its ability to generate new text.

[0670] When a user wants to get new ideas, they send a specific prompt from their device to the server, for example, "Think of an idea for a new project. The goal is to expand the market." This prompt is sent to the server and parsed using a tokenizer.

[0671] This is where sentiment analysis technology comes in, recognizing emotions from the user's prompts. The server uses sentiment analysis tools (such as IBM Watson or Hume AI) to analyze the text in the user's prompts and assess their emotional state. For example, it can identify when the user is tense or relaxed.

[0672] The server then adjusts the generated ideas based on the emotions recognized through emotion analysis, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is nervous, the server generates ideas containing encouraging words.

[0673] Finally, the generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. As a specific example, an idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. Users can easily generate original ideas by simply entering prompts.

[0674] This system will be an effective means of streamlining idea generation within a company, making extensive use of leaders' knowledge, and enabling ideas to be provided that take into consideration users' emotions.

[0675] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0676] Step 1:

[0677] The server collects CEO quotes and ideas. The input is the URL of a specific website or database. The server uses web scraping technology (BeautifulSoup or Scrapy) to obtain the data and save it in text format. Specifically, the server accesses the website, parses the HTML document, and extracts the required text data.

[0678] Input: URL, API endpoint

[0679] Output: Text data (CEO quotes and ideas)

[0680] Step 2:

[0681] The server preprocesses the collected text data. First, the collected text is tokenized. Next, stop words are removed. To do this, a natural language processing library (NLTK or SpaCy) is used. Specifically, the text is divided into words and words with high frequency but low information content are filtered out.

[0682] Input: Text data

[0683] Output: Preprocessed text data (tokenized and stop words removed)

[0684] Step 3:

[0685] The server uses the preprocessed text data to train a generative artificial intelligence model. The model used is GPT-2. Using Hugging Face's Transformers library, the preprocessed data is fed to the model, which is trained over multiple epochs. Specifically, a training dataset is prepared, and the model's training parameters are set and run.

[0686] Input: Preprocessed text data

[0687] Output: A trained generative artificial intelligence model

[0688] Step 4:

[0689] The user inputs a prompt for a new idea from the terminal and sends it to the server. For example, the user inputs the instruction "Let's think of an idea for a new project. The goal is to expand the market," and clicks the send button.

[0690] Input: User prompt

[0691] Output: Send prompt to server

[0692] Step 5:

[0693] The server passes the prompt received to a sentiment analysis engine for analysis. The sentiment analysis engine uses IBM Watson or Hume AI. This evaluates the emotional state of the text contained in the prompt. Specifically, it obtains an emotional score and an emotional label.

[0694] Input: User prompt

[0695] Output: Sentiment analysis results (sentiment score, emotion label)

[0696] Step 6:

[0697] The server uses a generative artificial intelligence model to generate ideas based on the results of sentiment analysis and user prompts. The tone and content of the generated ideas are adjusted depending on the results of sentiment analysis. For example, if the prompt "Let's think of an idea for a new project. The goal is to expand the market," and the user feels nervous, the server will generate an idea that includes encouraging words.

[0698] Input: User prompt, sentiment analysis results

[0699] Output: Generated ideas

[0700] Step 7:

[0701] The server sends the generated ideas back to the terminal so that the user can review them. Specifically, the generated ideas are displayed in text format on the user's screen. An idea such as "Introduce digital marketing to existing product lines to expand the market" is displayed.

[0702] Input: Generated ideas

[0703] Output: The idea displayed on the user's device

[0704] Through each of the above processing steps, the system can efficiently generate and quickly provide useful ideas while taking into consideration the user's emotional state.

[0705] (Application example 2)

[0706] 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."

[0707] In idea generation systems using artificial intelligence, there is a need for a method that appropriately reflects the user's emotional state and provides specific and optimal ideas that are suited to the user's purpose and situation. In such systems, the user experience can be improved by dynamically adjusting the tone and content of the ideas generated based on the user's emotions, but the specific means for achieving this have been unclear.

[0708] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0709] In this invention, the server includes means for collecting CEO quotes and ideas, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for recognizing emotions from user input text, means for adjusting generated ideas based on the recognized emotion data, and means for optimizing the tone and content of the generated ideas, thereby enabling the server to accurately grasp the user's emotional state and quickly provide optimal ideas corresponding to that state.

[0710] "Quotations" refers to the content or records of past statements made by a specific person or group.

[0711] "Idea" refers to creative thoughts such as new ideas, plans, and strategies.

[0712] "Collection" refers to the act of gathering necessary data or information using specific means.

[0713] "Preprocessing" refers to a series of tasks that involve formatting data and removing unnecessary elements in order to improve the efficiency of data analysis and machine learning.

[0714] "Artificial intelligence model" refers to a computational model designed to learn from collected data and provide appropriate outputs based on new data.

[0715] "User" refers to an individual or corporation that uses a system or application.

[0716] A "prompt" refers to a sentence of instructions or questions that a user inputs to a system.

[0717] "Emotions" refer to psychological states such as joy, sadness, and anger that people experience.

[0718] "Recognition" refers to understanding and identifying specific patterns or meanings from data or information.

[0719] "Data" refers to facts, measurements, or records obtained from a particular source.

[0720] "Tone" refers to the mood, attitude, and style of a piece of writing or speech.

[0721] As an embodiment of the present invention, a system that incorporates emotion recognition and generates optimal ideas in response to user prompts will be described. This system efficiently collects CEO quotes and past ideas, trains an AI model using the collected data, and generates ideas that correspond to the user's emotional state. The detailed configuration and specific operation of the system will be described below.

