system

Abstract

Provide a system. 【Solution means】 Means for collecting market data, Means for analyzing the collected market data, Means for generating business options based on the analyzed data, Means for storing the generated options in a database, Means for allowing users to view options and provide feedback, Means for analyzing the provided feedback and modifying business options, Means for storing the modified options in the database again and notifying the user, A system including the above.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In modern enterprises, a series of processes such as collection of market data, generation of business options, collection and analysis of feedback from users require time and labor with conventional manual methods, and there is a problem that it is difficult to make quick decisions. In particular, in emerging markets and highly competitive fields, timely data analysis and quick response are required, so an efficient system is needed.

Means for Solving the Problems

[0005] The present invention provides

[0006] 1. means for automatically collecting market data from the Internet,

[0007] 2. A means of analyzing collected market data using a machine learning model,

[0008] 3. A method using generative AI to generate business options based on analyzed data,

[0009] 4. A means of saving the generated options to a database,

[0010] 5. A means for users to view options on their devices and provide feedback,

[0011] 6. A means of analyzing the provided feedback using natural language processing technology and modifying business options,

[0012] 7. Means for saving the modified options back into the database and notifying the user.

[0013] This system includes the following features. This system enables rapid and efficient collection of market data, option generation, and user feedback. By continuously improving the options generated based on user feedback, it allows for quick decision-making and the development of optimal business strategies.

[0014] "Market data" refers to a set of information and data related to a specific market, including consumer behavior, competitive analysis, and sales data.

[0015] "Data analysis" is the process of analyzing collected data using statistical and machine learning techniques to extract meaningful information and insights.

[0016] "Business options" refer to the choices and strategies that a company or organization can implement to pursue new business opportunities.

[0017] "Generative AI" is an artificial intelligence technology that generates new information and options based on large amounts of data.

[0018] A "database" is a system for organizing the storage and management of collected and generated data and information.

[0019] A "terminal" is an electronic device through which a user can input and output information, such as a computer or a smartphone.

[0020] "Feedback" is the opinions and comments provided by users, and is information used for system improvement and optimization.

[0021] "Natural language processing technology" is a technology for a computer to understand, interpret, and generate human language.

[0022] [[ID=十六]]"Notification" is the transmission of information from the system to the user, including means such as emails and push notifications.

Brief Description of Drawings

[0023] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0024] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0025] First, let's explain the terminology used in the following explanation.

[0026] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0027] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0028] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0029] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0030] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0031] [First Embodiment]

[0032] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0033] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0034] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0035] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0036] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0037] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0038] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0039] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0040] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0041] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0042] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0043] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0044] This invention relates to a system that collects market data, generates business options using generative AI, and improves the options by collecting feedback from users. This system collects market data via the internet and analyzes the data using machine learning models. Based on the analyzed data, the generative AI generates business options and stores them in a database. Users can view the business options using their devices and provide feedback. The provided feedback is analyzed using natural language processing technology, and the options are modified. These modified options are also stored in the database and the user is notified.

[0045] Market data collection via servers

[0046] The server collects market data from multiple sources on the internet. Specifically, it periodically accesses a set list of URLs, sends HTTP requests, and retrieves the HTML content of web pages. Then, it uses analysis tools to extract the necessary market data from the HTML content and stores it in a database.

[0047] Server-based data analysis and business option generation.

[0048] Next, the server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options. For example, it analyzes specific market trends and consumer behavior patterns and proposes business plans and marketing strategies based on that information. The generated business options are then saved back into the database.

[0049] Displaying proposed options on devices and collecting feedback.

[0050] Users can access the database using their own devices and view the generated business options. Users can then provide feedback on the displayed options. This feedback includes specific opinions, comments, and suggestions for improvement.

[0051] Analysis of server-side feedback and revision of proposed options.

[0052] The server retrieves user feedback from the database and analyzes it using natural language processing technology. This analysis identifies useful information and areas for improvement based on user feedback. Based on the analysis results, a generative AI modifies the business options again and generates new option proposals. These modified options are saved back to the database and notified to the user.

[0053] Specific example

[0054] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback that "more cost reductions should be incorporated." Analyzing this feedback, the generative AI generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user, enabling a rapid improvement cycle.

[0055] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0056] The following describes the processing flow.

[0057] Step 1:

[0058] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page.

[0059] Step 2:

[0060] The server analyzes the acquired HTML content using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. Specifically, text and numerical data are extracted using certain tags and classes.

[0061] Step 3:

[0062] The server saves the extracted market data to a database. The saving method uses a database interface (e.g., SQL).

[0063] Step 4:

[0064] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes data preprocessing, feature extraction, and model application.

[0065] Step 5:

[0066] Based on the data analyzed by the server, a generative AI (e.g., GPT-3®) is used to generate business options. The generation process proposes specific business plans that take into account the business environment and market trends.

[0067] Step 6:

[0068] The server saves the generated business options to the database.

[0069] Step 7:

[0070] The terminal retrieves business options stored in the database and displays them to the user. The user views the business options on the terminal and provides ratings and comments.

[0071] Step 8:

[0072] The device receives the feedback provided by the user and saves it to a database.

[0073] Step 9:

[0074] The server retrieves user feedback from the database and analyzes it using natural language processing techniques. The analysis extracts useful information and areas for improvement from the feedback.

[0075] Step 10:

[0076] Based on the analysis results, the server uses generative AI again to modify existing business options. New options are generated, and a revised business plan reflecting the improvements is proposed again.

[0077] Step 11:

[0078] The server will save the modified business options back to the database and notify the user. The notification will be sent via email, push notification, or other means.

[0079] (Example 1)

[0080] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0081] Traditional processes for generating and improving business options based on market data often involved manual analysis and were inefficient. Furthermore, it was difficult to quickly incorporate user feedback, making it challenging to consistently provide optimal business options. Therefore, there is a need to efficiently manage the entire process, from market data collection to the generation and refinement of business options, using automated systems, thereby enabling rapid decision-making and the development of appropriate business strategies.

[0082] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0083] In this invention, the server includes means for collecting market data from multiple information sources on the internet, means for analyzing the collected market data using an analysis tool, means for generating business options based on the analyzed data using a generative AI model, means for storing the generated options in a database, means for users to view the options using their own terminals and provide feedback, means for analyzing the provided feedback using natural language processing technology and modifying the business options, and means for storing the modified options back in the database and notifying the user. This makes it possible to consistently and automatically and efficiently perform everything from collecting market data to generating business options and modifying the options based on feedback.

[0084] "Multiple sources of information on the internet" refers to a collection of information accessible via the internet, such as numerous websites and online databases.

[0085] "Market data" refers to any information related to a specific market, including price information, sales trends, consumer behavior, and other data.

[0086] "Analysis tools" refer to software and libraries used to extract and analyze data. For example, BeautifulSoup is used for HTML parsing.

[0087] "Generative AI models" refer to artificial intelligence models used to generate business options and proposals. Specifically, this includes natural language generation models such as GPT-3.

[0088] "Business options" refer to business proposals and strategies generated based on the analysis of market data.

[0089] A "database" refers to a system for systematically storing and managing collected data and generated options. Examples include relational databases such as PostgreSQL.

[0090] A "terminal" refers to an electronic device, such as a computer or smartphone, that a user uses to access a system.

[0091] "Feedback" refers to information such as opinions, comments, and suggestions for improvement provided by users.

[0092] "Natural language processing technology" refers to technologies that analyze user feedback and convert it into meaningful information. Specifically, this includes technologies such as NLTK and Spacy.

[0093] This invention is a system that collects market data, generates business options using a generative AI model, and improves the options by collecting feedback from users. This system consists of three main elements: a server, a terminal, and a user.

[0094] Market data collection via servers

[0095] The server collects market data from multiple sources on the internet. During this process, the server periodically accesses a configured list of URLs, sending HTTP requests to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using analytical tools such as BeautifulSoup to extract the necessary market data. The extracted data is then stored in a database such as PostgreSQL.

[0096] Server-based data analysis and business option generation.

[0097] Next, the server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TENSORFLOW® or Scikit-learn). Based on the analyzed data, it generates business options using generative AI models (e.g., GPT-3). The generated business options are then saved back into the database.

[0098] Displaying proposed options on devices and collecting feedback.

[0099] Users can log in to the system using their personal computers, smartphones, or other devices and view the generated business options. Users can then provide specific feedback on the displayed business options. For example, a user can provide feedback by entering "More cost reduction should be incorporated" into the feedback form and pressing the submit button.

[0100] Analysis of server-side feedback and revision of proposed options.

[0101] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). Useful information and areas for improvement are extracted from the feedback, and a generative AI model then modifies and generates new business options based on this information. The modified business options are saved back into the database and notified to the user via email or push notification.

[0102] Specific example

[0103] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback, stating that "more cost reduction should be incorporated." The generative AI analyzes this feedback and generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user.

[0104] This system efficiently executes a series of processes, from market data collection and business option generation to the collection and incorporation of user feedback. It also supports rapid decision-making and the development of optimal business strategies.

[0105] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0106] Step 1:

[0107] Market data collection

[0108] The server retrieves a pre-configured list of URLs and periodically sends HTTP requests to these URLs to retrieve the HTML content of web pages. The retrieved HTML content is analyzed using an analysis tool such as BeautifulSoup, and necessary market data such as "pricing information" and "sales trends" is extracted. The input is the URL list and the configured HTTP requests, and the output is the analyzed market data. The extracted market data is stored in a database such as PostgreSQL.

[0109] Step 2:

[0110] Data analysis and business option generation

[0111] The server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). The input is market data, and the output is market trends and consumer behavior patterns as analysis results. Based on these analysis results, a generative AI model (GPT-3) generates business options. These generated business options are also saved back into the database. The input is the analysis results of market trends, and the output is business options.

[0112] Step 3:

[0113] Display of option proposals

[0114] Users access the database using their own devices and log in to the system. Logged-in users can view the latest business options. The input is the user's authentication information, and the output is a display of the latest business options.

[0115] Step 4:

[0116] Provide feedback

[0117] Users provide specific feedback on the displayed business options. For example, a user might enter "More cost reductions should be implemented" into the feedback form and then press the submit button to provide feedback. The input is the user's feedback, and the output is the submission of the feedback data.

[0118] Step 5:

[0119] Feedback analysis

[0120] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). The input is the feedback data, and the output is useful information and suggestions for improvement extracted from the feedback.

[0121] Step 6:

[0122] Modification of the proposed options

[0123] The generative AI model modifies and regenerates business options based on extracted feedback information. The modified business options are also saved back to the database, and emails and push notifications are sent to users. The input is the feedback analysis results, and the output is the modified business options and notifications to users.

[0124] (Application Example 1)

[0125] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0126] Traditional e-commerce sites have struggled to efficiently propose products based on market trends, making it difficult to respond quickly to user needs. Furthermore, mechanisms for improving product recommendations based on user feedback are insufficient, potentially leading to decreased customer satisfaction. To address these challenges, a system is needed that effectively collects and analyzes market data, uses that data to make product recommendations, and quickly and effectively incorporates user feedback.

[0127] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0128] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback and modifying the business options, means for storing the modified options back in the database and notifying the user, means for generating product suggestions based on market trends, and means for improving product suggestions based on user feedback. This enables rapid and effective product suggestions based on market trends and improvement of product suggestions utilizing user feedback.

[0129] "Market data" refers to information related to the market, including consumer trends, competitor activities, and social media trends.

[0130] "Means of analysis" refers to methods and techniques for evaluating, comparing, and calculating collected market data, and transforming it into valuable information.

[0131] "Generative means" refers to methods and technologies for creating new business options and product proposals based on analyzed data.

[0132] A "database" refers to a system that systematically stores information such as generated options and feedback, making it accessible later.

[0133] "Feedback" refers to opinions, comments, and evaluations provided by users, which are used to improve business options and product proposals.

[0134] "Means of modification" refers to methods and technologies for changing and improving business options and product proposals based on user feedback.

[0135] "Means of notification" refers to methods and technologies for informing users of revised options or suggestions.

[0136] "Product proposals based on market trends" refers to proposing new products and services to users based on trends obtained by analyzing market data.

[0137] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to automatically generate optimal business options and product suggestions from market data.

[0138] A "prompt statement" refers to a document used to give instructions or questions to an AI model, and is used as a definition or guideline for the content that is generated.

[0139] This invention relates to a system that collects market data using the internet, generates business options using a generative AI model, and improves these options based on user feedback. Specific embodiments are described below.

[0140] Market data collection via servers

[0141] The server collects market data from multiple sources on the internet. Specifically, it periodically sends HTTP requests to a set list of URLs to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using tools such as BeautifulSoup to extract the necessary market data, which is then stored in a database.

[0142] example:

[0143] Assume the URL list includes "https: / / example.com / marketdata1" and "https: / / example.com / marketdata2". Periodically send HTTP requests to these URLs and extract market data from the retrieved HTML content, such as "Smartwatches are a popular product on review site A" or "Wireless earphones are a product with recent sales growth on competitor e-commerce site B".

[0144] Server-based data analysis and business option generation.

[0145] The server retrieves market data collected from the database and analyzes the data using a generative AI model. During this analysis process, it uses prompts such as the following:

[0146] Example of a prompt:

[0147] "Please generate business options based on the following market data:

[0148] Popular items on review site A are "smartwatches".

[0149] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[0150] The trend gaining attention on social media is "eco-friendly products."

[0151] The generated business options are stored in the database.

[0152] Displaying options via the device and collecting feedback

[0153] Users access the database using their own devices (e.g., smartphones or personal computers) and view the generated business options. In response, users can provide feedback such as specific opinions, comments, and suggestions for improvement.

[0154] example:

[0155] If a user provides feedback stating that "the options should include more eco-friendly products," this feedback will be stored in a database.

[0156] Server-based feedback analysis and option correction

[0157] The server extracts feedback provided by users and analyzes it using natural language processing technology. Based on this analysis, it identifies areas for improvement, and the generated AI model then creates newly modified business options.

[0158] Example of a prompt:

[0159] Please improve your business options based on the following feedback:

[0160] Feedback: The options should include more eco-friendly products.

[0161] The modified business options are saved back to the database and the user is notified.

[0162] Hardware and software use cases

[0163] The hardware required to run this system includes an internet-connected server (e.g., an Amazon EC2 instance) and user devices (e.g., a smartphone or personal computer). The software used includes Python scripts, an HTTP request library (e.g., requests), an HTML parsing tool (e.g., BeautifulSoup), a generative AI model (e.g., OpenAI® API), and a database management system (e.g., MySQL®, PostgreSQL).

[0164] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0165] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0166] Step 1:

[0167] The server collects market data. At this stage, the server periodically sends HTTP requests to a configured list of URLs to retrieve the HTML content of the web pages. The retrieved HTML content is parsed using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. The extracted market data is stored in a database. The input consists of a URL list and HTTP requests, and the output is the parsed market data.

[0168] Step 2:

[0169] The server retrieves market data collected from the database and analyzes it using a generative AI model. During the analysis, it provides the generative AI model with prompt statements to generate business options. As a result, business options generated based on the analyzed data are output. These options are then saved back into the database. The input requires market data and prompt statements, and the output generates business options.