[0722] The server first collects the CEO's quotes and ideas, for example by scraping the website or by retrieving information from a database via an API. The collected data is stored in text format and then preprocessed. Preprocessing includes tokenization and stop word removal, and is performed using a natural language processing library (e.g., nltk).

[0723] Next, an artificial intelligence model (e.g., GPT-2) is trained using the preprocessed data. The training process uses a large amount of high-quality text data, allowing the model to effectively learn patterns, which improves its ability to generate new text.

[0724] When a user wants to get a new idea, they send a specific prompt from their device to the server. For example, it may contain specific instructions such as "Think of an idea for a new project. The goal is to expand the market." Based on this prompt, the emotion engine recognizes emotions from the user's input text. Using natural language processing techniques, the emotion engine analyzes the emotional state of the input text and determines states such as "relaxed" or "tense."

[0725] The server then adjusts the generated ideas based on the recognized emotion data. This can include changing the tone or specific content of the generated text. For example, if the user is nervous, the server might generate ideas that include words of encouragement or support. The generated ideas are then sent back to the user's device for review.

[0726] As a concrete example, if a user inputs the prompt "I would like to think of a new initiative to expand our current market. Competition is intensifying, and I feel a little nervous," the emotion engine will recognize the emotion of "tension" and ultimately generate an idea such as "To expand our market, we recommend introducing a new product line and formulating a comprehensive strategy to deal with the intensifying competition. In the process, we should also introduce refreshing activities to increase employee motivation." In this way, the system can provide appropriate ideas that take into account the user's emotional state.

[0727] The required hardware is a server with a high-performance processor (e.g., GPU) and sufficient memory, and the required software is Python, a natural language processing library (e.g., transformers, nltk), and a machine learning framework (e.g., PyTorch).

[0728] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0729] Step 1:

[0730] The server collects CEO quotes and ideas. The collection method is to use techniques such as scraping data from websites and retrieving information from databases via APIs. This step requires website URLs and database API endpoints as input, and generates text data as output.

[0731] Step 2:

[0732] The server preprocesses the collected data. Specifically, it tokenizes the text and removes stop words using a natural language processing library (e.g., nltk). The input of this step is the text data collected in step 1, and the output is the tokenized, clean text data.

[0733] Step 3:

[0734] The server uses the preprocessed data to train an artificial intelligence model (e.g., GPT-2) using a machine learning framework (e.g., PyTorch). The input required is the preprocessed tokenized text data, and the output generated is a trained model.

[0735] Step 4:

[0736] To get new ideas, the user sends a prompt from their terminal to the server. A specific prompt might be, "Let's think of an idea for a new project. The goal is to expand the market." The input for this step is the user's prompt, and the output is the prompt sent to the server.

[0737] Step 5:

[0738] The server recognizes the emotion from the user's prompt. It uses an emotion engine to analyze the text and evaluate the emotional state. The input of this step is the prompt, and the output is the emotional state (e.g., "tense" or "relaxed").

[0739] Step 6:

[0740] The server adjusts the generated ideas based on the recognized emotion data. It uses a generative AI model (e.g., GPT-2) to generate emotion-based ideas. The input for this step is the prompt and emotion data, and the output is the adjusted idea.

[0741] Step 7:

[0742] The server sends the generated ideas back to the user's terminal. The input of this step is the adjusted ideas, and the output is the ideas displayed on the user's terminal.

[0743] Step 8:

[0744] The user confirms the idea sent to the terminal and receives guidance on the next step. The input of this step is the idea displayed on the terminal, and the output is the user's confirmation of the idea and feedback.

[0745] 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.

[0746] 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.

[0747] 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.

[0748] [Fourth embodiment]

[0749] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0750] 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.

[0751] 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).

[0752] 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.

[0753] 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.

[0754] 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).

[0755] 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.

[0756] 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.

[0757] 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.

[0758] 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.

[0759] 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.

[0760] 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.

[0761] 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."

[0762] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. The following describes the system configuration and its specific operation.

[0763] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0764] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0765] The server then uses the preprocessed data to train an artificial intelligence model. This training method uses machine learning algorithms to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns to improve the model's ability to generate new text.

[0766] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0767] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0768] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0769] The processing flow will be explained below.

[0770] Understood. The program's processing will be explained in the following format, divided into steps.

[0771] Step 1:

[0772] The server sends an HTTP request from the specified URL list to retrieve data including the CEO's quotes and ideas. The retrieved data is saved in JSON format or similar.

[0773] Step 2:

[0774] The server preprocesses the collected data by extracting and combining text parts from the data, tokenizing the text into words, and removing frequent stop words to make it easier to analyze.

[0775] Step 3:

[0776] The server trains an artificial intelligence model (e.g., GPT-2) using the preprocessed text data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters.

[0777] Step 4:

[0778] A user sends a request to the server by entering a specific prompt from a terminal, which is text containing instructions or questions about a new idea or proposal.

[0779] Step 5:

[0780] The server tokenizes the input prompt and converts it into a generative tensor, which is then passed to a trained artificial intelligence model, which is then instructed to generate text up to a specified maximum length.

[0781] Step 6:

[0782] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0783] Step 7:

[0784] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0785] These are the specific processing steps of the program. Through these steps, users can efficiently generate new ideas and use them in business proposal materials, etc.

[0786] Example 1

[0787] 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."

[0788] Conventional idea generation systems have struggled to efficiently collect CEO quotes and ideas and generate new ideas based on them. This process requires multiple steps, such as collecting data from websites, retrieving ideas from databases, and preprocessing text, which can be labor-intensive and time-consuming when done manually. Furthermore, the quality of the generated ideas is unstable, resulting in insufficient compatibility with user needs. This has led to a need for more efficient idea generation processes within companies.

[0789] 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.

[0790] In this invention, the server includes means for scraping CEO quotes and ideas from a website, means for retrieving quotes and ideas from a database using an API, means for storing the collected data in the database, means for preprocessing the collected data, means for tokenizing the preprocessed data and removing stop words, means for normalizing the preprocessed data, means for training an AI model using the preprocessed data, and means for generating ideas based on user prompts using the trained AI model. This enables high-quality ideas to be generated quickly based on user-entered prompts. Furthermore, the preprocessing of collected data and the AI ​​model training process are automated, significantly reducing labor and time. Furthermore, the generated ideas are more tailored to user needs, contributing to the efficiency of the idea generation process within a company.

[0791] "CEO quotes and ideas" refers to statements, thoughts, strategies, visions, etc. announced by a company's chief executive officer.

[0792] "Website scraping" refers to techniques and methods for automatically obtaining information from specific web pages using a program.

[0793] "Means of obtaining comments and ideas from a database using an API" refers to the technology or method of using an application programming interface to access a specific database and obtain the required information.

[0794] "Means for storing collected data in a database" refers to the techniques and methods for storing acquired or collected data in a database in an appropriate format.

[0795] "Means for preprocessing collected data" refers to the processing carried out before data analysis, and refers to techniques and methods for formatting, cleaning, standardizing, etc. of data.

[0796] "Means for tokenizing preprocessed data and removing stop words" refers to techniques and methods for splitting text data into words or phrases and removing unnecessary common words.

[0797] "Means for normalizing preprocessed data" refers to techniques or methods for maintaining consistency in preprocessed data, such as converting to all lowercase and removing special characters and unnecessary whitespace.

[0798] "Methods for training artificial intelligence models using preprocessed data" refers to techniques and methods that use organized data to train machine learning algorithms or artificial intelligence models and improve their performance.

[0799] "Means for generating ideas based on user prompts using a trained artificial intelligence model" refers to technologies and methods that use a pre-trained artificial intelligence model to automatically generate new ideas or text in response to specified input (prompts) from a user.

[0800] "Means for analyzing the generated ideas and returning them to the user's device" refers to the technology or method for analyzing automatically generated ideas and sending the results to the device used by the user.

[0801] The following describes an embodiment of the present invention. The present invention is a system that efficiently collects quotes and ideas from top executives of a company, trains an artificial intelligence model based on the collected ideas, and generates new ideas in response to user prompts. The system configuration and its specific operation are described below.

[0802] First, the server scrapes corporate leaders' quotes and ideas from their websites. It uses Python libraries such as BeautifulSoup and Selenium to automatically extract data from specific web pages. This allows the leaders' past quotes and ideas to be collected as text data.

[0803] The server then uses an API to retrieve the comments and ideas from the database. It uses an application programming interface, such as Firebase or Google Sheets API, to pull the required information from the database. This process integrates data from multiple sources.

[0804] The collected data is stored by the server in a database using a database management system such as SQLite or MySQL, and the data is organized in a suitable format so that it can be used efficiently in subsequent processing steps.

[0805] Next, the server preprocesses the collected data. This includes tokenizing the text data, removing stop words, and normalizing the data. Specifically, it uses Python's NLTK (Natural Language Toolkit) and Spacy to tokenize and remove frequent meaningless words (stop words). It also converts all data to lowercase and removes special characters and unnecessary whitespace to create a consistent dataset.

[0806] The preprocessed data is then used to train an artificial intelligence model. Machine learning libraries such as TensorFlow and PyTorch are used to train the model on the data. The server splits the dataset into training and validation sets and trains them over multiple epochs (training cycles), optimizing the model's performance.

[0807] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter a prompt like, "Let's think of an idea for a new project. The goal is to expand the market." The server receives this prompt and analyzes it as text data. Using the preprocessed data, a trained artificial intelligence model generates new ideas.

[0808] Finally, the generated ideas are sent back from the server to the device, where the user can review the new ideas and modify or adopt them as necessary. This process allows users to quickly and efficiently obtain new ideas and suggestions.

[0809] Let's take a concrete example. When a user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market," the server generates an idea such as "Introduce digital marketing to our existing product line to expand the market" and sends it back to the device. In this way, users can easily come up with original ideas simply by inputting a prompt.

[0810] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for making idea generation more efficient within a company and making extensive use of the knowledge of leaders.

[0811] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0812] Step 1: Collect data

[0813] The server collects quotes and ideas from the CEO. The server runs scripts written in Python and uses BeautifulSoup and Selenium to scrape data from specific websites. The server also retrieves quotes and ideas from a database using Firebase and Google Sheets APIs. The input for this step is the website URL and database query, and the output is text data. Specifically, it parses the HTML source of the webpage and extracts the required information. It also sends API requests and organizes the returned data.

[0814] Step 2: Save your data

[0815] The text data collected by the server is saved in a database. The database management systems used are SQLite and MySQL. The input is the text data collected in step 1, and the output is the data stored in the database. Specifically, the process connects to the database, creates a table, and inserts data.

[0816] Step 3: Preprocessing the data

[0817] The server preprocesses the data. It uses Python's NLTK or Spacy to tokenize the collected text data and remove stop words. It also normalizes the data. The input is the raw data saved in step 2, and the output is the preprocessed, clean data. Specifically, it splits the text into words, removes unnecessary words, and converts all text to lowercase.