[0170] Step 3:

[0171] Users access the database using a terminal and view the generated business options. Here, users can review the options and provide feedback such as opinions, comments, and suggestions for improvement. This feedback is stored in the database. Business options are required as input, and user feedback is obtained as output.

[0172] Step 4:

[0173] The server retrieves feedback from the database and analyzes it using natural language processing technology. This analysis extracts information and areas for improvement from the feedback. Next, it generates prompt statements based on the extracted feedback information and provides them to a generation AI model to modify the business options. The modified business options are output, saved back to the database, and notified to the user. User feedback and prompt statements are required as input, and the output is modified business options.

[0174] Specific examples of operation

[0175] The server accesses URLs such as "https: / / example.com / marketdata1", retrieves and analyzes the HTML content, and extracts market data.

[0176] Add the analyzed market data to the following prompt:

[0177] "The most popular product on review site A is 'smartwatches'."

[0178] Provide prompt text to the generative AI model:

[0179] "Please generate business options based on the following market data:

[0180] Popular items on review site A are "smartwatches".

[0181] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[0182] The trend gaining attention on social media is "eco-friendly products."

[0183] Users use their devices to review business options and provide feedback such as, "The options should include more eco-friendly products."

[0184] The server analyzes the feedback and generates the following prompt:

[0185] Please improve your business options based on the following feedback:

[0186] Feedback: The options should include more eco-friendly products.

[0187] The above describes the specific processing steps and operations for implementing the system of the present invention.

[0188] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0189] This invention combines an emotion engine with a system that collects market data, generates business options using generative AI, and improves options by collecting and analyzing user feedback. By using the emotion engine throughout the process from market data collection to feedback analysis, it is possible to generate more effective business options that also take user emotions into account.

[0190] Market data collection via servers

[0191] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and an analysis tool is used to extract the necessary market data. The extracted market data is then stored in a database.

[0192] Server-based data analysis and business option generation.

[0193] The server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options, which are then stored in the database. Specific options include new business plans and marketing strategies based on market trends and consumer behavior analysis.

[0194] Displaying proposed options on devices and collecting feedback.

[0195] Users can use their own devices to view business options stored in the database. Users can provide feedback on the displayed options, including not only text comments but also sentiment.

[0196] Server-based feedback and emotion analysis

[0197] The server retrieves user-provided feedback from the database. In addition to analyzing the feedback using natural language processing technology, an emotion engine recognizes and analyzes the user's emotions during the feedback process. This allows for a more precise analysis that takes into account the emotions the user expressed during the feedback.

[0198] Server-based modification of business options

[0199] Based on the analysis results, the generative AI further refines the business options. In particular, the revisions take user emotions into consideration, aiming to improve the user experience. For example, if a user expresses dissatisfaction, the AI ​​will propose improvements to address that dissatisfaction. These new options are also stored in the database and notified to the user.

[0200] Specific example

[0201] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. A user views this option and comments that it "doesn't offer much in the way of savings," and the emotion engine then recognizes "disappointment" from the user's comment. The server analyzes this feedback and emotion, and uses generative AI to regenerate the option. This regeneration includes new energy-saving technologies and improvements that don't incur additional costs, addressing the user's "disappointment." This improved option is then saved back to the database and the user is notified, enabling a rapid improvement cycle.

[0202] Thus, the system of the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with a series of processes, from market data collection to option generation and analysis and reflection of user feedback.

[0203] The following describes the processing flow.

[0204] Step 1:

[0205] The server accesses a pre-configured list of URLs and sends an HTTP request to each URL. It then retrieves the HTML content of the web page.

[0206] Step 2:

[0207] The server retrieves HTML content, which is then analyzed using a parsing tool (such as BeautifulSoup) to identify tags and classes, and extract the necessary market data.

[0208] Step 3:

[0209] The server executes an SQL query to save the extracted market data to the database. This ensures that the data is stored systematically.

[0210] Step 4:

[0211] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes processes such as preprocessing and feature extraction.

[0212] Step 5:

[0213] The server uses the analyzed data to run a generative AI (e.g., GPT-3) and generate business options. Specific prompts are input to the generative AI, and the results are retrieved.

[0214] Step 6:

[0215] The server saves the generated business options to the database. SQL queries are used to insert the proposed options into the database.

[0216] Step 7:

[0217] The terminal retrieves business options from the database and displays them to the user. The user views the proposed options on the terminal.

[0218] Step 8:

[0219] Users provide feedback on the displayed business options. Users enter their feedback as text on their device.

[0220] Step 9:

[0221] The device acquires user feedback and analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions from text and generates data.

[0222] Step 10:

[0223] The device saves feedback and sentiment data to a database. SQL queries are used to save the data.

[0224] Step 11:

[0225] The server retrieves user feedback and sentiment data from the database and analyzes it using natural language processing techniques. This analysis identifies useful information and areas for improvement.

[0226] Step 12:

[0227] The server executes a generative AI based on the analysis results, modifying and regenerating business options. In particular, it creates new business plans that take user emotions into consideration.

[0228] Step 13:

[0229] The server saves the modified business options to the database and notifies the user. Notifications are sent via methods such as email or push notifications.

[0230] (Example 2)

[0231] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0232] Business options generated based on market data often fail to adequately consider user emotions and feedback, resulting in a lack of improved user experience and difficulty in formulating effective business strategies. Furthermore, if user feedback and emotions are not accurately analyzed and reflected in business options without prompt improvement, the business's competitiveness may decline.

[0233] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0234] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback using natural language processing technology and sentiment recognition technology, means for modifying the business options based on the analysis results, and means for storing the modified options back in the database and notifying the user. This enables the generation of effective business options that take user sentiment into account and the rapid incorporation of feedback.

[0235] "Market data" refers to information about market trends, product information, consumer behavior, and so on.

[0236] "Means of collection" refers to the function of obtaining data by sending an HTTP request from a specific URL on the internet and storing it in a database.

[0237] "Means of analysis" refer to techniques for processing and breaking down collected data to extract informational features and patterns.

[0238] "Means for generating business options" refers to the function of generating new business plans and marketing strategies based on analyzed market data.

[0239] "Generative AI" is an artificial intelligence technology that generates new information and ideas based on data.

[0240] A "database" is a system for organizing and storing collected and generated data and information.

[0241] "Feedback" refers to opinions such as evaluations and impressions of options provided by users.

[0242] "Natural language processing technology" is a technology that converts human language into a format that can be handled by computers and then analyzes it.

[0243] "Emotion recognition technology" is a technology that extracts and identifies emotions from users' text and comments.

[0244] This invention combines an emotion engine with a system that collects market data, generates business options using a generative AI model, and improves options by collecting user feedback. The following describes how this invention is specifically implemented.

[0245] Market data collection

[0246] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. Specifically, it uses analysis tools such as Beautiful Soup or Scrapy to parse the HTML content of the web pages and extract market data (e.g., new product information, market trends). The extracted data is stored in a database on the server.

[0247] Data analysis and business option generation

[0248] The server retrieves market data collected from the database and analyzes it using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI models such as GPT-4(registered trademark). These generated options, such as new business plans and marketing strategies, are also stored in the database.

[0249] Display of proposed options and collection of feedback.

[0250] The server sends business options stored in the database to the user's device (smartphone or PC), which then displays them. The user views the options and provides feedback, including text comments and sentiment. This feedback information is sent from the device to the server and stored in the database.

[0251] Feedback and emotion analysis

[0252] The server retrieves user-provided feedback from the database. It analyzes the text of the feedback using natural language processing techniques such as BERT and SpaCy, and recognizes and analyzes the user's emotions while they are providing the feedback using an Aspect-based Sentiment Analysis model.

[0253] Revision of business options

[0254] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The modified business options are further refined to take user sentiment into account. These new options are also stored in the database and notified to the user.

[0255] Specific example

[0256] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. Suppose a user sees this option and comments that it "doesn't offer much in the way of savings," and the emotion engine recognizes this as "disappointment." The server analyzes this feedback and emotion and uses a generative AI model to regenerate the option. This regeneration includes new energy-saving technologies and improvements that do not incur additional costs, in order to address the user's "disappointment." This improved option is then saved back to the database and the user is notified.

[0257] Example of a prompt

[0258] "Generate concrete ideas for improving energy-saving appliance management systems in the smart home market. User feedback indicates 'low savings' and their sentiment is 'disappointment.' Propose improvements that will satisfy users."

[0259] In this way, the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with processes ranging from market data collection to option generation, and from the collection, analysis, and reflection of user feedback.

[0260] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0261] Step 1: Collect market data

[0262] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The input is the list of market data URLs, and the output is the HTML content obtained from each URL. Specifically, the server uses tools like Beautiful Soup or Scrapy to parse the HTML content and extract market data (e.g., new product information, market trends). The extracted data is then stored in a database.

[0263] Step 2: Data analysis and business option generation

[0264] The server retrieves market data collected from a database. Its input is the stored market data, and its output is the data analysis results and generated business options. Specifically, the server analyzes the market data using machine learning models such as TensorFlow or PyTorch. Based on these results, it generates business options using generative AI models such as GPT-4. The generated options are stored in the database.

[0265] Step 3: Displaying proposed options and gathering feedback

[0266] The server sends business options stored in the database to the user's terminal. The input is the business option data in the database, and the output is the proposed options displayed on the user's terminal. Specifically, the user views the business options on their terminal (smartphone or PC) and provides feedback, including text comments and sentiment. This feedback information is sent from the terminal to the server and stored in the database.

[0267] Step 4: Feedback and emotional analysis

[0268] The server retrieves user-provided feedback from the database. The input is user-provided feedback data, and the output is the analysis results of the feedback and the sentiment recognition results. Specifically, the server uses natural language processing techniques such as BERT and SpaCy to analyze the feedback text and uses an Aspect-based Sentiment Analysis model to recognize and analyze the user's emotions.

[0269] Step 5: Modifying Business Options

[0270] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The input is feedback and sentiment analysis results, and the output is the modified business options. Specifically, the server considers the user's emotions and generates options that include specific improvements, such as addressing dissatisfaction. These new options are also stored in the database and notified to the user.

[0271] In this way, by having all steps work together in coordination, it becomes possible to formulate more effective business strategies and improve the user experience.

[0272] (Application Example 2)

[0273] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0274] Traditional systems for generating and improving business options based on market data failed to adequately improve user experience and customer satisfaction because they relied solely on numerical data and text feedback, without considering user emotions.

[0275] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting market information, means for analyzing the collected market information, means for generating business options based on the analyzed information, means for storing the generated options in an information repository, means for users to view the options and provide feedback including emotions, means for analyzing the provided feedback including emotions and modifying the business options, and means for storing the modified options in the information repository again and notifying the user. This enables the generation of more effective business options that take user emotions into consideration and a rapid improvement cycle.

[0276] "Market information" refers to data and information related to the market, such as consumer behavior and trends, and the movements of competing companies.

[0277] "To analyze" refers to the process of processing the collected market information and feedback to draw meaningful insights.

[0278] "Business options" refer to new business plans and marketing strategies proposed based on the analysis results of market information.

[0279] "Information repository" refers to a database for storing the generated business options, the collected market information, feedback, etc.

[0280] "Users" refer to individuals or groups who use the system to view business options and provide feedback.

[0281] "Feedback containing emotions" refers to the emotional elements contained in the feedback in addition to the opinions and comments provided by users.

[0282] "Emotion analysis engine" refers to the technology for analyzing the emotions of the provided feedback and recognizing the emotional state of the user.

[0283] "Learning model" refers to a machine learning algorithm for analyzing the collected market information and generating business options based on it.

[0284] The system for implementing this invention has a process of collecting market information, generating business options based on that information, collecting and analyzing feedback containing emotions from users, and further using the results to modify and improve the business options. Next, specific processes are shown.

[0285] 1. Collection of market information

[0286] The server accesses a pre-set list of URLs of market information and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and necessary market information is extracted using parsing tools such as BeautifulSoup. The extracted market information is stored in an information repository.

[0287] 2. Data Analysis and Generation of Business Options

[0288] The server retrieves the market information collected from the information repository and analyzes the data using machine learning models such as TensorFlow or PyTorch. Based on the analysis results, business options are generated using generative AI (e.g., GPT-4). These options are also stored in the information repository.

[0289] 3. Display of Business Options and Collection of Feedback Including Emotions

[0290] Users view the business options stored in the information repository using devices such as smartphones and smart glasses. Users provide feedback on the displayed options, including emotions. This feedback including emotions is also stored in the information repository.

[0291] 4. Analysis of Feedback and Emotions

[0292] The server retrieves the feedback provided by users from the information repository and uses natural language processing techniques (e.g., SpaCy or NLTK) and emotion analysis engines such as IBM Watson's Tone Analyzer to recognize and analyze the emotions of users in the feedback.

[0293] 5. Modification of Business Options

[0294] Based on the analysis of feedback, the server uses generative AI to regenerate business options. In particular, modifications are made that take user emotions into consideration, thereby improving the user experience. The modified business options are then saved again to the information repository, and users are notified.

[0295] Specific example

[0296] For example, suppose market data is collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "Energy-Saving Home Appliance Management System" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[0297] Example of a prompt

[0298] User feedback: "This ad is very ordinary and doesn't convey any passion." Emotions detected: "Disappointed." Modify the following ad campaign to better address user concerns: "Eco-friendly new products! (Energy-saving appliances) will support your home."

[0299] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0300] Step 1:

[0301] The server accesses a pre-set list of URLs of market information and sends an HTTP request to each URL. The input is the list of URLs, and the output is the HTML content of each web page. The server retrieves the HTML content and uses parsing tools such as BeautifulSoup to extract the necessary market information. The extracted information is saved in the market information repository.

[0302] Step 2:

[0303] The server retrieves the market information collected from the market information repository. The input is the market information saved in the market information repository, and the output is the data converted into an analyzable format. This data is analyzed using machine learning models such as TensorFlow or PyTorch. Based on the analysis results, generative AI (e.g., GPT-4) generates business options. The generated options are saved in the information repository.

[0304] Step 3:

[0305] The terminal accesses the information repository and displays the generated business options. The user browses the options using a smartphone, smart glasses, etc. The input is the business options saved in the information repository, and the output is the options displayed on the terminal. The user provides feedback on the displayed options. The feedback includes text comments and sentiment information.

[0306] Step 4:

[0307] The server retrieves the feedback provided by the user from the information repository. The input is the feedback saved in the information repository, and the output is the analyzable feedback data. Natural language processing techniques (e.g., SpaCy or NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer are used to recognize and analyze the user's sentiment in the feedback.

[0308] Step 5:

[0309] The server uses generative AI to regenerate business options based on the analysis results. The input is the analysis results and the original business options, and the output is the improved business options. In particular, modifications are made to take user sentiment into consideration, and the newly generated business options are saved again in the information repository.