[0818] Step 4: Training the AI ​​model

[0819] The server uses the preprocessed data to train an artificial intelligence model. Using TensorFlow or PyTorch, a large amount of text data is input and the model is trained. The input is the data preprocessed in step 3, and the output is the trained model. Specifically, the data is divided into training and validation data, and the model is trained over multiple epochs.

[0820] Step 5: Receiving the prompt

[0821] When a user wants to get a new idea, they send a specific prompt from their terminal to the server. The input is the prompt entered by the user, and the output is the data sent to the server. For example, a user might enter the prompt "Let's think of an idea for a new project. The goal is to expand the market." The specific operation is to enter the prompt into a form on the terminal and click the send button.

[0822] Step 6: Idea generation

[0823] Based on the prompt received by the server, a trained artificial intelligence model is used to generate new ideas. The input is the user's prompt and the trained model, and the output is the generated idea. Specifically, the prompt is input into the model and new text related to it is generated.

[0824] Step 7: Return and view your ideas

[0825] The server sends the generated idea back to the user's terminal, where the user confirms it. The input is the idea generated in step 6, and the output is the text displayed on the user's terminal. Specifically, the server sends the generated idea as an HTTP response, and the text is displayed in the browser.

[0826] (Application example 1)

[0827] 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."

[0828] In order to improve factory productivity, it is essential to quickly adopt new technologies and ideas. However, it takes a lot of time and effort for on-site engineers and managers to collect the necessary information and take appropriate measures. Furthermore, there is no system in place to effectively utilize the CEO's opinions and past ideas, which means that the knowledge of the entire organization cannot be fully utilized.

[0829] 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.

[0830] In this invention, the server includes a means for collecting CEO quotes and ideas, a means for preprocessing the collected data, a means for training a generative artificial intelligence model using the preprocessed data, a means for generating ideas based on user prompts, and a means for transmitting the generated ideas to robots in the factory, thereby enabling factory engineers and managers to quickly adopt new technologies and measures and effectively utilize knowledge from the entire organization.

[0831] A "CEO" is the highest-ranking executive who, as the chief executive officer, determines the company's management policies and formulates and implements the company's strategies.

[0832] A "quote" is a statement made or recorded by a specific individual in the past.

[0833] An "idea" is an original thought or proposal for solving a particular problem.

[0834] "Collection methods" refer to the methods and techniques used to obtain and store data from a particular source.

[0835] "Preprocessing means" refers to methods and techniques for processing collected data to prepare it in a form suitable for analysis and learning.

[0836] A "generative artificial intelligence model" is an artificial intelligence system that is trained using machine learning algorithms and has the ability to generate new information.

[0837] A "prompt" is a question or instruction that a user enters to give instructions to an artificial intelligence model.

[0838] "Generative means" refers to the methods or techniques by which an AI model generates new text or ideas in response to input prompts.

[0839] "Factory robots" are autonomous mechanical devices used to automate production lines and factory operations.

[0840] A "user terminal" is a device through which a user can input or output information, such as a computing device such as a smartphone or tablet.

[0841] This invention is a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on them, and generates ideas based on user prompts. This system is particularly useful for quickly acquiring and implementing new technologies and improvements for factory robots. The system configuration and specific operation are described below.

[0842] First, the server collects the CEO's quotes and ideas. The collection method uses algorithms and APIs to obtain and store data from specific sources. Specifically, this can involve techniques such as scraping data from websites or retrieving information from databases via APIs. This allows the CEO's past statements and ideas to be collected as text data.

[0843] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a preprocessing method, natural language processing (NLP) libraries such as SpaCy and NLTK are used to prepare the data in a format that is easy to analyze. Tokenization divides sentences into words and removes frequent meaningless words (stop words), making the data easier to analyze.

[0844] The server then uses the preprocessed data to train a generative AI model. The training method involves using machine learning algorithms such as OpenAI's GPT-4 to train the model on large amounts of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0845] When a user wants to get new ideas, they send a specific prompt from their device to the server. For example, they can enter specific instructions such as, "Tell me how to improve the efficiency of a new production line" or "Please provide me with a new idea to reduce manufacturing costs." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0846] The generated ideas are sent from the server to robots and terminals in the factory, where users can check them. The robots in the factory present the generated ideas to managers by reading them out loud or displaying them on a screen. This allows users to quickly and efficiently obtain new ideas and suggestions. For example, specific ideas such as "To improve the efficiency of the production line, we will introduce automation technology and optimize the coordination of each process" and "To reduce manufacturing costs, it is effective to introduce energy-efficient equipment and promote resource recycling" are generated.

[0847] The above is a specific embodiment for carrying out the present invention. The roles and functions of the server, terminal, and user allow users to easily come up with new ideas and increase factory productivity.

[0848] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0849] Step 1:

[0850] The server retrieves and stores data from a specific source using a method to collect CEO quotes and ideas, such as scraping data from a website or pulling information from a database via an API. The input for this step is a specific source URL or API endpoint, and the output is the collected text data.

[0851] Step 2:

[0852] The server preprocesses the collected data using a natural language processing (NLP) library. The libraries used are SpaCy and NLTK. Specifically, the collected text data is tokenized and stop words are removed. The input of this step is the collected text data, and the output is the preprocessed tokenized data.