[0310] Step 6:

[0311] The terminal accesses the information vault, displays improved business options, and notifies the user. The input is the improved business options, and the output is the improved options displayed on the terminal and the notification to the user. This allows the user to review the new business options and provide further feedback as needed.

[0312] Specific examples of operation:

[0313] For example, market data might be collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "energy-saving home appliance management system" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[0314] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0315] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0316] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0317] [Second Embodiment]

[0318] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0319] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0320] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0321] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0322] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0323] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0324] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0325] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0326] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0327] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0328] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0329] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0330] This invention relates to a system that collects market data, generates business options using generative AI, and improves the options by collecting feedback from users. This system collects market data via the internet and analyzes the data using machine learning models. Based on the analyzed data, the generative AI generates business options and stores them in a database. Users can view the business options using their devices and provide feedback. The provided feedback is analyzed using natural language processing technology, and the options are modified. These modified options are also stored in the database and the user is notified.

[0331] Market data collection via servers

[0332] The server collects market data from multiple sources on the internet. Specifically, it periodically accesses a set list of URLs, sends HTTP requests, and retrieves the HTML content of web pages. Then, it uses analysis tools to extract the necessary market data from the HTML content and stores it in a database.

[0333] Server-based data analysis and business option generation.

[0334] Next, the server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options. For example, it analyzes specific market trends and consumer behavior patterns and proposes business plans and marketing strategies based on that information. The generated business options are then saved back into the database.

[0335] Displaying proposed options on devices and collecting feedback.

[0336] Users can access the database using their own devices and view the generated business options. Users can then provide feedback on the displayed options. This feedback includes specific opinions, comments, and suggestions for improvement.

[0337] Analysis of server-side feedback and revision of proposed options.

[0338] The server retrieves user feedback from the database and analyzes it using natural language processing technology. This analysis identifies useful information and areas for improvement based on user feedback. Based on the analysis results, a generative AI modifies the business options again and generates new option proposals. These modified options are saved back to the database and notified to the user.

[0339] Specific example

[0340] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback that "more cost reductions should be incorporated." Analyzing this feedback, the generative AI generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user, enabling a rapid improvement cycle.

[0341] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0342] The following describes the processing flow.

[0343] Step 1:

[0344] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page.

[0345] Step 2:

[0346] The server analyzes the acquired HTML content using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. Specifically, text and numerical data are extracted using certain tags and classes.

[0347] Step 3:

[0348] The server saves the extracted market data to a database. The saving method uses a database interface (e.g., SQL).

[0349] Step 4:

[0350] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes data preprocessing, feature extraction, and model application.

[0351] Step 5:

[0352] Based on the data analyzed by the server, a generative AI (e.g., GPT-3) generates business options. The generation process proposes specific business plans that take into account the business environment and market trends.

[0353] Step 6:

[0354] The server saves the generated business options to the database.

[0355] Step 7:

[0356] The terminal retrieves business options stored in the database and displays them to the user. The user views the business options on the terminal and provides ratings and comments.

[0357] Step 8:

[0358] The device receives the feedback provided by the user and saves it to a database.

[0359] Step 9:

[0360] The server retrieves user feedback from the database and analyzes it using natural language processing techniques. The analysis extracts useful information and areas for improvement from the feedback.

[0361] Step 10:

[0362] Based on the analysis results, the server uses generative AI again to modify existing business options. New options are generated, and a revised business plan reflecting the improvements is proposed again.

[0363] Step 11:

[0364] The server will save the modified business options back to the database and notify the user. The notification will be sent via email, push notification, or other means.

[0365] (Example 1)

[0366] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0367] Traditional processes for generating and improving business options based on market data often involved manual analysis and were inefficient. Furthermore, it was difficult to quickly incorporate user feedback, making it challenging to consistently provide optimal business options. Therefore, there is a need to efficiently manage the entire process, from market data collection to the generation and refinement of business options, using automated systems, thereby enabling rapid decision-making and the development of appropriate business strategies.

[0368] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0369] In this invention, the server includes means for collecting market data from multiple information sources on the internet, means for analyzing the collected market data using an analysis tool, means for generating business options based on the analyzed data using a generative AI model, means for storing the generated options in a database, means for users to view the options using their own terminals and provide feedback, means for analyzing the provided feedback using natural language processing technology and modifying the business options, and means for storing the modified options back in the database and notifying the user. This makes it possible to consistently and automatically and efficiently perform everything from collecting market data to generating business options and modifying the options based on feedback.

[0370] "Multiple sources of information on the internet" refers to a collection of information accessible via the internet, such as numerous websites and online databases.

[0371] "Market data" refers to any information related to a specific market, including price information, sales trends, consumer behavior, and other data.

[0372] "Analysis tools" refer to software and libraries used to extract and analyze data. For example, BeautifulSoup is used for HTML parsing.

[0373] "Generative AI models" refer to artificial intelligence models used to generate business options and proposals. Specifically, this includes natural language generation models such as GPT-3.

[0374] "Business options" refer to business proposals and strategies generated based on the analysis of market data.

[0375] A "database" refers to a system for systematically storing and managing collected data and generated options. Examples include relational databases such as PostgreSQL.

[0376] A "terminal" refers to an electronic device, such as a computer or smartphone, that a user uses to access a system.

[0377] "Feedback" refers to information such as opinions, comments, and suggestions for improvement provided by users.

[0378] "Natural language processing technology" refers to technologies that analyze user feedback and convert it into meaningful information. Specifically, this includes technologies such as NLTK and Spacy.

[0379] This invention is a system that collects market data, generates business options using a generative AI model, and improves the options by collecting feedback from users. This system consists of three main elements: a server, a terminal, and a user.

[0380] Market data collection via servers

[0381] The server collects market data from multiple sources on the internet. During this process, the server periodically accesses a configured list of URLs, sending HTTP requests to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using analytical tools such as BeautifulSoup to extract the necessary market data. The extracted data is then stored in a database such as PostgreSQL.

[0382] Server-based data analysis and business option generation.

[0383] Next, the server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). Based on the analyzed data, it generates business options using generative AI models (e.g., GPT-3). The generated business options are then saved back into the database.

[0384] Displaying proposed options on devices and collecting feedback.

[0385] Users can log in to the system using their personal computers, smartphones, or other devices and view the generated business options. Users can then provide specific feedback on the displayed business options. For example, a user can provide feedback by entering "More cost reduction should be incorporated" into the feedback form and pressing the submit button.

[0386] Analysis of server-side feedback and revision of proposed options.

[0387] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). Useful information and areas for improvement are extracted from the feedback, and a generative AI model then modifies and generates new business options based on this information. The modified business options are saved back into the database and notified to the user via email or push notification.

[0388] Specific example

[0389] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback, stating that "more cost reduction should be incorporated." The generative AI analyzes this feedback and generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user.

[0390] This system efficiently executes a series of processes, from market data collection and business option generation to the collection and incorporation of user feedback. It also supports rapid decision-making and the development of optimal business strategies.

[0391] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0392] Step 1:

[0393] Market data collection

[0394] The server retrieves a pre-configured list of URLs and periodically sends HTTP requests to these URLs to retrieve the HTML content of web pages. The retrieved HTML content is analyzed using an analysis tool such as BeautifulSoup, and necessary market data such as "pricing information" and "sales trends" is extracted. The input is the URL list and the configured HTTP requests, and the output is the analyzed market data. The extracted market data is stored in a database such as PostgreSQL.

[0395] Step 2:

[0396] Data analysis and business option generation

[0397] The server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). The input is market data, and the output is market trends and consumer behavior patterns as analysis results. Based on these analysis results, a generative AI model (GPT-3) generates business options. These generated business options are also saved back into the database. The input is the analysis results of market trends, and the output is business options.

[0398] Step 3:

[0399] Display of option proposals

[0400] Users access the database using their own devices and log in to the system. Logged-in users can view the latest business options. The input is the user's authentication information, and the output is a display of the latest business options.

[0401] Step 4:

[0402] Provide feedback

[0403] Users provide specific feedback on the displayed business options. For example, a user might enter "More cost reductions should be implemented" into the feedback form and then press the submit button to provide feedback. The input is the user's feedback, and the output is the submission of the feedback data.

[0404] Step 5:

[0405] Feedback analysis

[0406] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). The input is the feedback data, and the output is useful information and suggestions for improvement extracted from the feedback.

[0407] Step 6:

[0408] Modification of the proposed options

[0409] The generative AI model modifies and regenerates business options based on extracted feedback information. The modified business options are also saved back to the database, and emails and push notifications are sent to users. The input is the feedback analysis results, and the output is the modified business options and notifications to users.

[0410] (Application Example 1)

[0411] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0412] Traditional e-commerce sites have struggled to efficiently propose products based on market trends, making it difficult to respond quickly to user needs. Furthermore, mechanisms for improving product recommendations based on user feedback are insufficient, potentially leading to decreased customer satisfaction. To address these challenges, a system is needed that effectively collects and analyzes market data, uses that data to make product recommendations, and quickly and effectively incorporates user feedback.

[0413] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0414] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback and modifying the business options, means for storing the modified options back in the database and notifying the user, means for generating product suggestions based on market trends, and means for improving product suggestions based on user feedback. This enables rapid and effective product suggestions based on market trends and improvement of product suggestions utilizing user feedback.

[0415] "Market data" refers to information related to the market, including consumer trends, competitor activities, and social media trends.

[0416] "Means of analysis" refers to methods and techniques for evaluating, comparing, and calculating collected market data, and transforming it into valuable information.

[0417] "Generative means" refers to methods and technologies for creating new business options and product proposals based on analyzed data.

[0418] A "database" refers to a system that systematically stores information such as generated options and feedback, making it accessible later.

[0419] "Feedback" refers to opinions, comments, and evaluations provided by users, which are used to improve business options and product proposals.

[0420] "Means of modification" refers to methods and technologies for changing and improving business options and product proposals based on user feedback.

[0421] "Means of notification" refers to methods and technologies for informing users of revised options or suggestions.

[0422] "Product proposals based on market trends" refers to proposing new products and services to users based on trends obtained by analyzing market data.

[0423] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to automatically generate optimal business options and product suggestions from market data.

[0424] A "prompt statement" refers to a document used to give instructions or questions to an AI model, and is used as a definition or guideline for the content that is generated.

[0425] This invention relates to a system that collects market data using the internet, generates business options using a generative AI model, and improves these options based on user feedback. Specific embodiments are described below.

[0426] Market data collection via servers

[0427] The server collects market data from multiple sources on the internet. Specifically, it periodically sends HTTP requests to a set list of URLs to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using tools such as BeautifulSoup to extract the necessary market data, which is then stored in a database.

[0428] example:

[0429] Assume the URL list includes "https: / / example.com / marketdata1" and "https: / / example.com / marketdata2". Periodically send HTTP requests to these URLs and extract market data from the retrieved HTML content, such as "Smartwatches are a popular product on review site A" or "Wireless earphones are a product with recent sales growth on competitor e-commerce site B".

[0430] Server-based data analysis and business option generation.

[0431] The server retrieves market data collected from the database and analyzes the data using a generative AI model. During this analysis process, it uses prompts such as the following:

[0432] Example of a prompt:

[0433] "Please generate business options based on the following market data:

[0434] Popular items on review site A are "smartwatches".

[0435] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[0436] The trend gaining attention on social media is "eco-friendly products."

[0437] The generated business options are stored in the database.

[0438] Displaying options via the device and collecting feedback

[0439] Users access the database using their own devices (e.g., smartphones or personal computers) and view the generated business options. In response, users can provide feedback such as specific opinions, comments, and suggestions for improvement.

[0440] example:

[0441] If a user provides feedback stating that "the options should include more eco-friendly products," this feedback will be stored in a database.

[0442] Server-based feedback analysis and option correction

[0443] The server extracts feedback provided by users and analyzes it using natural language processing technology. Based on this analysis, it identifies areas for improvement, and the generated AI model then creates newly modified business options.

[0444] Example of a prompt:

[0445] Please improve your business options based on the following feedback:

[0446] Feedback: The options should include more eco-friendly products.

[0447] The modified business options are saved back to the database and the user is notified.

[0448] Hardware and software use cases

[0449] The hardware required to run this system includes an internet-connected server (e.g., an Amazon EC2 instance) and user devices (e.g., a smartphone or personal computer). The software used includes Python scripts, an HTTP request library (e.g., requests), an HTML parsing tool (e.g., BeautifulSoup), a generative AI model (e.g., the OpenAI API), and a database management system (e.g., MySQL, PostgreSQL).

[0450] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0451] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0452] Step 1:

[0453] The server collects market data. At this stage, the server periodically sends HTTP requests to a configured list of URLs to retrieve the HTML content of the web pages. The retrieved HTML content is parsed using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. The extracted market data is stored in a database. The input consists of a URL list and HTTP requests, and the output is the parsed market data.

[0454] Step 2:

[0455] The server retrieves market data collected from the database and analyzes it using a generative AI model. During the analysis, it provides the generative AI model with prompt statements to generate business options. As a result, business options generated based on the analyzed data are output. These options are then saved back into the database. The input requires market data and prompt statements, and the output generates business options.

[0456] Step 3:

[0457] Users access the database using a terminal and view the generated business options. Here, users can review the options and provide feedback such as opinions, comments, and suggestions for improvement. This feedback is stored in the database. Business options are required as input, and user feedback is obtained as output.

[0458] Step 4:

[0459] The server retrieves feedback from the database and analyzes it using natural language processing technology. This analysis extracts information and areas for improvement from the feedback. Next, it generates prompt statements based on the extracted feedback information and provides them to a generation AI model to modify the business options. The modified business options are output, saved back to the database, and notified to the user. User feedback and prompt statements are required as input, and the output is modified business options.

[0460] Specific examples of operation

[0461] The server accesses URLs such as "https: / / example.com / marketdata1", retrieves and analyzes the HTML content, and extracts market data.

[0462] Add the analyzed market data to the following prompt:

[0463] "The most popular product on review site A is 'smartwatches'."

[0464] Provide prompt text to the generative AI model:

[0465] "Please generate business options based on the following market data:

[0466] Popular items on review site A are "smartwatches".

[0467] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[0468] The trend gaining attention on social media is "eco-friendly products."

[0469] Users use their devices to review business options and provide feedback such as, "The options should include more eco-friendly products."

[0470] The server analyzes the feedback and generates the following prompt:

[0471] Please improve your business options based on the following feedback:

[0472] Feedback: The options should include more eco-friendly products.

[0473] The above describes the specific processing steps and operations for implementing the system of the present invention.

[0474] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0475] This invention combines an emotion engine with a system that collects market data, generates business options using generative AI, and improves options by collecting and analyzing user feedback. By using the emotion engine throughout the process from market data collection to feedback analysis, it is possible to generate more effective business options that also take user emotions into account.

[0476] Market data collection via servers

[0477] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and an analysis tool is used to extract the necessary market data. The extracted market data is then stored in a database.

[0478] Server-based data analysis and business option generation.

[0479] The server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options, which are then stored in the database. Specific options include new business plans and marketing strategies based on market trends and consumer behavior analysis.

[0480] Displaying proposed options on devices and collecting feedback.

[0481] Users can use their own devices to view business options stored in the database. Users can provide feedback on the displayed options, including not only text comments but also sentiment.

[0482] Server-based feedback and emotion analysis

[0483] The server retrieves user-provided feedback from the database. In addition to analyzing the feedback using natural language processing technology, an emotion engine recognizes and analyzes the user's emotions during the feedback process. This allows for a more precise analysis that takes into account the emotions the user expressed during the feedback.

[0484] Server-based modification of business options

[0485] Based on the analysis results, the generative AI further refines the business options. In particular, the revisions take user emotions into consideration, aiming to improve the user experience. For example, if a user expresses dissatisfaction, the AI ​​will propose improvements to address that dissatisfaction. These new options are also stored in the database and notified to the user.

[0486] Specific example

[0487] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. A user views this option and comments that it "doesn't offer much in the way of savings," and the emotion engine then recognizes "disappointment" from the user's comment. The server analyzes this feedback and emotion, and uses generative AI to regenerate the option. This regeneration includes new energy-saving technologies and improvements that don't incur additional costs, addressing the user's "disappointment." This improved option is then saved back to the database and the user is notified, enabling a rapid improvement cycle.

[0488] Thus, the system of the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with a series of processes, from market data collection to option generation and analysis and reflection of user feedback.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The server accesses a pre-configured list of URLs and sends an HTTP request to each URL. It then retrieves the HTML content of the web page.

[0492] Step 2:

[0493] The server retrieves HTML content, which is then analyzed using a parsing tool (such as BeautifulSoup) to identify tags and classes, and extract the necessary market data.

[0494] Step 3:

[0495] The server executes an SQL query to save the extracted market data to the database. This ensures that the data is stored systematically.

[0496] Step 4:

[0497] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes processes such as preprocessing and feature extraction.

[0498] Step 5:

[0499] The server uses the analyzed data to run a generative AI (e.g., GPT-3) and generate business options. Specific prompts are input to the generative AI, and the results are retrieved.

[0500] Step 6:

[0501] The server saves the generated business options to the database. SQL queries are used to insert the proposed options into the database.

[0502] Step 7:

[0503] The terminal retrieves business options from the database and displays them to the user. The user views the proposed options on the terminal.

[0504] Step 8:

[0505] Users provide feedback on the displayed business options. Users enter their feedback as text on their device.

[0506] Step 9:

[0507] The device acquires user feedback and analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions from text and generates data.

[0508] Step 10:

[0509] The device saves feedback and sentiment data to a database. SQL queries are used to save the data.

[0510] Step 11:

[0511] The server retrieves user feedback and sentiment data from the database and analyzes it using natural language processing techniques. This analysis identifies useful information and areas for improvement.

[0512] Step 12:

[0513] The server executes a generative AI based on the analysis results, modifying and regenerating business options. In particular, it creates new business plans that take user emotions into consideration.

[0514] Step 13:

[0515] The server saves the modified business options to the database and notifies the user. Notifications are sent via methods such as email or push notifications.

[0516] (Example 2)

[0517] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0518] Business options generated based on market data often fail to adequately consider user emotions and feedback, resulting in a lack of improved user experience and difficulty in formulating effective business strategies. Furthermore, if user feedback and emotions are not accurately analyzed and reflected in business options without prompt improvement, the business's competitiveness may decline.

[0519] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0520] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback using natural language processing technology and sentiment recognition technology, means for modifying the business options based on the analysis results, and means for storing the modified options back in the database and notifying the user. This enables the generation of effective business options that take user sentiment into account and the rapid incorporation of feedback.

[0521] "Market data" refers to information about market trends, product information, consumer behavior, and so on.

[0522] "Means of collection" refers to the function of obtaining data by sending an HTTP request from a specific URL on the internet and storing it in a database.

[0523] "Means of analysis" refer to techniques for processing and breaking down collected data to extract informational features and patterns.

[0524] "Means for generating business options" refers to the function of generating new business plans and marketing strategies based on analyzed market data.

[0525] "Generative AI" is an artificial intelligence technology that generates new information and ideas based on data.

[0526] A "database" is a system for organizing and storing collected and generated data and information.

[0527] "Feedback" refers to opinions such as evaluations and impressions of options provided by users.

[0528] "Natural language processing technology" is a technology that converts human language into a format that can be handled by computers and then analyzes it.

[0529] "Emotion recognition technology" is a technology that extracts and identifies emotions from users' text and comments.

[0530] This invention combines an emotion engine with a system that collects market data, generates business options using a generative AI model, and improves options by collecting user feedback. The following describes how this invention is specifically implemented.

[0531] Market data collection

[0532] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. Specifically, it uses analysis tools such as Beautiful Soup or Scrapy to parse the HTML content of the web pages and extract market data (e.g., new product information, market trends). The extracted data is stored in a database on the server.

[0533] Data analysis and business option generation

[0534] The server retrieves market data collected from the database and analyzes it using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI models such as GPT-4. These generated options, such as new business plans and marketing strategies, are also stored in the database.

[0535] Display of proposed options and collection of feedback.

[0536] The server sends business options stored in the database to the user's device (smartphone or PC), which then displays them. The user views the options and provides feedback, including text comments and sentiment. This feedback information is sent from the device to the server and stored in the database.

[0537] Feedback and emotion analysis

[0538] The server retrieves user-provided feedback from the database. It analyzes the text of the feedback using natural language processing techniques such as BERT and SpaCy, and recognizes and analyzes the user's emotions while they are providing the feedback using an Aspect-based Sentiment Analysis model.

[0539] Revision of business options

[0540] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The modified business options are further refined to take user sentiment into account. These new options are also stored in the database and notified to the user.

[0541] Specific example

[0542] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. Suppose a user sees this option and comments that it "doesn't offer much in the way of savings," and the emotion engine recognizes this as "disappointment." The server analyzes this feedback and emotion and uses a generative AI model to regenerate the option. This regeneration includes new energy-saving technologies and improvements that do not incur additional costs, in order to address the user's "disappointment." This improved option is then saved back to the database and the user is notified.

[0543] Example of a prompt

[0544] "Generate concrete ideas for improving energy-saving appliance management systems in the smart home market. User feedback indicates 'low savings' and their sentiment is 'disappointment.' Propose improvements that will satisfy users."

[0545] In this way, the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with processes ranging from market data collection to option generation, and from the collection, analysis, and reflection of user feedback.

[0546] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0547] Step 1: Collect market data

[0548] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The input is the list of market data URLs, and the output is the HTML content obtained from each URL. Specifically, the server uses tools like Beautiful Soup or Scrapy to parse the HTML content and extract market data (e.g., new product information, market trends). The extracted data is then stored in a database.

[0549] Step 2: Data analysis and business option generation

[0550] The server retrieves market data collected from a database. Its input is the stored market data, and its output is the data analysis results and generated business options. Specifically, the server analyzes the market data using machine learning models such as TensorFlow or PyTorch. Based on these results, it generates business options using generative AI models such as GPT-4. The generated options are stored in the database.

[0551] Step 3: Displaying proposed options and gathering feedback

[0552] The server sends business options stored in the database to the user's terminal. The input is the business option data in the database, and the output is the proposed options displayed on the user's terminal. Specifically, the user views the business options on their terminal (smartphone or PC) and provides feedback, including text comments and sentiment. This feedback information is sent from the terminal to the server and stored in the database.

[0553] Step 4: Feedback and emotional analysis

[0554] The server retrieves user-provided feedback from the database. The input is user-provided feedback data, and the output is the analysis results of the feedback and the sentiment recognition results. Specifically, the server uses natural language processing techniques such as BERT and SpaCy to analyze the feedback text and uses an Aspect-based Sentiment Analysis model to recognize and analyze the user's emotions.

[0555] Step 5: Modifying Business Options

[0556] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The input is feedback and sentiment analysis results, and the output is the modified business options. Specifically, the server considers the user's emotions and generates options that include specific improvements, such as addressing dissatisfaction. These new options are also stored in the database and notified to the user.

[0557] In this way, by having all steps work together in coordination, it becomes possible to formulate more effective business strategies and improve the user experience.

[0558] (Application Example 2)

[0559] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0560] Traditional systems for generating and improving business options based on market data failed to adequately improve user experience and customer satisfaction because they relied solely on numerical data and text feedback, without considering user emotions.

[0561] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting market information, means for analyzing the collected market information, means for generating business options based on the analyzed information, means for storing the generated options in an information repository, means for users to view the options and provide feedback including emotions, means for analyzing the provided feedback including emotions and modifying the business options, and means for storing the modified options in the information repository again and notifying the user. This enables the generation of more effective business options that take user emotions into consideration and a rapid improvement cycle.

[0562] "Market information" refers to data and information about the market, such as consumer behavior and trends, and the activities of competitors.

[0563] "Analyzing" refers to the process of processing collected market information and feedback to extract meaningful insights.

[0564] "Business options" refer to new business plans and marketing strategies proposed based on the analysis of market information.

[0565] An "information repository" refers to a database used to store generated business options, collected market information, feedback, and other data.

[0566] "Users" refers to individuals or organizations that use the system to view business options and provide feedback.

[0567] "Feedback that includes emotion" refers to the emotional elements contained within the opinions and comments provided by users.

[0568] An "emotion analysis engine" refers to a technology that analyzes the emotions of the feedback provided and recognizes the user's emotional state.

[0569] A "learning model" refers to a machine learning algorithm that analyzes collected market information and generates business options based on that analysis.

[0570] The system implementing this invention has a process for collecting market information, generating business options based on that information, collecting and analyzing feedback from users, including emotional feedback, and further modifying and improving the business options using the results. The specific process is shown below.

[0571] 1. Gathering market information

[0572] The server accesses a pre-configured list of market information URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and analysis tools such as BeautifulSoup are used to extract the necessary market information. The extracted market information is then stored in an information repository.

[0573] 2. Data analysis and business option generation

[0574] The server retrieves market information collected from the data repository and analyzes the data using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI (e.g., GPT-4). These options are also stored in the data repository.

[0575] 3. Displaying business options and collecting feedback, including sentiment.

[0576] Users view business options stored in the information vault using devices such as smartphones and smart glasses. Users provide feedback on the displayed options, including their emotions. This feedback, including emotions, is also stored in the information vault.

[0577] 4. Feedback and Sentiment Analysis

[0578] The server retrieves user-provided feedback from the data repository and uses natural language processing technologies (e.g., SpaCy and NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer to recognize and analyze the user's emotions during the feedback process.

[0579] 5. Revision of business options

[0580] Based on the analysis of feedback, the server uses generative AI to regenerate business options. In particular, modifications are made that take user emotions into consideration, thereby improving the user experience. The modified business options are then saved again to the information repository, and users are notified.

[0581] Specific example

[0582] For example, suppose market data is collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "Energy-Saving Home Appliance Management System" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[0583] Example of a prompt

[0584] User feedback: "This ad is very ordinary and doesn't convey any passion." Emotions detected: "Disappointed." Modify the following ad campaign to better address user concerns: "Eco-friendly new products! (Energy-saving appliances) will support your home."

[0585] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0586] Step 1:

[0587] The server accesses a pre-configured list of market information URLs and sends an HTTP request to each URL. The input is the URL list, and the output is the HTML content of each web page. The HTML content is retrieved, and the necessary market information is extracted using an analysis tool such as BeautifulSoup. The extracted information is stored in the market information repository.

[0588] Step 2:

[0589] The server retrieves market information collected from the market information repository. The input is the market information stored in the repository, and the output is data converted into an analyzable format. This data is analyzed using machine learning models such as TensorFlow or PyTorch. Based on the analysis results, a generative AI (e.g., GPT-4) generates business options. The generated options are stored in the information repository.

[0590] Step 3:

[0591] The terminal accesses the information vault and displays the generated business options. Users view the options using smartphones, smart glasses, etc. The input is the business options stored in the information vault, and the output is the options displayed on the terminal. Users provide feedback on the displayed options. This feedback includes text comments and sentiment information.

[0592] Step 4:

[0593] The server retrieves user-provided feedback from the data repository. The input is the feedback stored in the data repository, and the output is analyzable feedback data. Natural language processing techniques (e.g., SpaCy or NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer are used to recognize and analyze the user's emotions during feedback.

[0594] Step 5:

[0595] The server uses generative AI to regenerate business options based on the analysis results. The input is the analysis results and the original business options, and the output is the improved business options. In particular, modifications are made to take user sentiment into consideration, and the newly generated business options are saved again in the information repository.

[0596] Step 6:

[0597] The terminal accesses the information vault, displays improved business options, and notifies the user. The input is the improved business options, and the output is the improved options displayed on the terminal and the notification to the user. This allows the user to review the new business options and provide further feedback as needed.

[0598] Specific examples of operation:

[0599] For example, market data might be collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "energy-saving home appliance management system" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[0600] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0601] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0602] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0603] [Third Embodiment]

[0604] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0605] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0606] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0607] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0608] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0609] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0610] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0611] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0612] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0613] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0614] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0615] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0616] This invention relates to a system that collects market data, generates business options using generative AI, and improves the options by collecting feedback from users. This system collects market data via the internet and analyzes the data using machine learning models. Based on the analyzed data, the generative AI generates business options and stores them in a database. Users can view the business options using their devices and provide feedback. The provided feedback is analyzed using natural language processing technology, and the options are modified. These modified options are also stored in the database and the user is notified.

[0617] Market data collection via servers

[0618] The server collects market data from multiple sources on the internet. Specifically, it periodically accesses a set list of URLs, sends HTTP requests, and retrieves the HTML content of web pages. Then, it uses analysis tools to extract the necessary market data from the HTML content and stores it in a database.

[0619] Server-based data analysis and business option generation.

[0620] Next, the server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options. For example, it analyzes specific market trends and consumer behavior patterns and proposes business plans and marketing strategies based on that information. The generated business options are then saved back into the database.

[0621] Displaying proposed options on devices and collecting feedback.

[0622] Users can access the database using their own devices and view the generated business options. Users can then provide feedback on the displayed options. This feedback includes specific opinions, comments, and suggestions for improvement.

[0623] Analysis of server-side feedback and revision of proposed options.

[0624] The server retrieves user feedback from the database and analyzes it using natural language processing technology. This analysis identifies useful information and areas for improvement based on user feedback. Based on the analysis results, a generative AI modifies the business options again and generates new option proposals. These modified options are saved back to the database and notified to the user.

[0625] Specific example

[0626] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback that "more cost reductions should be incorporated." Analyzing this feedback, the generative AI generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user, enabling a rapid improvement cycle.

[0627] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0628] The following describes the processing flow.

[0629] Step 1:

[0630] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page.

[0631] Step 2:

[0632] The server analyzes the acquired HTML content using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. Specifically, text and numerical data are extracted using certain tags and classes.

[0633] Step 3:

[0634] The server saves the extracted market data to a database. The saving method uses a database interface (e.g., SQL).

[0635] Step 4:

[0636] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes data preprocessing, feature extraction, and model application.