[0853] Step 3:

[0854] The server uses the preprocessed data to train a generative AI model. The algorithm used is a machine learning model such as OpenAI's GPT-4. Specifically, the model takes tokenized data as input and learns its patterns to improve its ability to generate new text. The input for this step is preprocessed tokenized data, and the output is a trained generative AI model.

[0855] Step 4:

[0856] A user uses a terminal to send a prompt to the server to get new ideas. Specifically, the user inputs a prompt such as "Please tell me a new method to improve the efficiency of the production line" or "Please provide me with a new idea to reduce manufacturing costs." The input of this step is the user's prompt, and the output is the transmission of the prompt to the server.

[0857] Step 5:

[0858] The server receives prompts from users and generates ideas using a trained generative AI model. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text. The input for this step is the prompt sent by the user, and the output is the generated idea text.

[0859] Step 6:

[0860] The server sends the generated ideas to the robots and terminals in the factory. Specifically, the generated text is read aloud or sent to the robots to be displayed on a display. The input of this step is the generated idea text, and the output is the specific idea displayed on the robots and terminals.

[0861] Step 7:

[0862] The user checks the generated ideas through the terminal or the robot and takes appropriate measures. The input of this step is the text of the ideas displayed on the robot and the terminal, and the output is the user's utilization of the ideas.

[0863] The above is the specific process flow for implementing the invention. This system allows users to quickly and efficiently adopt new technologies and solutions.

[0864] 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.

[0865] The following describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains an artificial intelligence model based on the collected data, and generates ideas based on user prompts, with an emotion engine that recognizes the user's emotions. The following describes the system configuration and its specific operation.

[0866] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, this could involve scraping data from websites or extracting information from databases via APIs. This allows the CEO's past quotes and ideas to be collected as text data.

[0867] Next, the server preprocesses the collected data. This preprocessing includes tokenization and removal of stop words. As a means of preprocessing, a natural language processing library is used to prepare the data in a format that is easy to analyze. For example, by dividing a sentence into words and removing frequent meaningless words (stop words), the data becomes easier to analyze.

[0868] The server then uses the preprocessed data to train an artificial intelligence model (such as GPT-2). This training method uses a machine learning algorithm to train a large amount of text data. This process uses tokenized data as input and learns its patterns, improving the model's ability to generate new text.

[0869] When a user wants to get new ideas, they send a specific prompt from their device to the server. They input specific instructions such as, "Come up with an idea for a new project, with the goal of expanding the market." Based on this prompt, the server uses a trained artificial intelligence model to generate appropriate ideas. Specifically, it uses a tokenizer to analyze the prompt and generate relevant text.

[0870] This is where the emotion engine comes in, recognizing emotions from the user's input prompt. The emotion engine analyzes the text in the user's prompt and evaluates their emotional state. For example, it can determine if the user is nervous or relaxed.

[0871] The server adjusts the generated ideas based on the emotions recognized by the emotion engine, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is feeling nervous, the server may generate ideas containing encouraging words.

[0872] The generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. For example, a specific idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. In this way, users can easily generate original ideas simply by entering prompts.

[0873] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0874] The processing flow will be explained below.

[0875] Understood. As an embodiment of the invention, the process flow will be described in detail in the following format.

[0876] Step 1:

[0877] The server sends HTTP requests from a specified URL list to collect the CEO's quotes and ideas. The collected data is saved in JSON format.

[0878] Step 2:

[0879] The server preprocesses the collected data. Specifically, it extracts and combines text parts from the data. It also tokenizes the text data into words and removes stop words, making it easier to analyze.

[0880] Step 3:

[0881] The server trains an artificial intelligence model using the preprocessed data. It inputs the tokenized data into the model and uses the backpropagation algorithm to learn the model's parameters, thereby improving the model's ability to generate new text.

[0882] Step 4:

[0883] A user inputs a specific prompt from a terminal and sends a request to the server. For example, the user inputs a prompt such as "Let's think of an idea for a new project. The goal is to expand the market."

[0884] Step 5:

[0885] The server tokenizes the input prompt and converts it into tensor data for generation. The emotion engine analyzes the prompt text and recognizes the user's emotion. For example, it determines whether the user is "excited" or "nervous" from the prompt text.

[0886] Step 6:

[0887] The server inputs the trained AI model with the emotional information recognized by the emotion engine, which allows the generated ideas to be optimized for the user's emotional state.

[0888] Step 7:

[0889] The server decodes and formats the generated text, removing unnecessary tokens and special characters and shaping the generated ideas into natural-looking text.

[0890] Step 8:

[0891] The server sends the generated ideas back to the user's device, where the user can use them to create new projects and proposals.

[0892] For example, if a user inputs the prompt "Let's think of a new project idea with the goal of market expansion," the server uses the emotion engine to recognize that the user's emotion is "excited." Based on this, the AI ​​model generates ideas such as "Introduce digital marketing to existing product lines to target new customer segments in order to expand the market" and sends them back to the user in an encouraging and hopeful tone.

[0893] The above is a specific embodiment for carrying out the present invention. This system is a powerful tool for streamlining idea generation within a company, making extensive use of the knowledge of leaders, and enabling the provision of ideas that take into consideration the emotions of users.

[0894] Example 2

[0895] 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."

[0896] Conventional systems were unable to efficiently collect the CEO's knowledge and ideas and then effectively generate useful ideas for users based on them. Furthermore, the generated ideas were not adapted to the user's emotional state, resulting in low user satisfaction and effectiveness. Furthermore, there was a lack of a way to quickly and reliably deliver the generated ideas to the user's device.

[0897] 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.