[0637] Step 5:

[0638] Based on the data analyzed by the server, a generative AI (e.g., GPT-3) generates business options. The generation process proposes specific business plans that take into account the business environment and market trends.

[0639] Step 6:

[0640] The server saves the generated business options to the database.

[0641] Step 7:

[0642] The terminal retrieves business options stored in the database and displays them to the user. The user views the business options on the terminal and provides ratings and comments.

[0643] Step 8:

[0644] The device receives the feedback provided by the user and saves it to a database.

[0645] Step 9:

[0646] The server retrieves user feedback from the database and analyzes it using natural language processing techniques. The analysis extracts useful information and areas for improvement from the feedback.

[0647] Step 10:

[0648] Based on the analysis results, the server uses generative AI again to modify existing business options. New options are generated, and a revised business plan reflecting the improvements is proposed again.

[0649] Step 11:

[0650] The server will save the modified business options back to the database and notify the user. The notification will be sent via email, push notification, or other means.

[0651] (Example 1)

[0652] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0653] Traditional processes for generating and improving business options based on market data often involved manual analysis and were inefficient. Furthermore, it was difficult to quickly incorporate user feedback, making it challenging to consistently provide optimal business options. Therefore, there is a need to efficiently manage the entire process, from market data collection to the generation and refinement of business options, using automated systems, thereby enabling rapid decision-making and the development of appropriate business strategies.

[0654] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0655] In this invention, the server includes means for collecting market data from multiple information sources on the internet, means for analyzing the collected market data using an analysis tool, means for generating business options based on the analyzed data using a generative AI model, means for storing the generated options in a database, means for users to view the options using their own terminals and provide feedback, means for analyzing the provided feedback using natural language processing technology and modifying the business options, and means for storing the modified options back in the database and notifying the user. This makes it possible to consistently and automatically and efficiently perform everything from collecting market data to generating business options and modifying the options based on feedback.

[0656] "Multiple sources of information on the internet" refers to a collection of information accessible via the internet, such as numerous websites and online databases.

[0657] "Market data" refers to any information related to a specific market, including price information, sales trends, consumer behavior, and other data.

[0658] "Analysis tools" refer to software and libraries used to extract and analyze data. For example, BeautifulSoup is used for HTML parsing.

[0659] "Generative AI models" refer to artificial intelligence models used to generate business options and proposals. Specifically, this includes natural language generation models such as GPT-3.

[0660] "Business options" refer to business proposals and strategies generated based on the analysis of market data.

[0661] A "database" refers to a system for systematically storing and managing collected data and generated options. Examples include relational databases such as PostgreSQL.

[0662] A "terminal" refers to an electronic device, such as a computer or smartphone, that a user uses to access a system.

[0663] "Feedback" refers to information such as opinions, comments, and suggestions for improvement provided by users.

[0664] "Natural language processing technology" refers to technologies that analyze user feedback and convert it into meaningful information. Specifically, this includes technologies such as NLTK and Spacy.

[0665] This invention is a system that collects market data, generates business options using a generative AI model, and improves the options by collecting feedback from users. This system consists of three main elements: a server, a terminal, and a user.

[0666] Market data collection via servers

[0667] The server collects market data from multiple sources on the internet. During this process, the server periodically accesses a configured list of URLs, sending HTTP requests to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using analytical tools such as BeautifulSoup to extract the necessary market data. The extracted data is then stored in a database such as PostgreSQL.

[0668] Server-based data analysis and business option generation.

[0669] Next, the server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). Based on the analyzed data, it generates business options using generative AI models (e.g., GPT-3). The generated business options are then saved back into the database.

[0670] Displaying proposed options on devices and collecting feedback.

[0671] Users can log in to the system using their personal computers, smartphones, or other devices and view the generated business options. Users can then provide specific feedback on the displayed business options. For example, a user can provide feedback by entering "More cost reduction should be incorporated" into the feedback form and pressing the submit button.

[0672] Analysis of server-side feedback and revision of proposed options.

[0673] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). Useful information and areas for improvement are extracted from the feedback, and a generative AI model then modifies and generates new business options based on this information. The modified business options are saved back into the database and notified to the user via email or push notification.

[0674] Specific example

[0675] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback, stating that "more cost reduction should be incorporated." The generative AI analyzes this feedback and generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user.

[0676] This system efficiently executes a series of processes, from market data collection and business option generation to the collection and incorporation of user feedback. It also supports rapid decision-making and the development of optimal business strategies.

[0677] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0678] Step 1:

[0679] Market data collection

[0680] The server retrieves a pre-configured list of URLs and periodically sends HTTP requests to these URLs to retrieve the HTML content of web pages. The retrieved HTML content is analyzed using an analysis tool such as BeautifulSoup, and necessary market data such as "pricing information" and "sales trends" is extracted. The input is the URL list and the configured HTTP requests, and the output is the analyzed market data. The extracted market data is stored in a database such as PostgreSQL.

[0681] Step 2:

[0682] Data analysis and business option generation

[0683] The server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). The input is market data, and the output is market trends and consumer behavior patterns as analysis results. Based on these analysis results, a generative AI model (GPT-3) generates business options. These generated business options are also saved back into the database. The input is the analysis results of market trends, and the output is business options.

[0684] Step 3:

[0685] Display of option proposals

[0686] Users access the database using their own devices and log in to the system. Logged-in users can view the latest business options. The input is the user's authentication information, and the output is a display of the latest business options.

[0687] Step 4:

[0688] Provide feedback

[0689] Users provide specific feedback on the displayed business options. For example, a user might enter "More cost reductions should be implemented" into the feedback form and then press the submit button to provide feedback. The input is the user's feedback, and the output is the submission of the feedback data.

[0690] Step 5:

[0691] Feedback analysis

[0692] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). The input is the feedback data, and the output is useful information and suggestions for improvement extracted from the feedback.

[0693] Step 6:

[0694] Modification of the proposed options

[0695] The generative AI model modifies and regenerates business options based on extracted feedback information. The modified business options are also saved back to the database, and emails and push notifications are sent to users. The input is the feedback analysis results, and the output is the modified business options and notifications to users.

[0696] (Application Example 1)

[0697] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0698] Traditional e-commerce sites have struggled to efficiently propose products based on market trends, making it difficult to respond quickly to user needs. Furthermore, mechanisms for improving product recommendations based on user feedback are insufficient, potentially leading to decreased customer satisfaction. To address these challenges, a system is needed that effectively collects and analyzes market data, uses that data to make product recommendations, and quickly and effectively incorporates user feedback.

[0699] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0700] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback and modifying the business options, means for storing the modified options back in the database and notifying the user, means for generating product suggestions based on market trends, and means for improving product suggestions based on user feedback. This enables rapid and effective product suggestions based on market trends and improvement of product suggestions utilizing user feedback.

[0701] "Market data" refers to information related to the market, including consumer trends, competitor activities, and social media trends.

[0702] "Means of analysis" refers to methods and techniques for evaluating, comparing, and calculating collected market data, and transforming it into valuable information.

[0703] "Generative means" refers to methods and technologies for creating new business options and product proposals based on analyzed data.

[0704] A "database" refers to a system that systematically stores information such as generated options and feedback, making it accessible later.

[0705] "Feedback" refers to opinions, comments, and evaluations provided by users, which are used to improve business options and product proposals.

[0706] "Means of modification" refers to methods and technologies for changing and improving business options and product proposals based on user feedback.

[0707] "Means of notification" refers to methods and technologies for informing users of revised options or suggestions.

[0708] "Product proposals based on market trends" refers to proposing new products and services to users based on trends obtained by analyzing market data.

[0709] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to automatically generate optimal business options and product suggestions from market data.

[0710] A "prompt statement" refers to a document used to give instructions or questions to an AI model, and is used as a definition or guideline for the content that is generated.

[0711] This invention relates to a system that collects market data using the internet, generates business options using a generative AI model, and improves these options based on user feedback. Specific embodiments are described below.

[0712] Market data collection via servers

[0713] The server collects market data from multiple sources on the internet. Specifically, it periodically sends HTTP requests to a set list of URLs to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using tools such as BeautifulSoup to extract the necessary market data, which is then stored in a database.

[0714] example:

[0715] Assume the URL list includes "https: / / example.com / marketdata1" and "https: / / example.com / marketdata2". Periodically send HTTP requests to these URLs and extract market data from the retrieved HTML content, such as "Smartwatches are a popular product on review site A" or "Wireless earphones are a product with recent sales growth on competitor e-commerce site B".

[0716] Server-based data analysis and business option generation.

[0717] The server retrieves market data collected from the database and analyzes the data using a generative AI model. During this analysis process, it uses prompts such as the following:

[0718] Example of a prompt:

[0719] "Please generate business options based on the following market data:

[0720] Popular items on review site A are "smartwatches".

[0721] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[0722] The trend gaining attention on social media is "eco-friendly products."

[0723] The generated business options are stored in the database.

[0724] Displaying options via the device and collecting feedback

[0725] Users access the database using their own devices (e.g., smartphones or personal computers) and view the generated business options. In response, users can provide feedback such as specific opinions, comments, and suggestions for improvement.

[0726] example:

[0727] If a user provides feedback stating that "the options should include more eco-friendly products," this feedback will be stored in a database.

[0728] Server-based feedback analysis and option correction

[0729] The server extracts feedback provided by users and analyzes it using natural language processing technology. Based on this analysis, it identifies areas for improvement, and the generated AI model then creates newly modified business options.

[0730] Example of a prompt:

[0731] Please improve your business options based on the following feedback:

[0732] Feedback: The options should include more eco-friendly products.

[0733] The modified business options are saved back to the database and the user is notified.

[0734] Hardware and software use cases

[0735] The hardware required to run this system includes an internet-connected server (e.g., an Amazon EC2 instance) and user devices (e.g., a smartphone or personal computer). The software used includes Python scripts, an HTTP request library (e.g., requests), an HTML parsing tool (e.g., BeautifulSoup), a generative AI model (e.g., the OpenAI API), and a database management system (e.g., MySQL, PostgreSQL).

[0736] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0737] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0738] Step 1:

[0739] The server collects market data. At this stage, the server periodically sends HTTP requests to a configured list of URLs to retrieve the HTML content of the web pages. The retrieved HTML content is parsed using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. The extracted market data is stored in a database. The input consists of a URL list and HTTP requests, and the output is the parsed market data.

[0740] Step 2:

[0741] The server retrieves market data collected from the database and analyzes it using a generative AI model. During the analysis, it provides the generative AI model with prompt statements to generate business options. As a result, business options generated based on the analyzed data are output. These options are then saved back into the database. The input requires market data and prompt statements, and the output generates business options.

[0742] Step 3:

[0743] Users access the database using a terminal and view the generated business options. Here, users can review the options and provide feedback such as opinions, comments, and suggestions for improvement. This feedback is stored in the database. Business options are required as input, and user feedback is obtained as output.

[0744] Step 4:

[0745] The server retrieves feedback from the database and analyzes it using natural language processing technology. This analysis extracts information and areas for improvement from the feedback. Next, it generates prompt statements based on the extracted feedback information and provides them to a generation AI model to modify the business options. The modified business options are output, saved back to the database, and notified to the user. User feedback and prompt statements are required as input, and the output is modified business options.

[0746] Specific examples of operation

[0747] The server accesses URLs such as "https: / / example.com / marketdata1", retrieves and analyzes the HTML content, and extracts market data.

[0748] Add the analyzed market data to the following prompt:

[0749] "The most popular product on review site A is 'smartwatches'."

[0750] Provide prompt text to the generative AI model:

[0751] "Please generate business options based on the following market data:

[0752] Popular items on review site A are "smartwatches".

[0753] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[0754] The trend gaining attention on social media is "eco-friendly products."

[0755] Users use their devices to review business options and provide feedback such as, "The options should include more eco-friendly products."

[0756] The server analyzes the feedback and generates the following prompt:

[0757] Please improve your business options based on the following feedback:

[0758] Feedback: The options should include more eco-friendly products.

[0759] The above describes the specific processing steps and operations for implementing the system of the present invention.

[0760] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0761] This invention combines an emotion engine with a system that collects market data, generates business options using generative AI, and improves options by collecting and analyzing user feedback. By using the emotion engine throughout the process from market data collection to feedback analysis, it is possible to generate more effective business options that also take user emotions into account.

[0762] Market data collection via servers

[0763] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and an analysis tool is used to extract the necessary market data. The extracted market data is then stored in a database.

[0764] Server-based data analysis and business option generation.

[0765] The server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options, which are then stored in the database. Specific options include new business plans and marketing strategies based on market trends and consumer behavior analysis.

[0766] Displaying proposed options on devices and collecting feedback.

[0767] Users can use their own devices to view business options stored in the database. Users can provide feedback on the displayed options, including not only text comments but also sentiment.

[0768] Server-based feedback and emotion analysis

[0769] The server retrieves user-provided feedback from the database. In addition to analyzing the feedback using natural language processing technology, an emotion engine recognizes and analyzes the user's emotions during the feedback process. This allows for a more precise analysis that takes into account the emotions the user expressed during the feedback.

[0770] Server-based modification of business options

[0771] Based on the analysis results, the generative AI further refines the business options. In particular, the revisions take user emotions into consideration, aiming to improve the user experience. For example, if a user expresses dissatisfaction, the AI ​​will propose improvements to address that dissatisfaction. These new options are also stored in the database and notified to the user.

[0772] Specific example

[0773] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. A user views this option and comments that it "doesn't offer much in the way of savings," and the emotion engine then recognizes "disappointment" from the user's comment. The server analyzes this feedback and emotion, and uses generative AI to regenerate the option. This regeneration includes new energy-saving technologies and improvements that don't incur additional costs, addressing the user's "disappointment." This improved option is then saved back to the database and the user is notified, enabling a rapid improvement cycle.

[0774] Thus, the system of the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with a series of processes, from market data collection to option generation and analysis and reflection of user feedback.

[0775] The following describes the processing flow.

[0776] Step 1:

[0777] The server accesses a pre-configured list of URLs and sends an HTTP request to each URL. It then retrieves the HTML content of the web page.

[0778] Step 2:

[0779] The server retrieves HTML content, which is then analyzed using a parsing tool (such as BeautifulSoup) to identify tags and classes, and extract the necessary market data.

[0780] Step 3:

[0781] The server executes an SQL query to save the extracted market data to the database. This ensures that the data is stored systematically.

[0782] Step 4:

[0783] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes processes such as preprocessing and feature extraction.

[0784] Step 5:

[0785] The server uses the analyzed data to run a generative AI (e.g., GPT-3) and generate business options. Specific prompts are input to the generative AI, and the results are retrieved.

[0786] Step 6:

[0787] The server saves the generated business options to the database. SQL queries are used to insert the proposed options into the database.

[0788] Step 7:

[0789] The terminal retrieves business options from the database and displays them to the user. The user views the proposed options on the terminal.

[0790] Step 8:

[0791] Users provide feedback on the displayed business options. Users enter their feedback as text on their device.

[0792] Step 9:

[0793] The device acquires user feedback and analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions from text and generates data.

[0794] Step 10:

[0795] The device saves feedback and sentiment data to a database. SQL queries are used to save the data.

[0796] Step 11:

[0797] The server retrieves user feedback and sentiment data from the database and analyzes it using natural language processing techniques. This analysis identifies useful information and areas for improvement.

[0798] Step 12:

[0799] The server executes a generative AI based on the analysis results, modifying and regenerating business options. In particular, it creates new business plans that take user emotions into consideration.

[0800] Step 13:

[0801] The server saves the modified business options to the database and notifies the user. Notifications are sent via methods such as email or push notifications.

[0802] (Example 2)

[0803] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0804] Business options generated based on market data often fail to adequately consider user emotions and feedback, resulting in a lack of improved user experience and difficulty in formulating effective business strategies. Furthermore, if user feedback and emotions are not accurately analyzed and reflected in business options without prompt improvement, the business's competitiveness may decline.

[0805] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0806] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback using natural language processing technology and sentiment recognition technology, means for modifying the business options based on the analysis results, and means for storing the modified options back in the database and notifying the user. This enables the generation of effective business options that take user sentiment into account and the rapid incorporation of feedback.

[0807] "Market data" refers to information about market trends, product information, consumer behavior, and so on.

[0808] "Means of collection" refers to the function of obtaining data by sending an HTTP request from a specific URL on the internet and storing it in a database.

[0809] "Means of analysis" refer to techniques for processing and breaking down collected data to extract informational features and patterns.

[0810] "Means for generating business options" refers to the function of generating new business plans and marketing strategies based on analyzed market data.

[0811] "Generative AI" is an artificial intelligence technology that generates new information and ideas based on data.

[0812] A "database" is a system for organizing and storing collected and generated data and information.

[0813] "Feedback" refers to opinions such as evaluations and impressions of options provided by users.

[0814] "Natural language processing technology" is a technology that converts human language into a format that can be handled by computers and then analyzes it.

[0815] "Emotion recognition technology" is a technology that extracts and identifies emotions from users' text and comments.

[0816] This invention combines an emotion engine with a system that collects market data, generates business options using a generative AI model, and improves options by collecting user feedback. The following describes how this invention is specifically implemented.

[0817] Market data collection

[0818] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. Specifically, it uses analysis tools such as Beautiful Soup or Scrapy to parse the HTML content of the web pages and extract market data (e.g., new product information, market trends). The extracted data is stored in a database on the server.

[0819] Data analysis and business option generation

[0820] The server retrieves market data collected from the database and analyzes it using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI models such as GPT-4. These generated options, such as new business plans and marketing strategies, are also stored in the database.

[0821] Display of proposed options and collection of feedback.

[0822] The server sends business options stored in the database to the user's device (smartphone or PC), which then displays them. The user views the options and provides feedback, including text comments and sentiment. This feedback information is sent from the device to the server and stored in the database.

[0823] Feedback and emotion analysis

[0824] The server retrieves user-provided feedback from the database. It analyzes the text of the feedback using natural language processing techniques such as BERT and SpaCy, and recognizes and analyzes the user's emotions while they are providing the feedback using an Aspect-based Sentiment Analysis model.

[0825] Revision of business options

[0826] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The modified business options are further refined to take user sentiment into account. These new options are also stored in the database and notified to the user.

[0827] Specific example

[0828] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. Suppose a user sees this option and comments that it "doesn't offer much in the way of savings," and the emotion engine recognizes this as "disappointment." The server analyzes this feedback and emotion and uses a generative AI model to regenerate the option. This regeneration includes new energy-saving technologies and improvements that do not incur additional costs, in order to address the user's "disappointment." This improved option is then saved back to the database and the user is notified.

[0829] Example of a prompt

[0830] "Generate concrete ideas for improving energy-saving appliance management systems in the smart home market. User feedback indicates 'low savings' and their sentiment is 'disappointment.' Propose improvements that will satisfy users."

[0831] In this way, the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with processes ranging from market data collection to option generation, and from the collection, analysis, and reflection of user feedback.

[0832] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0833] Step 1: Collect market data

[0834] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The input is the list of market data URLs, and the output is the HTML content obtained from each URL. Specifically, the server uses tools like Beautiful Soup or Scrapy to parse the HTML content and extract market data (e.g., new product information, market trends). The extracted data is then stored in a database.

[0835] Step 2: Data analysis and business option generation

[0836] The server retrieves market data collected from a database. Its input is the stored market data, and its output is the data analysis results and generated business options. Specifically, the server analyzes the market data using machine learning models such as TensorFlow or PyTorch. Based on these results, it generates business options using generative AI models such as GPT-4. The generated options are stored in the database.

[0837] Step 3: Displaying proposed options and gathering feedback

[0838] The server sends business options stored in the database to the user's terminal. The input is the business option data in the database, and the output is the proposed options displayed on the user's terminal. Specifically, the user views the business options on their terminal (smartphone or PC) and provides feedback, including text comments and sentiment. This feedback information is sent from the terminal to the server and stored in the database.

[0839] Step 4: Feedback and emotional analysis

[0840] The server retrieves user-provided feedback from the database. The input is user-provided feedback data, and the output is the analysis results of the feedback and the sentiment recognition results. Specifically, the server uses natural language processing techniques such as BERT and SpaCy to analyze the feedback text and uses an Aspect-based Sentiment Analysis model to recognize and analyze the user's emotions.

[0841] Step 5: Modifying Business Options

[0842] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The input is feedback and sentiment analysis results, and the output is the modified business options. Specifically, the server considers the user's emotions and generates options that include specific improvements, such as addressing dissatisfaction. These new options are also stored in the database and notified to the user.

[0843] In this way, by having all steps work together in coordination, it becomes possible to formulate more effective business strategies and improve the user experience.

[0844] (Application Example 2)

[0845] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0846] Traditional systems for generating and improving business options based on market data failed to adequately improve user experience and customer satisfaction because they relied solely on numerical data and text feedback, without considering user emotions.

[0847] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting market information, means for analyzing the collected market information, means for generating business options based on the analyzed information, means for storing the generated options in an information repository, means for users to view the options and provide feedback including emotions, means for analyzing the provided feedback including emotions and modifying the business options, and means for storing the modified options in the information repository again and notifying the user. This enables the generation of more effective business options that take user emotions into consideration and a rapid improvement cycle.

[0848] "Market information" refers to data and information about the market, such as consumer behavior and trends, and the activities of competitors.

[0849] "Analyzing" refers to the process of processing collected market information and feedback to extract meaningful insights.

[0850] "Business options" refer to new business plans and marketing strategies proposed based on the analysis of market information.

[0851] An "information repository" refers to a database used to store generated business options, collected market information, feedback, and other data.

[0852] "Users" refers to individuals or organizations that use the system to view business options and provide feedback.

[0853] "Feedback that includes emotion" refers to the emotional elements contained within the opinions and comments provided by users.

[0854] An "emotion analysis engine" refers to a technology that analyzes the emotions of the feedback provided and recognizes the user's emotional state.

[0855] A "learning model" refers to a machine learning algorithm that analyzes collected market information and generates business options based on that analysis.

[0856] The system implementing this invention has a process for collecting market information, generating business options based on that information, collecting and analyzing feedback from users, including emotional feedback, and further modifying and improving the business options using the results. The specific process is shown below.

[0857] 1. Gathering market information

[0858] The server accesses a pre-configured list of market information URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and analysis tools such as BeautifulSoup are used to extract the necessary market information. The extracted market information is then stored in an information repository.

[0859] 2. Data analysis and business option generation

[0860] The server retrieves market information collected from the data repository and analyzes the data using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI (e.g., GPT-4). These options are also stored in the data repository.

[0861] 3. Displaying business options and collecting feedback, including sentiment.

[0862] Users view business options stored in the information vault using devices such as smartphones and smart glasses. Users provide feedback on the displayed options, including their emotions. This feedback, including emotions, is also stored in the information vault.

[0863] 4. Feedback and Sentiment Analysis

[0864] The server retrieves user-provided feedback from the data repository and uses natural language processing technologies (e.g., SpaCy and NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer to recognize and analyze the user's emotions during the feedback process.

[0865] 5. Revision of business options

[0866] Based on the analysis of feedback, the server uses generative AI to regenerate business options. In particular, modifications are made that take user emotions into consideration, thereby improving the user experience. The modified business options are then saved again to the information repository, and users are notified.

[0867] Specific example

[0868] For example, suppose market data is collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "Energy-Saving Home Appliance Management System" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[0869] Example of a prompt

[0870] User feedback: "This ad is very ordinary and doesn't convey any passion." Emotions detected: "Disappointed." Modify the following ad campaign to better address user concerns: "Eco-friendly new products! (Energy-saving appliances) will support your home."

[0871] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0872] Step 1:

[0873] The server accesses a pre-configured list of market information URLs and sends an HTTP request to each URL. The input is the URL list, and the output is the HTML content of each web page. The HTML content is retrieved, and the necessary market information is extracted using an analysis tool such as BeautifulSoup. The extracted information is stored in the market information repository.

[0874] Step 2:

[0875] The server retrieves market information collected from the market information repository. The input is the market information stored in the repository, and the output is data converted into an analyzable format. This data is analyzed using machine learning models such as TensorFlow or PyTorch. Based on the analysis results, a generative AI (e.g., GPT-4) generates business options. The generated options are stored in the information repository.

[0876] Step 3:

[0877] The terminal accesses the information vault and displays the generated business options. Users view the options using smartphones, smart glasses, etc. The input is the business options stored in the information vault, and the output is the options displayed on the terminal. Users provide feedback on the displayed options. This feedback includes text comments and sentiment information.

[0878] Step 4:

[0879] The server retrieves user-provided feedback from the data repository. The input is the feedback stored in the data repository, and the output is analyzable feedback data. Natural language processing techniques (e.g., SpaCy or NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer are used to recognize and analyze the user's emotions during feedback.

[0880] Step 5:

[0881] The server uses generative AI to regenerate business options based on the analysis results. The input is the analysis results and the original business options, and the output is the improved business options. In particular, modifications are made to take user sentiment into consideration, and the newly generated business options are saved again in the information repository.

[0882] Step 6:

[0883] The terminal accesses the information vault, displays improved business options, and notifies the user. The input is the improved business options, and the output is the improved options displayed on the terminal and the notification to the user. This allows the user to review the new business options and provide further feedback as needed.

[0884] Specific examples of operation:

[0885] For example, market data might be collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "energy-saving home appliance management system" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[0886] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0887] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0888] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0889] [Fourth Embodiment]

[0890] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0891] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0892] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0893] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0894] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0895] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0896] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0897] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0898] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0899] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0900] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0901] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0902] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0903] This invention relates to a system that collects market data, generates business options using generative AI, and improves the options by collecting feedback from users. This system collects market data via the internet and analyzes the data using machine learning models. Based on the analyzed data, the generative AI generates business options and stores them in a database. Users can view the business options using their devices and provide feedback. The provided feedback is analyzed using natural language processing technology, and the options are modified. These modified options are also stored in the database and the user is notified.

[0904] Market data collection via servers

[0905] The server collects market data from multiple sources on the internet. Specifically, it periodically accesses a set list of URLs, sends HTTP requests, and retrieves the HTML content of web pages. Then, it uses analysis tools to extract the necessary market data from the HTML content and stores it in a database.

[0906] Server-based data analysis and business option generation.

[0907] Next, the server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options. For example, it analyzes specific market trends and consumer behavior patterns and proposes business plans and marketing strategies based on that information. The generated business options are then saved back into the database.

[0908] Displaying proposed options on devices and collecting feedback.

[0909] Users can access the database using their own devices and view the generated business options. Users can then provide feedback on the displayed options. This feedback includes specific opinions, comments, and suggestions for improvement.

[0910] Analysis of server-side feedback and revision of proposed options.

[0911] The server retrieves user feedback from the database and analyzes it using natural language processing technology. This analysis identifies useful information and areas for improvement based on user feedback. Based on the analysis results, a generative AI modifies the business options again and generates new option proposals. These modified options are saved back to the database and notified to the user.

[0912] Specific example

[0913] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback that "more cost reductions should be incorporated." Analyzing this feedback, the generative AI generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user, enabling a rapid improvement cycle.

[0914] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[0915] The following describes the processing flow.

[0916] Step 1:

[0917] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page.

[0918] Step 2:

[0919] The server analyzes the acquired HTML content using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. Specifically, text and numerical data are extracted using certain tags and classes.

[0920] Step 3:

[0921] The server saves the extracted market data to a database. The saving method uses a database interface (e.g., SQL).

[0922] Step 4:

[0923] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes data preprocessing, feature extraction, and model application.

[0924] Step 5:

[0925] Based on the data analyzed by the server, a generative AI (e.g., GPT-3) generates business options. The generation process proposes specific business plans that take into account the business environment and market trends.

[0926] Step 6:

[0927] The server saves the generated business options to the database.

[0928] Step 7:

[0929] The terminal retrieves business options stored in the database and displays them to the user. The user views the business options on the terminal and provides ratings and comments.

[0930] Step 8:

[0931] The device receives the feedback provided by the user and saves it to a database.

[0932] Step 9:

[0933] The server retrieves user feedback from the database and analyzes it using natural language processing techniques. The analysis extracts useful information and areas for improvement from the feedback.

[0934] Step 10:

[0935] Based on the analysis results, the server uses generative AI again to modify existing business options. New options are generated, and a revised business plan reflecting the improvements is proposed again.

[0936] Step 11:

[0937] The server will save the modified business options back to the database and notify the user. The notification will be sent via email, push notification, or other means.

[0938] (Example 1)

[0939] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0940] Traditional processes for generating and improving business options based on market data often involved manual analysis and were inefficient. Furthermore, it was difficult to quickly incorporate user feedback, making it challenging to consistently provide optimal business options. Therefore, there is a need to efficiently manage the entire process, from market data collection to the generation and refinement of business options, using automated systems, thereby enabling rapid decision-making and the development of appropriate business strategies.

[0941] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0942] In this invention, the server includes means for collecting market data from multiple information sources on the internet, means for analyzing the collected market data using an analysis tool, means for generating business options based on the analyzed data using a generative AI model, means for storing the generated options in a database, means for users to view the options using their own terminals and provide feedback, means for analyzing the provided feedback using natural language processing technology and modifying the business options, and means for storing the modified options back in the database and notifying the user. This makes it possible to consistently and automatically and efficiently perform everything from collecting market data to generating business options and modifying the options based on feedback.

[0943] "Multiple sources of information on the internet" refers to a collection of information accessible via the internet, such as numerous websites and online databases.

[0944] "Market data" refers to any information related to a specific market, including price information, sales trends, consumer behavior, and other data.

[0945] "Analysis tools" refer to software and libraries used to extract and analyze data. For example, BeautifulSoup is used for HTML parsing.

[0946] "Generative AI models" refer to artificial intelligence models used to generate business options and proposals. Specifically, this includes natural language generation models such as GPT-3.