[0898] In this invention, the server includes means for collecting CEO quotes and ideas, means for tokenizing the collected data and removing stop words and preprocessing the data, means for training a generative artificial intelligence model using the preprocessed data, means for generating ideas based on user prompts, means for performing sentiment analysis and adjusting the generated ideas based on the results, and means for returning the generated ideas to the user's terminal. This makes it possible to efficiently generate useful ideas while taking the user's sentiment into consideration and quickly and reliably provide them to the user's terminal.

[0899] "Means for collecting CEO quotes and ideas" refers to technology that obtains past statements and ideas of a company's chief executive officer (CEO) from various sources and stores them in a database.

[0900] "Tokenization" refers to the process of dividing text data into words, sentences, and other semantic units.

[0901] "Stop word removal" refers to a technique for removing meaningless words (such as "the" and "and") that are frequent but not very useful for analysis from text.

[0902] "Preprocessing methods" refers to a series of operations (e.g., tokenization, stop word removal, normalization, etc.) performed on collected data to make it easier for machine learning models to process.

[0903] A "generative artificial intelligence model" refers to a machine learning model that has been trained on a large amount of data in advance and is capable of generating new text based on given prompts.

[0904] "Sentiment analysis" refers to the technology of evaluating and classifying emotions and emotional states contained in text data.

[0905] "Means for generating ideas" refers to a technology that uses a pre-trained generative artificial intelligence model to generate new ideas based on user-entered prompts.

[0906] "Means for adjusting ideas" refers to a technology that adapts the tone and content of generated ideas to the user's emotional state based on the results of sentiment analysis.

[0907] "Means for sending back to the user's terminal" refers to technology that sends the generated ideas to the user's computing device so that they can be viewed.

[0908] This section describes an embodiment of the present invention. The present invention combines a system that efficiently collects CEO quotes and ideas, trains a generative AI model based on the collected data, and generates ideas based on user prompts, with emotion analysis technology that recognizes user emotions. The following describes the system configuration and its specific operation.

[0909] First, the server collects the CEO's quotes and ideas. This is done using algorithms or APIs that retrieve and store data from specific sources. For example, web scraping technology (BeautifulSoup or Scrapy) can be used to collect text data from interviews and speeches. Another method is to retrieve the CEO's past statements from a company's internal database via API.

[0910] The server then preprocesses the collected data, which includes tokenization and stop word removal. Natural language processing libraries (such as NLTK and SpaCy) are used to split the text into words and remove stop words, making the data easier to analyze.

[0911] The server then uses the preprocessed data to train a generative artificial intelligence model. The model used is GPT-2. Hugging Face's Transformers library is used to train the model using the preprocessed data. This process trains the model using a large amount of text data, improving its ability to generate new text.

[0912] When a user wants to get new ideas, they send a specific prompt from their device to the server, for example, "Think of an idea for a new project. The goal is to expand the market." This prompt is sent to the server and parsed using a tokenizer.

[0913] This is where sentiment analysis technology comes in, recognizing emotions from the user's prompts. The server uses sentiment analysis tools (such as IBM Watson or Hume AI) to analyze the text in the user's prompts and assess their emotional state. For example, it can identify when the user is tense or relaxed.

[0914] The server then adjusts the generated ideas based on the emotions recognized through emotion analysis, optimizing the tone and content of the ideas output according to the user's emotional state. For example, if the user is nervous, the server generates ideas containing encouraging words.

[0915] Finally, the generated ideas are sent back from the server to the device for the user to review. This allows users to quickly and efficiently obtain new ideas and proposals. As a specific example, an idea such as "Introduce digital marketing to existing product lines to expand the market" may be generated. Users can easily generate original ideas by simply entering prompts.

[0916] This system will be an effective means of streamlining idea generation within a company, making extensive use of leaders' knowledge, and enabling ideas to be provided that take into consideration users' emotions.

[0917] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0918] Step 1:

[0919] The server collects CEO quotes and ideas. The input is the URL of a specific website or database. The server uses web scraping technology (BeautifulSoup or Scrapy) to obtain the data and save it in text format. Specifically, the server accesses the website, parses the HTML document, and extracts the required text data.

[0920] Input: URL, API endpoint

[0921] Output: Text data (CEO quotes and ideas)

[0922] Step 2:

[0923] The server preprocesses the collected text data. First, the collected text is tokenized. Next, stop words are removed. To do this, a natural language processing library (NLTK or SpaCy) is used. Specifically, the text is divided into words and words with high frequency but low information content are filtered out.

[0924] Input: Text data

[0925] Output: Preprocessed text data (tokenized and stop words removed)

[0926] Step 3:

[0927] The server uses the preprocessed text data to train a generative artificial intelligence model. The model used is GPT-2. Using Hugging Face's Transformers library, the preprocessed data is fed to the model, which is trained over multiple epochs. Specifically, a training dataset is prepared, and the model's training parameters are set and run.

[0928] Input: Preprocessed text data

[0929] Output: A trained generative artificial intelligence model

[0930] Step 4:

[0931] The user inputs a prompt for a new idea from the terminal and sends it to the server. For example, the user inputs the instruction "Let's think of an idea for a new project. The goal is to expand the market," and clicks the send button.

[0932] Input: User prompt

[0933] Output: Send prompt to server

[0934] Step 5:

[0935] The server passes the prompt received to a sentiment analysis engine for analysis. The sentiment analysis engine uses IBM Watson or Hume AI. This evaluates the emotional state of the text contained in the prompt. Specifically, it obtains an emotional score and an emotional label.