[0947] "Business options" refer to business proposals and strategies generated based on the analysis of market data.

[0948] A "database" refers to a system for systematically storing and managing collected data and generated options. Examples include relational databases such as PostgreSQL.

[0949] A "terminal" refers to an electronic device, such as a computer or smartphone, that a user uses to access a system.

[0950] "Feedback" refers to information such as opinions, comments, and suggestions for improvement provided by users.

[0951] "Natural language processing technology" refers to technologies that analyze user feedback and convert it into meaningful information. Specifically, this includes technologies such as NLTK and Spacy.

[0952] This invention is a system that collects market data, generates business options using a generative AI model, and improves the options by collecting feedback from users. This system consists of three main elements: a server, a terminal, and a user.

[0953] Market data collection via servers

[0954] The server collects market data from multiple sources on the internet. During this process, the server periodically accesses a configured list of URLs, sending HTTP requests to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using analytical tools such as BeautifulSoup to extract the necessary market data. The extracted data is then stored in a database such as PostgreSQL.

[0955] Server-based data analysis and business option generation.

[0956] Next, the server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). Based on the analyzed data, it generates business options using generative AI models (e.g., GPT-3). The generated business options are then saved back into the database.

[0957] Displaying proposed options on devices and collecting feedback.

[0958] Users can log in to the system using their personal computers, smartphones, or other devices and view the generated business options. Users can then provide specific feedback on the displayed business options. For example, a user can provide feedback by entering "More cost reduction should be incorporated" into the feedback form and pressing the submit button.

[0959] Analysis of server-side feedback and revision of proposed options.

[0960] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). Useful information and areas for improvement are extracted from the feedback, and a generative AI model then modifies and generates new business options based on this information. The modified business options are saved back into the database and notified to the user via email or push notification.

[0961] Specific example

[0962] For example, suppose a server collects data on the "smart city" market. This data includes residents' lifestyles, traffic patterns, and energy consumption. Based on this data, a generative AI generates a business option: "A new smart grid system for improved energy efficiency." A user sees this option and provides feedback, stating that "more cost reduction should be incorporated." The generative AI analyzes this feedback and generates a new smart grid system option that further considers cost efficiency. This new option is then saved back to the database and notified to the user.

[0963] This system efficiently executes a series of processes, from market data collection and business option generation to the collection and incorporation of user feedback. It also supports rapid decision-making and the development of optimal business strategies.

[0964] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0965] Step 1:

[0966] Market data collection

[0967] The server retrieves a pre-configured list of URLs and periodically sends HTTP requests to these URLs to retrieve the HTML content of web pages. The retrieved HTML content is analyzed using an analysis tool such as BeautifulSoup, and necessary market data such as "pricing information" and "sales trends" is extracted. The input is the URL list and the configured HTTP requests, and the output is the analyzed market data. The extracted market data is stored in a database such as PostgreSQL.

[0968] Step 2:

[0969] Data analysis and business option generation

[0970] The server retrieves market data collected from the database and analyzes it using machine learning models (e.g., TensorFlow or Scikit-learn). The input is market data, and the output is market trends and consumer behavior patterns as analysis results. Based on these analysis results, a generative AI model (GPT-3) generates business options. These generated business options are also saved back into the database. The input is the analysis results of market trends, and the output is business options.

[0971] Step 3:

[0972] Display of option proposals

[0973] Users access the database using their own devices and log in to the system. Logged-in users can view the latest business options. The input is the user's authentication information, and the output is a display of the latest business options.

[0974] Step 4:

[0975] Provide feedback

[0976] Users provide specific feedback on the displayed business options. For example, a user might enter "More cost reductions should be implemented" into the feedback form and then press the submit button to provide feedback. The input is the user's feedback, and the output is the submission of the feedback data.

[0977] Step 5:

[0978] Feedback analysis

[0979] The server retrieves user feedback from a database and analyzes it using natural language processing techniques (e.g., NLTK or Spacy). The input is the feedback data, and the output is useful information and suggestions for improvement extracted from the feedback.

[0980] Step 6:

[0981] Modification of the proposed options

[0982] The generative AI model modifies and regenerates business options based on extracted feedback information. The modified business options are also saved back to the database, and emails and push notifications are sent to users. The input is the feedback analysis results, and the output is the modified business options and notifications to users.

[0983] (Application Example 1)

[0984] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0985] Traditional e-commerce sites have struggled to efficiently propose products based on market trends, making it difficult to respond quickly to user needs. Furthermore, mechanisms for improving product recommendations based on user feedback are insufficient, potentially leading to decreased customer satisfaction. To address these challenges, a system is needed that effectively collects and analyzes market data, uses that data to make product recommendations, and quickly and effectively incorporates user feedback.

[0986] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0987] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback and modifying the business options, means for storing the modified options back in the database and notifying the user, means for generating product suggestions based on market trends, and means for improving product suggestions based on user feedback. This enables rapid and effective product suggestions based on market trends and improvement of product suggestions utilizing user feedback.

[0988] "Market data" refers to information related to the market, including consumer trends, competitor activities, and social media trends.

[0989] "Means of analysis" refers to methods and techniques for evaluating, comparing, and calculating collected market data, and transforming it into valuable information.

[0990] "Generative means" refers to methods and technologies for creating new business options and product proposals based on analyzed data.

[0991] A "database" refers to a system that systematically stores information such as generated options and feedback, making it accessible later.

[0992] "Feedback" refers to opinions, comments, and evaluations provided by users, which are used to improve business options and product proposals.

[0993] "Means of modification" refers to methods and technologies for changing and improving business options and product proposals based on user feedback.

[0994] "Means of notification" refers to methods and technologies for informing users of revised options or suggestions.

[0995] "Product proposals based on market trends" refers to proposing new products and services to users based on trends obtained by analyzing market data.

[0996] A "generative AI model" refers to an artificial intelligence model that uses machine learning techniques to automatically generate optimal business options and product suggestions from market data.

[0997] A "prompt statement" refers to a document used to give instructions or questions to an AI model, and is used as a definition or guideline for the content that is generated.

[0998] This invention relates to a system that collects market data using the internet, generates business options using a generative AI model, and improves these options based on user feedback. Specific embodiments are described below.

[0999] Market data collection via servers

[1000] The server collects market data from multiple sources on the internet. Specifically, it periodically sends HTTP requests to a set list of URLs to retrieve the HTML content of web pages. The retrieved HTML content is then analyzed using tools such as BeautifulSoup to extract the necessary market data, which is then stored in a database.

[1001] example:

[1002] Assume the URL list includes "https: / / example.com / marketdata1" and "https: / / example.com / marketdata2". Periodically send HTTP requests to these URLs and extract market data from the retrieved HTML content, such as "Smartwatches are a popular product on review site A" or "Wireless earphones are a product with recent sales growth on competitor e-commerce site B".

[1003] Server-based data analysis and business option generation.

[1004] The server retrieves market data collected from the database and analyzes the data using a generative AI model. During this analysis process, it uses prompts such as the following:

[1005] Example of a prompt:

[1006] "Please generate business options based on the following market data:

[1007] Popular items on review site A are "smartwatches".

[1008] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[1009] The trend gaining attention on social media is "eco-friendly products."

[1010] The generated business options are stored in the database.

[1011] Displaying options via the device and collecting feedback

[1012] Users access the database using their own devices (e.g., smartphones or personal computers) and view the generated business options. In response, users can provide feedback such as specific opinions, comments, and suggestions for improvement.

[1013] example:

[1014] If a user provides feedback stating that "the options should include more eco-friendly products," this feedback will be stored in a database.

[1015] Server-based feedback analysis and option correction

[1016] The server extracts feedback provided by users and analyzes it using natural language processing technology. Based on this analysis, it identifies areas for improvement, and the generated AI model then creates newly modified business options.

[1017] Example of a prompt:

[1018] Please improve your business options based on the following feedback:

[1019] Feedback: The options should include more eco-friendly products.

[1020] The modified business options are saved back to the database and the user is notified.

[1021] Hardware and software use cases

[1022] The hardware required to run this system includes an internet-connected server (e.g., an Amazon EC2 instance) and user devices (e.g., a smartphone or personal computer). The software used includes Python scripts, an HTTP request library (e.g., requests), an HTML parsing tool (e.g., BeautifulSoup), a generative AI model (e.g., the OpenAI API), and a database management system (e.g., MySQL, PostgreSQL).

[1023] Thus, the system of the present invention can efficiently execute a series of processes, from collecting market data to generating business options and analyzing and incorporating user feedback, thereby supporting rapid decision-making and the formulation of optimal business strategies.

[1024] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1025] Step 1:

[1026] The server collects market data. At this stage, the server periodically sends HTTP requests to a configured list of URLs to retrieve the HTML content of the web pages. The retrieved HTML content is parsed using an analysis tool (e.g., BeautifulSoup) to extract the necessary market data. The extracted market data is stored in a database. The input consists of a URL list and HTTP requests, and the output is the parsed market data.

[1027] Step 2:

[1028] The server retrieves market data collected from the database and analyzes it using a generative AI model. During the analysis, it provides the generative AI model with prompt statements to generate business options. As a result, business options generated based on the analyzed data are output. These options are then saved back into the database. The input requires market data and prompt statements, and the output generates business options.

[1029] Step 3:

[1030] Users access the database using a terminal and view the generated business options. Here, users can review the options and provide feedback such as opinions, comments, and suggestions for improvement. This feedback is stored in the database. Business options are required as input, and user feedback is obtained as output.

[1031] Step 4:

[1032] The server retrieves feedback from the database and analyzes it using natural language processing technology. This analysis extracts information and areas for improvement from the feedback. Next, it generates prompt statements based on the extracted feedback information and provides them to a generation AI model to modify the business options. The modified business options are output, saved back to the database, and notified to the user. User feedback and prompt statements are required as input, and the output is modified business options.

[1033] Specific examples of operation

[1034] The server accesses URLs such as "https: / / example.com / marketdata1", retrieves and analyzes the HTML content, and extracts market data.

[1035] Add the analyzed market data to the following prompt:

[1036] "The most popular product on review site A is 'smartwatches'."

[1037] Provide prompt text to the generative AI model:

[1038] "Please generate business options based on the following market data:

[1039] Popular items on review site A are "smartwatches".

[1040] The product that has seen a recent increase in sales at competitor e-commerce site B is "wireless earphones."

[1041] The trend gaining attention on social media is "eco-friendly products."

[1042] Users use their devices to review business options and provide feedback such as, "The options should include more eco-friendly products."

[1043] The server analyzes the feedback and generates the following prompt:

[1044] Please improve your business options based on the following feedback:

[1045] Feedback: The options should include more eco-friendly products.

[1046] The above describes the specific processing steps and operations for implementing the system of the present invention.

[1047] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1048] This invention combines an emotion engine with a system that collects market data, generates business options using generative AI, and improves options by collecting and analyzing user feedback. By using the emotion engine throughout the process from market data collection to feedback analysis, it is possible to generate more effective business options that also take user emotions into account.

[1049] Market data collection via servers

[1050] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and an analysis tool is used to extract the necessary market data. The extracted market data is then stored in a database.

[1051] Server-based data analysis and business option generation.

[1052] The server retrieves market data collected from the database and analyzes it using a machine learning model. Based on the analysis results, a generative AI generates business options, which are then stored in the database. Specific options include new business plans and marketing strategies based on market trends and consumer behavior analysis.

[1053] Displaying proposed options on devices and collecting feedback.

[1054] Users can use their own devices to view business options stored in the database. Users can provide feedback on the displayed options, including not only text comments but also sentiment.

[1055] Server-based feedback and emotion analysis

[1056] The server retrieves user-provided feedback from the database. In addition to analyzing the feedback using natural language processing technology, an emotion engine recognizes and analyzes the user's emotions during the feedback process. This allows for a more precise analysis that takes into account the emotions the user expressed during the feedback.

[1057] Server-based modification of business options

[1058] Based on the analysis results, the generative AI further refines the business options. In particular, the revisions take user emotions into consideration, aiming to improve the user experience. For example, if a user expresses dissatisfaction, the AI ​​will propose improvements to address that dissatisfaction. These new options are also stored in the database and notified to the user.

[1059] Specific example

[1060] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. A user views this option and comments that it "doesn't offer much in the way of savings," and the emotion engine then recognizes "disappointment" from the user's comment. The server analyzes this feedback and emotion, and uses generative AI to regenerate the option. This regeneration includes new energy-saving technologies and improvements that don't incur additional costs, addressing the user's "disappointment." This improved option is then saved back to the database and the user is notified, enabling a rapid improvement cycle.

[1061] Thus, the system of the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with a series of processes, from market data collection to option generation and analysis and reflection of user feedback.

[1062] The following describes the processing flow.

[1063] Step 1:

[1064] The server accesses a pre-configured list of URLs and sends an HTTP request to each URL. It then retrieves the HTML content of the web page.

[1065] Step 2:

[1066] The server retrieves HTML content, which is then analyzed using a parsing tool (such as BeautifulSoup) to identify tags and classes, and extract the necessary market data.

[1067] Step 3:

[1068] The server executes an SQL query to save the extracted market data to the database. This ensures that the data is stored systematically.

[1069] Step 4:

[1070] The server retrieves market data collected from the database and analyzes the data using a machine learning model. This analysis includes processes such as preprocessing and feature extraction.

[1071] Step 5:

[1072] The server uses the analyzed data to run a generative AI (e.g., GPT-3) and generate business options. Specific prompts are input to the generative AI, and the results are retrieved.

[1073] Step 6:

[1074] The server saves the generated business options to the database. SQL queries are used to insert the proposed options into the database.

[1075] Step 7:

[1076] The terminal retrieves business options from the database and displays them to the user. The user views the proposed options on the terminal.

[1077] Step 8:

[1078] Users provide feedback on the displayed business options. Users enter their feedback as text on their device.

[1079] Step 9:

[1080] The device acquires user feedback and analyzes the user's emotions using an emotion engine. The emotion engine recognizes emotions from text and generates data.

[1081] Step 10:

[1082] The device saves feedback and sentiment data to a database. SQL queries are used to save the data.

[1083] Step 11:

[1084] The server retrieves user feedback and sentiment data from the database and analyzes it using natural language processing techniques. This analysis identifies useful information and areas for improvement.

[1085] Step 12:

[1086] The server executes a generative AI based on the analysis results, modifying and regenerating business options. In particular, it creates new business plans that take user emotions into consideration.

[1087] Step 13:

[1088] The server saves the modified business options to the database and notifies the user. Notifications are sent via methods such as email or push notifications.

[1089] (Example 2)

[1090] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1091] Business options generated based on market data often fail to adequately consider user emotions and feedback, resulting in a lack of improved user experience and difficulty in formulating effective business strategies. Furthermore, if user feedback and emotions are not accurately analyzed and reflected in business options without prompt improvement, the business's competitiveness may decline.

[1092] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1093] In this invention, the server includes means for collecting market data, means for analyzing the collected market data, means for generating business options based on the analyzed data, means for storing the generated options in a database, means for users to view the options and provide feedback, means for analyzing the provided feedback using natural language processing technology and sentiment recognition technology, means for modifying the business options based on the analysis results, and means for storing the modified options back in the database and notifying the user. This enables the generation of effective business options that take user sentiment into account and the rapid incorporation of feedback.

[1094] "Market data" refers to information about market trends, product information, consumer behavior, and so on.

[1095] "Means of collection" refers to the function of obtaining data by sending an HTTP request from a specific URL on the internet and storing it in a database.

[1096] "Means of analysis" refer to techniques for processing and breaking down collected data to extract informational features and patterns.

[1097] "Means for generating business options" refers to the function of generating new business plans and marketing strategies based on analyzed market data.

[1098] "Generative AI" is an artificial intelligence technology that generates new information and ideas based on data.

[1099] A "database" is a system for organizing and storing collected and generated data and information.

[1100] "Feedback" refers to opinions such as evaluations and impressions of options provided by users.

[1101] "Natural language processing technology" is a technology that converts human language into a format that can be handled by computers and then analyzes it.

[1102] "Emotion recognition technology" is a technology that extracts and identifies emotions from users' text and comments.

[1103] This invention combines an emotion engine with a system that collects market data, generates business options using a generative AI model, and improves options by collecting user feedback. The following describes how this invention is specifically implemented.

[1104] Market data collection

[1105] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. Specifically, it uses analysis tools such as Beautiful Soup or Scrapy to parse the HTML content of the web pages and extract market data (e.g., new product information, market trends). The extracted data is stored in a database on the server.

[1106] Data analysis and business option generation

[1107] The server retrieves market data collected from the database and analyzes it using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI models such as GPT-4. These generated options, such as new business plans and marketing strategies, are also stored in the database.

[1108] Display of proposed options and collection of feedback.

[1109] The server sends business options stored in the database to the user's device (smartphone or PC), which then displays them. The user views the options and provides feedback, including text comments and sentiment. This feedback information is sent from the device to the server and stored in the database.

[1110] Feedback and emotion analysis

[1111] The server retrieves user-provided feedback from the database. It analyzes the text of the feedback using natural language processing techniques such as BERT and SpaCy, and recognizes and analyzes the user's emotions while they are providing the feedback using an Aspect-based Sentiment Analysis model.

[1112] Revision of business options

[1113] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The modified business options are further refined to take user sentiment into account. These new options are also stored in the database and notified to the user.

[1114] Specific example

[1115] For example, suppose a server collects data on the "smart home" market and generates a business option called "energy-saving appliance management system" based on this data. Suppose a user sees this option and comments that it "doesn't offer much in the way of savings," and the emotion engine recognizes this as "disappointment." The server analyzes this feedback and emotion and uses a generative AI model to regenerate the option. This regeneration includes new energy-saving technologies and improvements that do not incur additional costs, in order to address the user's "disappointment." This improved option is then saved back to the database and the user is notified.

[1116] Example of a prompt

[1117] "Generate concrete ideas for improving energy-saving appliance management systems in the smart home market. User feedback indicates 'low savings' and their sentiment is 'disappointment.' Propose improvements that will satisfy users."

[1118] In this way, the present invention improves the user experience and supports the formulation of more effective business strategies by combining an emotion engine with processes ranging from market data collection to option generation, and from the collection, analysis, and reflection of user feedback.

[1119] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1120] Step 1: Collect market data

[1121] The server accesses a pre-configured list of market data URLs and sends an HTTP request to each URL. The input is the list of market data URLs, and the output is the HTML content obtained from each URL. Specifically, the server uses tools like Beautiful Soup or Scrapy to parse the HTML content and extract market data (e.g., new product information, market trends). The extracted data is then stored in a database.

[1122] Step 2: Data analysis and business option generation

[1123] The server retrieves market data collected from a database. Its input is the stored market data, and its output is the data analysis results and generated business options. Specifically, the server analyzes the market data using machine learning models such as TensorFlow or PyTorch. Based on these results, it generates business options using generative AI models such as GPT-4. The generated options are stored in the database.

[1124] Step 3: Displaying proposed options and gathering feedback

[1125] The server sends business options stored in the database to the user's terminal. The input is the business option data in the database, and the output is the proposed options displayed on the user's terminal. Specifically, the user views the business options on their terminal (smartphone or PC) and provides feedback, including text comments and sentiment. This feedback information is sent from the terminal to the server and stored in the database.

[1126] Step 4: Feedback and emotional analysis

[1127] The server retrieves user-provided feedback from the database. The input is user-provided feedback data, and the output is the analysis results of the feedback and the sentiment recognition results. Specifically, the server uses natural language processing techniques such as BERT and SpaCy to analyze the feedback text and uses an Aspect-based Sentiment Analysis model to recognize and analyze the user's emotions.

[1128] Step 5: Modifying Business Options

[1129] The server uses a generative AI model to regenerate and modify business options based on user feedback and sentiment analysis results. The input is feedback and sentiment analysis results, and the output is the modified business options. Specifically, the server considers the user's emotions and generates options that include specific improvements, such as addressing dissatisfaction. These new options are also stored in the database and notified to the user.

[1130] In this way, by having all steps work together in coordination, it becomes possible to formulate more effective business strategies and improve the user experience.

[1131] (Application Example 2)

[1132] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1133] Traditional systems for generating and improving business options based on market data failed to adequately improve user experience and customer satisfaction because they relied solely on numerical data and text feedback, without considering user emotions.

[1134] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for collecting market information, means for analyzing the collected market information, means for generating business options based on the analyzed information, means for storing the generated options in an information repository, means for users to view the options and provide feedback including emotions, means for analyzing the provided feedback including emotions and modifying the business options, and means for storing the modified options in the information repository again and notifying the user. This enables the generation of more effective business options that take user emotions into consideration and a rapid improvement cycle.

[1135] "Market information" refers to data and information about the market, such as consumer behavior and trends, and the activities of competitors.

[1136] "Analyzing" refers to the process of processing collected market information and feedback to extract meaningful insights.

[1137] "Business options" refer to new business plans and marketing strategies proposed based on the analysis of market information.

[1138] An "information repository" refers to a database used to store generated business options, collected market information, feedback, and other data.

[1139] "Users" refers to individuals or organizations that use the system to view business options and provide feedback.

[1140] "Feedback that includes emotion" refers to the emotional elements contained within the opinions and comments provided by users.

[1141] An "emotion analysis engine" refers to a technology that analyzes the emotions of the feedback provided and recognizes the user's emotional state.

[1142] A "learning model" refers to a machine learning algorithm that analyzes collected market information and generates business options based on that analysis.

[1143] The system implementing this invention has a process for collecting market information, generating business options based on that information, collecting and analyzing feedback from users, including emotional feedback, and further modifying and improving the business options using the results. The specific process is shown below.

[1144] 1. Gathering market information

[1145] The server accesses a pre-configured list of market information URLs and sends an HTTP request to each URL. The HTTP request retrieves the HTML content of the web page, and analysis tools such as BeautifulSoup are used to extract the necessary market information. The extracted market information is then stored in an information repository.

[1146] 2. Data analysis and business option generation

[1147] The server retrieves market information collected from the data repository and analyzes the data using machine learning models such as TensorFlow and PyTorch. Based on the analysis results, it generates business options using generative AI (e.g., GPT-4). These options are also stored in the data repository.

[1148] 3. Displaying business options and collecting feedback, including sentiment.

[1149] Users view business options stored in the information vault using devices such as smartphones and smart glasses. Users provide feedback on the displayed options, including their emotions. This feedback, including emotions, is also stored in the information vault.

[1150] 4. Feedback and Sentiment Analysis

[1151] The server retrieves user-provided feedback from the data repository and uses natural language processing technologies (e.g., SpaCy and NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer to recognize and analyze the user's emotions during the feedback process.

[1152] 5. Revision of business options

[1153] Based on the analysis of feedback, the server uses generative AI to regenerate business options. In particular, modifications are made that take user emotions into consideration, thereby improving the user experience. The modified business options are then saved again to the information repository, and users are notified.

[1154] Specific example

[1155] For example, suppose market data is collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "Energy-Saving Home Appliance Management System" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[1156] Example of a prompt

[1157] User feedback: "This ad is very ordinary and doesn't convey any passion." Emotions detected: "Disappointed." Modify the following ad campaign to better address user concerns: "Eco-friendly new products! (Energy-saving appliances) will support your home."

[1158] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1159] Step 1:

[1160] The server accesses a pre-configured list of market information URLs and sends an HTTP request to each URL. The input is the URL list, and the output is the HTML content of each web page. The HTML content is retrieved, and the necessary market information is extracted using an analysis tool such as BeautifulSoup. The extracted information is stored in the market information repository.

[1161] Step 2:

[1162] The server retrieves market information collected from the market information repository. The input is the market information stored in the repository, and the output is data converted into an analyzable format. This data is analyzed using machine learning models such as TensorFlow or PyTorch. Based on the analysis results, a generative AI (e.g., GPT-4) generates business options. The generated options are stored in the information repository.

[1163] Step 3:

[1164] The terminal accesses the information vault and displays the generated business options. Users view the options using smartphones, smart glasses, etc. The input is the business options stored in the information vault, and the output is the options displayed on the terminal. Users provide feedback on the displayed options. This feedback includes text comments and sentiment information.

[1165] Step 4:

[1166] The server retrieves user-provided feedback from the data repository. The input is the feedback stored in the data repository, and the output is analyzable feedback data. Natural language processing techniques (e.g., SpaCy or NLTK) and sentiment analysis engines such as IBM Watson's Tone Analyzer are used to recognize and analyze the user's emotions during feedback.

[1167] Step 5:

[1168] The server uses generative AI to regenerate business options based on the analysis results. The input is the analysis results and the original business options, and the output is the improved business options. In particular, modifications are made to take user sentiment into consideration, and the newly generated business options are saved again in the information repository.

[1169] Step 6:

[1170] The terminal accesses the information vault, displays improved business options, and notifies the user. The input is the improved business options, and the output is the improved options displayed on the terminal and the notification to the user. This allows the user to review the new business options and provide further feedback as needed.

[1171] Specific examples of operation:

[1172] For example, market data might be collected indicating that "the trend towards eco-friendly products is increasing," and based on this data, a business option called "energy-saving home appliance management system" is generated. If a user sees this option and comments, "This ad is very bland and lacks passion," and the sentiment analysis engine further recognizes "disappointment," the server analyzes this feedback and sentiment, uses generative AI to regenerate the option, and proposes an improved ad such as, "New eco-friendly product! (Energy-saving appliances) will support your home." This new option is again saved in the information repository and notified to the user.

[1173] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1174] The data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One 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">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1175] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1177] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1183] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1184] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1185] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1186] 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.

[1187] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1188] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1189] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1190] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1191] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1194] The following is further disclosed regarding the embodiments described above.

[1195] (Claim 1)

[1196] Means of collecting market data,

[1197] Means for analyzing collected market data,

[1198] A means of generating business options based on the analyzed data,

[1199] A means of saving the generated options to a database,

[1200] A means for users to view options and provide feedback,

[1201] A means of analyzing the feedback provided and modifying business options,

[1202] A means to save the modified options back into the database and notify the user,

[1203] A system that includes this.

[1204] (Claim 2)

[1205] The system according to claim 1, comprising means for automatically generating the generated business options using a machine learning model.

[1206] (Claim 3)

[1207] The system according to claim 1, comprising means for analyzing the provided feedback using natural language processing technology.

[1208] "Example 1"

[1209] (Claim 1)

[1210] Means of collecting market data from multiple sources on the internet,

[1211] A means of analyzing collected market data using analytical tools,

[1212] A means of generating business options using a generative AI model based on analyzed data,

[1213] A means of saving the generated options to a database,

[1214] A means for users to view options and provide feedback using their own devices,

[1215] A means of analyzing the provided feedback using natural language processing technology and modifying business options,

[1216] A means to save the modified options back into the database and notify the user,

[1217] A system that includes this.

[1218] (Claim 2)

[1219] The system according to claim 1, comprising means for automatically generating the generated business options using a machine learning model.

[1220] (Claim 3)

[1221] The system according to claim 1, comprising means for analyzing the provided feedback using natural language processing technology.

[1222] "Application Example 1"

[1223] (Claim 1)

[1224] Means of collecting market data,

[1225] Means for analyzing collected market data,

[1226] A means of generating business options based on the analyzed data,

[1227] A means of saving the generated options to a database,

[1228] A means for users to view options and provide feedback,

[1229] A means of analyzing the feedback provided and modifying business options,

[1230] A means to save the modified options back into the database and notify the user,

[1231] A means of generating product proposals based on market trends,

[1232] A means of improving product suggestions based on user feedback,

[1233] A system that includes this.

[1234] (Claim 2)

[1235] The system according to claim 1, comprising means for automatically generating the generated business options using a machine learning model.

[1236] (Claim 3)

[1237] The system according to claim 1, comprising means for analyzing the provided feedback using natural language processing technology.

[1238] "Example 2 of combining an emotion engine"

[1239] (Claim 1)

[1240] Means of collecting market data,

[1241] Means for analyzing collected market data,

[1242] A means of generating business options based on the analyzed data,

[1243] A means of saving the generated options to a database,

[1244] A means for users to view options and provide feedback,

[1245] A means for analyzing the provided feedback using natural language processing technology and emotion recognition technology,

[1246] A means of modifying business options based on the analysis results,

[1247] A means to save the modified options back into the database and notify the user,

[1248] A system that includes this.

[1249] (Claim 2)

[1250] The system according to claim 1, comprising means for automatically generating the generated business options using a machine learning model and a generative AI model.

[1251] (Claim 3)

[1252] The system according to claim 1, comprising means for analyzing the provided feedback using natural language processing technology and for recognizing and analyzing emotions using an emotion engine.

[1253] "Application example 2 when combining with an emotional engine"

[1254] (Claim 1)

[1255] Means of collecting market information,

[1256] A means of analyzing collected market information,

[1257] A means of generating business options based on the analyzed information,

[1258] A means of storing the generated options in an information repository,

[1259] A means for users to view options and provide feedback, including emotional responses.

[1260] A means of analyzing the feedback provided, including emotions, and modifying business options,

[1261] A means of saving the modified options back to the information vault and notifying the user,

[1262] A system that includes this.

[1263] (Claim 2)

[1264] The system according to claim 1, comprising means for automatically generating the generated business options using a learning model.

[1265] (Claim 3)

[1266] The system according to claim 1, comprising means for analyzing the provided feedback using natural language processing technology and an emotion analysis engine. [Explanation of symbols]

[1267] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of collecting market data, Means for analyzing collected market data, A means of generating business options based on the analyzed data, A means of saving the generated options to a database, A means for users to view options and provide feedback, A means of analyzing the feedback provided and modifying business options, A means to save the modified options back into the database and notify the user, A system that includes this.

2. The system according to claim 1, comprising means for automatically generating the generated business options using a machine learning model.

3. The system according to claim 1, further comprising means for analyzing the provided feedback using natural language processing technology.

Images