[0936] Input: User prompt

[0937] Output: Sentiment analysis results (sentiment score, emotion label)

[0938] Step 6:

[0939] The server uses a generative artificial intelligence model to generate ideas based on the results of sentiment analysis and user prompts. The tone and content of the generated ideas are adjusted depending on the results of sentiment analysis. For example, if the prompt "Let's think of an idea for a new project. The goal is to expand the market," and the user feels nervous, the server will generate an idea that includes encouraging words.

[0940] Input: User prompt, sentiment analysis results

[0941] Output: Generated ideas

[0942] Step 7:

[0943] The server sends the generated ideas back to the terminal so that the user can review them. Specifically, the generated ideas are displayed in text format on the user's screen. An idea such as "Introduce digital marketing to existing product lines to expand the market" is displayed.

[0944] Input: Generated ideas

[0945] Output: The idea displayed on the user's device

[0946] Through each of the above processing steps, the system can efficiently generate and quickly provide useful ideas while taking into consideration the user's emotional state.

[0947] (Application example 2)

[0948] 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."

[0949] In idea generation systems using artificial intelligence, there is a need for a method that appropriately reflects the user's emotional state and provides specific and optimal ideas that are suited to the user's purpose and situation. In such systems, the user experience can be improved by dynamically adjusting the tone and content of the ideas generated based on the user's emotions, but the specific means for achieving this have been unclear.

[0950] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0951] In this invention, the server includes means for collecting CEO quotes and ideas, means for preprocessing the collected data, means for training an AI model using the preprocessed data, means for recognizing emotions from user input text, means for adjusting generated ideas based on the recognized emotion data, and means for optimizing the tone and content of the generated ideas, thereby enabling the server to accurately grasp the user's emotional state and quickly provide optimal ideas corresponding to that state.

[0952] "Quotations" refers to the content or records of past statements made by a specific person or group.

[0953] "Idea" refers to creative thoughts such as new ideas, plans, and strategies.

[0954] "Collection" refers to the act of gathering necessary data or information using specific means.

[0955] "Preprocessing" refers to a series of tasks that involve formatting data and removing unnecessary elements in order to improve the efficiency of data analysis and machine learning.

[0956] "Artificial intelligence model" refers to a computational model designed to learn from collected data and provide appropriate outputs based on new data.

[0957] "User" refers to an individual or corporation that uses a system or application.

[0958] A "prompt" refers to a sentence of instructions or questions that a user inputs to a system.

[0959] "Emotions" refer to psychological states such as joy, sadness, and anger that people experience.

[0960] "Recognition" refers to understanding and identifying specific patterns or meanings from data or information.

[0961] "Data" refers to facts, measurements, or records obtained from a particular source.

[0962] "Tone" refers to the mood, attitude, and style of a piece of writing or speech.

[0963] As an embodiment of the present invention, a system that incorporates emotion recognition and generates optimal ideas in response to user prompts will be described. This system efficiently collects CEO quotes and past ideas, trains an AI model using the collected data, and generates ideas that correspond to the user's emotional state. The detailed configuration and specific operation of the system will be described below.

[0964] The server first collects the CEO's quotes and ideas, for example by scraping the website or by retrieving information from a database via an API. The collected data is stored in text format and then preprocessed. Preprocessing includes tokenization and stop word removal, and is performed using a natural language processing library (e.g., nltk).

[0965] Next, an artificial intelligence model (e.g., GPT-2) is trained using the preprocessed data. The training process uses a large amount of high-quality text data, allowing the model to effectively learn patterns, which improves its ability to generate new text.

[0966] When a user wants to get a new idea, they send a specific prompt from their device to the server. For example, it may contain specific instructions such as "Think of an idea for a new project. The goal is to expand the market." Based on this prompt, the emotion engine recognizes emotions from the user's input text. Using natural language processing techniques, the emotion engine analyzes the emotional state of the input text and determines states such as "relaxed" or "tense."

[0967] The server then adjusts the generated ideas based on the recognized emotion data. This can include changing the tone or specific content of the generated text. For example, if the user is nervous, the server might generate ideas that include words of encouragement or support. The generated ideas are then sent back to the user's device for review.

[0968] As a concrete example, if a user inputs the prompt "I would like to think of a new initiative to expand our current market. Competition is intensifying, and I feel a little nervous," the emotion engine will recognize the emotion of "tension" and ultimately generate an idea such as "To expand our market, we recommend introducing a new product line and formulating a comprehensive strategy to deal with the intensifying competition. In the process, we should also introduce refreshing activities to increase employee motivation." In this way, the system can provide appropriate ideas that take into account the user's emotional state.

[0969] The required hardware is a server with a high-performance processor (e.g., GPU) and sufficient memory, and the required software is Python, a natural language processing library (e.g., transformers, nltk), and a machine learning framework (e.g., PyTorch).

[0970] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0971] Step 1:

[0972] The server collects CEO quotes and ideas. The collection method is to use techniques such as scraping data from websites and retrieving information from databases via APIs. This step requires website URLs and database API endpoints as input, and generates text data as output.

[0973] Step 2:

[0974] The server preprocesses the collected data. Specifically, it tokenizes the text and removes stop words using a natural language processing library (e.g., nltk). The input of this step is the text data collected in step 1, and the output is the tokenized, clean text data.

[0975] Step 3:

[0976] The server uses the preprocessed data to train an artificial intelligence model (e.g., GPT-2) using a machine learning framework (e.g., PyTorch). The input required is the preprocessed tokenized text data, and the output generated is a trained model.

[0977] Step 4:

[0978] To get new ideas, the user sends a prompt from their terminal to the server. A specific prompt might be, "Let's think of an idea for a new project. The goal is to expand the market." The input for this step is the user's prompt, and the output is the prompt sent to the server.

[0979] Step 5:

[0980] The server recognizes the emotion from the user's prompt. It uses an emotion engine to analyze the text and evaluate the emotional state. The input of this step is the prompt, and the output is the emotional state (e.g., "tense" or "relaxed").

[0981] Step 6:

[0982] The server adjusts the generated ideas based on the recognized emotion data. It uses a generative AI model (e.g., GPT-2) to generate emotion-based ideas. The input for this step is the prompt and emotion data, and the output is the adjusted idea.

[0983] Step 7:

[0984] The server sends the generated ideas back to the user's terminal. The input of this step is the adjusted ideas, and the output is the ideas displayed on the user's terminal.

[0985] Step 8:

[0986] The user confirms the idea sent to the terminal and receives guidance on the next step. The input of this step is the idea displayed on the terminal, and the output is the user's confirmation of the idea and feedback.

[0987] 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.

[0988] 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.

[0989] 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.

[0990] 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.

[0991] FIG. 9 illustrates 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 behaviors 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.

[0992] 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.

[0993] 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).

[0994] 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.

[0995] 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."

[0996] 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.

[0997] 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).

[0998] 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.

[0999] 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.

[1000] 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.

[1001] 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.

[1002] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, 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 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.

[1003] 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.

[1004] 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.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] The following is further disclosed regarding the above embodiment.

[1009] Understood. I propose a draft of the claims in the following format:

[1010] (Claim 1)

[1011] A means of collecting CEO quotes and ideas,

[1012] a means for pre-processing the collected data;

[1013] means for training an artificial intelligence model using the preprocessed data;

[1014] A system including a means for generating ideas based on user prompts.

[1015] (Claim 2)

[1016] 10. The system of claim 1, further comprising means for tokenizing text portions of the collected data and removing stop words.

[1017] (Claim 3)

[1018] 10. The system of claim 1, further comprising means for returning the generated ideas to the user's terminal.

[1019] "Example 1"

[1020] (Claim 1)

[1021] How to scrape CEO quotes and ideas from websites,

[1022] A means of retrieving comments and ideas from the database using an API;

[1023] a means for storing the collected data in a database;

[1024] a means for pre-processing the collected data;

[1025] means for tokenizing the preprocessed data and removing stop words;

[1026] means for training an artificial intelligence model using the preprocessed data;

[1027] A system including a means for generating ideas based on user prompts using a trained artificial intelligence model.

[1028] (Claim 2)

[1029] a means for tokenizing the text portion of the collected data and removing stop words;

[1030] 10. The system of claim 1, further comprising means for normalizing the preprocessed data.

[1031] (Claim 3)

[1032] 10. The system of claim 1, further comprising means for analyzing the generated ideas and returning them to the user's terminal.

[1033] "Application Example 1"

[1034] (Claim 1)

[1035] A means of collecting CEO quotes and ideas,

[1036] a means for pre-processing the collected data;

[1037] means for training a generative artificial intelligence model using the preprocessed data;

[1038] means for generating ideas based on user prompts and transmitting the generated ideas to robots in the factory;

[1039] A system including:

[1040] (Claim 2)

[1041] 10. The system of claim 1, further comprising means for tokenizing text portions of the collected data and removing stop words.

[1042] (Claim 3)

[1043] 10. The system of claim 1, further comprising means for sending the generated ideas back to the user's terminal and to the robots in the factory.

[1044] "Example 2: Combining Emotion Engines"

[1045] (Claim 1)

[1046] A means of collecting CEO quotes and ideas,

[1047] a means for tokenizing, removing stop words, and preprocessing the collected data;

[1048] means for training a generative artificial intelligence model using the preprocessed data;

[1049] means for generating ideas based on user prompts;

[1050] a means for performing sentiment analysis and adjusting generated ideas based on the results;

[1051] means for returning the generated ideas to the user's terminal;

[1052] A system including:

[1053] (Claim 2)

[1054] 10. The system of claim 1, further comprising means for tokenizing text portions of the collected data and removing stop words.

[1055] (Claim 3)

[1056] 10. The system of claim 1, further comprising means for analyzing text contained in a user's prompt to assess an emotional state.

[1057] "Application example 2 when combining emotion engines"

[1058] (Claim 1)

[1059] A means of collecting CEO quotes and ideas,

[1060] a means for pre-processing the collected data;

[1061] means for training an artificial intelligence model using the preprocessed data;

[1062] means for generating ideas based on user prompts;

[1063] means for recognizing emotions from a user's input text;

[1064] a means for adjusting the generated ideas based on the recognized emotion data;

[1065] A system that includes means to optimize the tone and content of generated ideas.

[1066] (Claim 2)

[1067] 10. The system of claim 1, further comprising means for tokenizing text portions of the collected data and removing stop words.

[1068] (Claim 3)

[1069] 10. The system of claim 1, further comprising means for returning the generated ideas to the user's terminal. [Explanation of symbols]

[1070] 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. A means of collecting CEO quotes and ideas, a means for pre-processing the collected data; means for training an artificial intelligence model using the preprocessed data; and a means for generating ideas based on user prompts.

2. 10. The system of claim 1, further comprising means for tokenizing the text portions of the collected data and removing stop words.

3. 2. The system of claim 1, further comprising means for returning the generated ideas to the user's terminal.

Images